diff --git a/.husky/pre-commit b/.husky/pre-commit
old mode 100644
new mode 100755
diff --git a/docs/toolhive/concepts/vmcp.mdx b/docs/toolhive/concepts/vmcp.mdx
index 4e53d216..93312dc5 100644
--- a/docs/toolhive/concepts/vmcp.mdx
+++ b/docs/toolhive/concepts/vmcp.mdx
@@ -161,9 +161,15 @@ MCPRemoteProxy backends into a single endpoint. The use cases range from simple
 aggregation to complex workflows with approval gates, making it valuable for
 teams managing multiple MCP servers.
 
+## Next steps
+
+- [Try the Quickstart](../guides-vmcp/quickstart.mdx) to deploy your first vMCP
+  on a Kubernetes cluster
+- [Learn how to deploy vMCP](../guides-vmcp/intro.mdx) for a full overview of
+  configuration and architecture
+
 ## Related information
 
-- [Deploy vMCP](../guides-vmcp/intro.mdx)
 - [Configure authentication](../guides-vmcp/authentication.mdx)
 - [Tool aggregation and conflict resolution](../guides-vmcp/tool-aggregation.mdx)
 - [Composite tools and workflows](../guides-vmcp/composite-tools.mdx)
diff --git a/docs/toolhive/faq.mdx b/docs/toolhive/faq.mdx
index 5a4d1fc6..2492d840 100644
--- a/docs/toolhive/faq.mdx
+++ b/docs/toolhive/faq.mdx
@@ -62,13 +62,13 @@ from the web using the
 [GoFetch MCP server](https://github.com/StacklokLabs/gofetch), and for popular
 services and platforms like:
 
-- **Atlassian** – Access Jira and Confluence
-- **AWS Documentation** – Query AWS service documentation
-- **GitHub** – Access repositories, issues, and pull requests
-- **Kubernetes** – Interact with Kubernetes clusters via the
+- **Atlassian** - Access Jira and Confluence
+- **AWS Documentation** - Query AWS service documentation
+- **GitHub** - Access repositories, issues, and pull requests
+- **Kubernetes** - Interact with Kubernetes clusters via the
   [MKP MCP server](https://github.com/StacklokLabs/mkp)
-- **MongoDB**, **PostgreSQL**, **Redis** – Connect to databases
-- **Notion** – Connect to Notion workspaces
+- **MongoDB**, **PostgreSQL**, **Redis** - Connect to databases
+- **Notion** - Connect to Notion workspaces
 - And many more
 
 ### Can I run MCP servers that aren't in the registry?
@@ -158,8 +158,8 @@ ToolHive provides secure secrets management:
 
 Yes. ToolHive uses permission profiles to control:
 
-- **File system access** – Which directories the server can read or write
-- **Network access** – Which hosts and ports the server can connect to
+- **File system access** - Which directories the server can read or write
+- **Network access** - Which hosts and ports the server can connect to
 
 You can use built-in profiles or create custom ones for specific security
 requirements.
@@ -213,21 +213,21 @@ Yes. ToolHive supports corporate environments with:
 
 ### Where can I get help if I'm stuck?
 
-- **Documentation** – Check the comprehensive guides and reference documentation
-- **GitHub Issues** – Report bugs or request features on the
+- **Documentation** - Check the comprehensive guides and reference documentation
+- **GitHub Issues** - Report bugs or request features on the
   [ToolHive GitHub repository](https://github.com/stacklok/toolhive/issues)
-- **Discord Community** – Join the
+- **Discord Community** - Join the
   [Stacklok Discord](https://discord.gg/stacklok) for community support
-- **Troubleshooting sections** – Each guide includes troubleshooting tips for
+- **Troubleshooting sections** - Each guide includes troubleshooting tips for
   common issues
 
 ### How do I report a bug or request a feature?
 
 Open an issue in the appropriate GitHub repository:
 
-- [**ToolHive UI**](https://github.com/stacklok/toolhive-studio/issues) – For
+- [**ToolHive UI**](https://github.com/stacklok/toolhive-studio/issues) - For
   issues specific to the graphical desktop app
-- [**ToolHive CLI & Kubernetes**](https://github.com/stacklok/toolhive/issues) –
+- [**ToolHive CLI & Kubernetes**](https://github.com/stacklok/toolhive/issues) -
   For issues related to the CLI tool or Kubernetes operator
 
 ### Is there a community I can join?
diff --git a/docs/toolhive/guides-cli/advanced-cicd.mdx b/docs/toolhive/guides-cli/advanced-cicd.mdx
index f803324f..5db353f8 100644
--- a/docs/toolhive/guides-cli/advanced-cicd.mdx
+++ b/docs/toolhive/guides-cli/advanced-cicd.mdx
@@ -310,9 +310,15 @@ When implementing advanced CI/CD patterns:
 6. **Implement change detection** to avoid unnecessary builds
 7. **Store sensitive data** in CI/CD secrets, not in code
 
+## Next steps
+
+- [Deploy to Kubernetes](../guides-k8s/run-mcp-k8s.mdx) to run your CI/CD-built
+  servers in production
+- [Aggregate multiple servers](../guides-vmcp/index.mdx) into a single endpoint
+  with Virtual MCP Server
+
 ## Related information
 
 - [Build MCP server containers](./build-containers.mdx)
-- [Run MCP servers in Kubernetes](../guides-k8s/run-mcp-k8s.mdx)
 - [`thv build` command reference](../reference/cli/thv_build.md)
 - [Secrets management](./secrets-management.mdx)
diff --git a/docs/toolhive/guides-cli/api-server.mdx b/docs/toolhive/guides-cli/api-server.mdx
index bf46742a..458acf6c 100644
--- a/docs/toolhive/guides-cli/api-server.mdx
+++ b/docs/toolhive/guides-cli/api-server.mdx
@@ -83,6 +83,12 @@ Open a browser to `http://localhost:8080/api/doc` to view the API documentation.
 The OpenAPI specification is also available at
 `http://localhost:8080/api/openapi.json`.
 
+## Next steps
+
+- [Secure your servers](./auth.mdx) with authentication and authorization
+- [Monitor server activity](./telemetry-and-metrics.mdx) with OpenTelemetry and
+  Prometheus
+
 ## Related information
 
 - [ToolHive API documentation](../reference/api.mdx)
diff --git a/docs/toolhive/guides-cli/auth.mdx b/docs/toolhive/guides-cli/auth.mdx
index d487daee..b1517c15 100644
--- a/docs/toolhive/guides-cli/auth.mdx
+++ b/docs/toolhive/guides-cli/auth.mdx
@@ -143,13 +143,22 @@ to perform an action, ToolHive will evaluate the request against the policies.
 If the request is permitted, the action will proceed; otherwise, it will be
 denied with a 403 Forbidden response.
 
+## Next steps
+
+- [Configure token exchange](./token-exchange.mdx) to let MCP servers
+  authenticate to backend services
+- [Enable telemetry and metrics](./telemetry-and-metrics.mdx) to gain
+  observability into MCP server interactions
+- [Learn about the auth framework](../concepts/auth-framework.mdx) for a deeper
+  understanding of ToolHive's authentication and authorization model
+
 ## Related information
 
-- For conceptual understanding, see
-  [Authentication and authorization framework](../concepts/auth-framework.mdx)
-- For detailed Cedar policy syntax, see
-  [Cedar policies](../concepts/cedar-policies.mdx) and the
-  [Cedar documentation](https://docs.cedarpolicy.com/)
+- [Authentication and authorization framework](../concepts/auth-framework.mdx)
+  for conceptual understanding
+- [Cedar policies](../concepts/cedar-policies.mdx) and the
+  [Cedar documentation](https://docs.cedarpolicy.com/) for detailed policy
+  syntax
 
 ## Troubleshooting
 
diff --git a/docs/toolhive/guides-cli/client-configuration.mdx b/docs/toolhive/guides-cli/client-configuration.mdx
index 8c3926ad..29dad8ec 100644
--- a/docs/toolhive/guides-cli/client-configuration.mdx
+++ b/docs/toolhive/guides-cli/client-configuration.mdx
@@ -148,6 +148,12 @@ Example output:
 Configure your client or library to connect to the MCP server using the URL
 ToolHive provides.
 
+## Next steps
+
+- [Set up custom permissions](./custom-permissions.mdx) to control filesystem
+  and network access for your servers
+- [Secure your servers](./auth.mdx) with OIDC authentication and Cedar policies
+
 ## Related information
 
 - [`thv client` command reference](../reference/cli/thv_client.md)
diff --git a/docs/toolhive/guides-cli/custom-permissions.mdx b/docs/toolhive/guides-cli/custom-permissions.mdx
index 2fa313fa..cdad21dd 100644
--- a/docs/toolhive/guides-cli/custom-permissions.mdx
+++ b/docs/toolhive/guides-cli/custom-permissions.mdx
@@ -229,6 +229,11 @@ When creating and using permission profiles:
 - Keep permission profiles in version control to track changes and share them
   with your team
 
+## Next steps
+
+- [Set up authentication](./auth.mdx) for user-level access control with OIDC
+  and Cedar policies
+
 ## Related information
 
 - [`thv run` command reference](../reference/cli/thv_run.md)
diff --git a/docs/toolhive/guides-cli/filesystem-access.mdx b/docs/toolhive/guides-cli/filesystem-access.mdx
index 23cce9c1..51d57243 100644
--- a/docs/toolhive/guides-cli/filesystem-access.mdx
+++ b/docs/toolhive/guides-cli/filesystem-access.mdx
@@ -217,6 +217,13 @@ container, use the server's `--db` flag to specify the new path:
 thv run --volume ~/my-database.db:/data/my-database.db sqlite -- --db /data/my-database.db
 ```
 
+## Next steps
+
+- [Exclude sensitive files](./thvignore.mdx) from MCP server access with
+  `.thvignore`
+- [Restrict network access](./network-isolation.mdx) to control outbound
+  connections
+
 ## Related information
 
 - [`thv run` command reference](../reference/cli/thv_run.md)
diff --git a/docs/toolhive/guides-cli/group-management.mdx b/docs/toolhive/guides-cli/group-management.mdx
index 2218bef9..bfdf1d35 100644
--- a/docs/toolhive/guides-cli/group-management.mdx
+++ b/docs/toolhive/guides-cli/group-management.mdx
@@ -120,9 +120,14 @@ Using `--with-workloads` permanently deletes all servers in the group.
 
 :::
 
+## Next steps
+
+- [Configure your AI client](./client-configuration.mdx) to connect to your
+  server groups
+- [Manage secrets](./secrets-management.mdx) for the MCP servers in your groups
+
 ## Related information
 
-- [Client configuration](client-configuration.mdx)
 - [Run MCP servers](run-mcp-servers.mdx)
 - [`thv group` command reference](../reference/cli/thv_group.md)
 - [`thv client` command reference](../reference/cli/thv_client.md)
diff --git a/docs/toolhive/guides-cli/manage-mcp-servers.mdx b/docs/toolhive/guides-cli/manage-mcp-servers.mdx
index 35ab0aa9..e55a0c98 100644
--- a/docs/toolhive/guides-cli/manage-mcp-servers.mdx
+++ b/docs/toolhive/guides-cli/manage-mcp-servers.mdx
@@ -151,6 +151,15 @@ thv start <REMOTE_SERVER_NAME>
 
 This will always prompt for re-authentication, even if valid tokens exist.
 
+## Next steps
+
+- [Organize servers into groups](./group-management.mdx) to manage related
+  servers together
+- [Monitor server activity](./telemetry-and-metrics.mdx) with OpenTelemetry and
+  Prometheus
+- [Configure your AI client](./client-configuration.mdx) to connect to your
+  servers
+
 ## Related information
 
 - [`thv list` command reference](../reference/cli/thv_list.md)
@@ -158,4 +167,3 @@ This will always prompt for re-authentication, even if valid tokens exist.
 - [`thv stop` command reference](../reference/cli/thv_stop.md)
 - [`thv start` command reference](../reference/cli/thv_start.md)
 - [`thv rm` command reference](../reference/cli/thv_rm.md)
-- [Monitor with OpenTelemetry](../guides-cli/telemetry-and-metrics.mdx)
diff --git a/docs/toolhive/guides-cli/network-isolation.mdx b/docs/toolhive/guides-cli/network-isolation.mdx
index 2375ba07..7d768bed 100644
--- a/docs/toolhive/guides-cli/network-isolation.mdx
+++ b/docs/toolhive/guides-cli/network-isolation.mdx
@@ -318,6 +318,11 @@ default behavior of allowing traffic only from the container's own hostname,
 
 :::
 
+## Next steps
+
+- [Set up authentication](./auth.mdx) for user-level access control with OIDC
+  and Cedar policies
+
 ## Related information
 
 - [`thv run` command reference](../reference/cli/thv_run.md)
diff --git a/docs/toolhive/guides-cli/run-mcp-servers.mdx b/docs/toolhive/guides-cli/run-mcp-servers.mdx
index f7a1ada3..bd3564e3 100644
--- a/docs/toolhive/guides-cli/run-mcp-servers.mdx
+++ b/docs/toolhive/guides-cli/run-mcp-servers.mdx
@@ -888,11 +888,14 @@ The configuration file must contain all server settings.
 
 ## Next steps
 
-See [Monitor and manage MCP servers](./manage-mcp-servers.mdx) to monitor and
-control your servers.
-
-[Test your MCP server](./test-mcp-servers.mdx) using the MCP Inspector or
-`thv mcp` commands.
+- [Monitor and manage MCP servers](./manage-mcp-servers.mdx) to control your
+  running servers
+- [Test your MCP servers](./test-mcp-servers.mdx) using the MCP Inspector or
+  `thv mcp` commands
+- [Secure your servers](./auth.mdx) with OIDC authentication and Cedar policies
+- [Enable telemetry and metrics](./telemetry-and-metrics.mdx) to gain
+  observability into MCP server interactions
+- [Run the API server](./api-server.mdx) for programmatic access to ToolHive
 
 ## Related information
 
diff --git a/docs/toolhive/guides-cli/secrets-management.mdx b/docs/toolhive/guides-cli/secrets-management.mdx
index e7cccf9f..27abdfce 100644
--- a/docs/toolhive/guides-cli/secrets-management.mdx
+++ b/docs/toolhive/guides-cli/secrets-management.mdx
@@ -267,10 +267,17 @@ This command retrieves the `token` and `team_id` fields from the `slackbot` item
 in the `MCPVault` vault and passes them to the `slack` MCP server as the
 `SLACK_BOT_TOKEN` and `SLACK_TEAM_ID` environment variables.
 
+## Next steps
+
+- [Configure your AI client](./client-configuration.mdx) to connect to your
+  servers
+- [Set up custom permissions](./custom-permissions.mdx) to control filesystem
+  and network access
+
 ## Related information
 
 - [`thv secret` command reference](../reference/cli/thv_secret.md)
-- [Run MCP servers](../guides-cli/run-mcp-servers.mdx)
+- [Run MCP servers](./run-mcp-servers.mdx)
 
 ## Troubleshooting
 
diff --git a/docs/toolhive/guides-cli/telemetry-and-metrics.mdx b/docs/toolhive/guides-cli/telemetry-and-metrics.mdx
index 16e6335a..78ad3e52 100644
--- a/docs/toolhive/guides-cli/telemetry-and-metrics.mdx
+++ b/docs/toolhive/guides-cli/telemetry-and-metrics.mdx
@@ -406,6 +406,15 @@ Telemetry adds minimal overhead when properly configured:
 - Use appropriate sampling rates for your traffic volume
 - Monitor your observability backend costs and adjust sampling accordingly
 
+## Next steps
+
+- [Learn about ToolHive's observability model](../concepts/observability.mdx)
+  for a deeper understanding of the telemetry architecture
+- [Monitor and manage MCP servers](./manage-mcp-servers.mdx) for server
+  lifecycle management including logs and status monitoring
+- [Collect telemetry for MCP workloads](../integrations/opentelemetry.mdx) for a
+  hands-on tutorial with an OpenTelemetry Collector
+
 ## Related information
 
 - Tutorial:
diff --git a/docs/toolhive/guides-cli/test-mcp-servers.mdx b/docs/toolhive/guides-cli/test-mcp-servers.mdx
index 37b70a69..602ea931 100644
--- a/docs/toolhive/guides-cli/test-mcp-servers.mdx
+++ b/docs/toolhive/guides-cli/test-mcp-servers.mdx
@@ -89,6 +89,14 @@ and see how your MCP server responds to various prompts.
 See [Test MCP servers in the ToolHive UI](../guides-ui/playground.mdx) to learn
 about the playground's features and how to get started.
 
+## Next steps
+
+- [Build MCP containers](./build-containers.mdx) to package your tested servers
+  for deployment
+- [Set up CI/CD patterns](./advanced-cicd.mdx) to automate testing in your
+  pipeline
+- [Secure your servers](./auth.mdx) with authentication and authorization
+
 ## Related information
 
 - [`thv inspector` command reference](../reference/cli/thv_inspector.md)
diff --git a/docs/toolhive/guides-cli/thvignore.mdx b/docs/toolhive/guides-cli/thvignore.mdx
index 90f50ba3..37fe16a3 100644
--- a/docs/toolhive/guides-cli/thvignore.mdx
+++ b/docs/toolhive/guides-cli/thvignore.mdx
@@ -128,6 +128,11 @@ example, `.env*`, build artifacts) in your project's local `.thvignore`.
 
 </details>
 
+## Next steps
+
+- [Restrict network access](./network-isolation.mdx) to control outbound
+  connections from MCP servers
+
 ## Related information
 
 - [File system access](./filesystem-access.mdx)
diff --git a/docs/toolhive/guides-cli/token-exchange.mdx b/docs/toolhive/guides-cli/token-exchange.mdx
index 72a86409..cd9d7cba 100644
--- a/docs/toolhive/guides-cli/token-exchange.mdx
+++ b/docs/toolhive/guides-cli/token-exchange.mdx
@@ -200,6 +200,12 @@ Key points in this example:
   (`api:read`, `api:write`). The user's identity is preserved, but the
   permissions are transformed for the target service.
 
+## Next steps
+
+- [Monitor server activity](./telemetry-and-metrics.mdx) with OpenTelemetry and
+  Prometheus
+- [Test your MCP servers](./test-mcp-servers.mdx) to validate your configuration
+
 ## Related information
 
 - [Backend authentication](../concepts/backend-auth.mdx) - conceptual overview
diff --git a/docs/toolhive/guides-k8s/auth-k8s.mdx b/docs/toolhive/guides-k8s/auth-k8s.mdx
index 20fcd4ec..f88a4f2e 100644
--- a/docs/toolhive/guides-k8s/auth-k8s.mdx
+++ b/docs/toolhive/guides-k8s/auth-k8s.mdx
@@ -476,7 +476,7 @@ kubectl apply -f embedded-auth-config.yaml
 
 The MCPServer needs two configuration references: `externalAuthConfigRef`
 enables the embedded authorization server, and `oidcConfig` validates the JWTs
-that the embedded authorization server issues. Unlike approaches 1–3 where
+that the embedded authorization server issues. Unlike approaches 1-3 where
 `oidcConfig` points to an external identity provider, here it points to the
 embedded authorization server itself—the `oidcConfig` issuer must match the
 `issuer` in your `MCPExternalAuthConfig`.
@@ -760,6 +760,13 @@ kubectl logs -n toolhive-system -l app.kubernetes.io/name=weather-server-k8s
 2. Make requests that should be denied
 3. Check the proxy logs to see authorization decisions
 
+## Next steps
+
+- [Configure token exchange](./token-exchange-k8s.mdx) to let MCP servers
+  authenticate to backend services
+- [Set up audit logging](./logging.mdx) to track authentication decisions and
+  MCP server activity
+
 ## Related information
 
 - For conceptual understanding, see
diff --git a/docs/toolhive/guides-k8s/customize-tools.mdx b/docs/toolhive/guides-k8s/customize-tools.mdx
index c176fd09..00aaaf1a 100644
--- a/docs/toolhive/guides-k8s/customize-tools.mdx
+++ b/docs/toolhive/guides-k8s/customize-tools.mdx
@@ -234,6 +234,12 @@ kubectl -n toolhive-system get mcpserver github -o yaml
 - If an MCPServer references a missing MCPToolConfig, the server enters Failed
   and the controller logs include the missing name and namespace.
 
+## Next steps
+
+- [Secure your servers](./auth-k8s.mdx) with authentication and authorization
+- [Monitor server activity](./telemetry-and-metrics.mdx) with OpenTelemetry and
+  Prometheus
+
 ## Related information
 
 - See the
diff --git a/docs/toolhive/guides-k8s/deploy-operator.mdx b/docs/toolhive/guides-k8s/deploy-operator.mdx
index 7f586d00..6c117814 100644
--- a/docs/toolhive/guides-k8s/deploy-operator.mdx
+++ b/docs/toolhive/guides-k8s/deploy-operator.mdx
@@ -440,10 +440,9 @@ kubectl delete namespace toolhive-system
 
 ## Next steps
 
-See [Run MCP servers in Kubernetes](./run-mcp-k8s.mdx) to learn how to create
-and manage MCP servers using the ToolHive operator in your Kubernetes cluster.
-The operator supports deploying MCPServer resources based on the deployment mode
-configured during installation.
+- [Run MCP servers in Kubernetes](./run-mcp-k8s.mdx) to create and manage MCP
+  servers using the ToolHive operator
+- [Configure authentication](./auth-k8s.mdx) before exposing servers externally
 
 ## Related information
 
diff --git a/docs/toolhive/guides-k8s/redis-session-storage.mdx b/docs/toolhive/guides-k8s/redis-session-storage.mdx
index aaf3e845..35ac2909 100644
--- a/docs/toolhive/guides-k8s/redis-session-storage.mdx
+++ b/docs/toolhive/guides-k8s/redis-session-storage.mdx
@@ -595,6 +595,13 @@ session storage is working correctly.
 
 </details>
 
+## Next steps
+
+- [Configure token exchange](./token-exchange-k8s.mdx) to let MCP servers
+  authenticate to backend services
+- [Monitor server activity](./telemetry-and-metrics.mdx) with OpenTelemetry and
+  Prometheus
+
 ## Related information
 
 - [Set up embedded authorization server authentication](./auth-k8s.mdx#set-up-embedded-authorization-server-authentication)
diff --git a/docs/toolhive/guides-k8s/run-mcp-k8s.mdx b/docs/toolhive/guides-k8s/run-mcp-k8s.mdx
index 339d6f9c..2d04e672 100644
--- a/docs/toolhive/guides-k8s/run-mcp-k8s.mdx
+++ b/docs/toolhive/guides-k8s/run-mcp-k8s.mdx
@@ -441,22 +441,15 @@ kubectl -n <NAMESPACE> describe mcpserver <NAME>
 
 ## Next steps
 
-Learn how to [connect clients to your MCP servers](./connect-clients.mdx) from
-outside the cluster using Ingress or Gateway API, or from applications running
-within the cluster. See the
-[Client compatibility](../reference/client-compatibility.mdx) reference for
-information about supported MCP clients.
-
-Learn how to customize MCP tools using
-[filters and overrides](./customize-tools.mdx).
-
-Collect telemetry data from your MCP servers by following the
-[Telemetry and metrics](./telemetry-and-metrics.mdx) guide. Configure audit
-logging by following the [Set up logging](./logging.mdx) guide.
-
-Discover your deployed MCP servers automatically using the
-[Kubernetes registry](../guides-registry/configuration.mdx#kubernetes-registry)
-feature in the ToolHive Registry Server.
+- [Connect clients to your MCP servers](./connect-clients.mdx) from outside the
+  cluster using Ingress or Gateway API, or from within the cluster
+- [Secure your servers](./auth-k8s.mdx) with OIDC authentication and Cedar
+  policies
+- [Customize MCP tools](./customize-tools.mdx) with filters and overrides
+- [Aggregate multiple servers](../guides-vmcp/index.mdx) into a single endpoint
+  with Virtual MCP Server
+- [Curate a server catalog](../guides-registry/index.mdx) for your team with the
+  Registry Server
 
 ## Related information
 
diff --git a/docs/toolhive/guides-k8s/telemetry-and-metrics.mdx b/docs/toolhive/guides-k8s/telemetry-and-metrics.mdx
index 232da38a..f2ce9421 100644
--- a/docs/toolhive/guides-k8s/telemetry-and-metrics.mdx
+++ b/docs/toolhive/guides-k8s/telemetry-and-metrics.mdx
@@ -275,12 +275,18 @@ Telemetry adds minimal overhead when properly configured:
 - Use appropriate sampling rates for your traffic volume
 - Monitor your observability backend costs and adjust sampling accordingly
 
+## Next steps
+
+- [Set up audit logging](./logging.mdx) for structured request and authorization
+  event tracking
+- [Secure your servers](./auth-k8s.mdx) with authentication and authorization
+
 ## Related information
 
 - Tutorial:
   [Collect telemetry for MCP workloads](../integrations/opentelemetry.mdx) -
-  Step-by-step guide to set up a local observability stack
-- [Telemetry and monitoring concepts](../concepts/observability.mdx) - Overview
+  step-by-step guide to set up a local observability stack
+- [Telemetry and monitoring concepts](../concepts/observability.mdx) - overview
   of ToolHive's observability architecture
 - [Kubernetes CRD reference](../reference/crd-spec.md#apiv1alpha1mcpserver) -
   Reference for the `MCPServer` Custom Resource Definition (CRD)
diff --git a/docs/toolhive/guides-k8s/token-exchange-k8s.mdx b/docs/toolhive/guides-k8s/token-exchange-k8s.mdx
index 1befe9ff..aa666bc2 100644
--- a/docs/toolhive/guides-k8s/token-exchange-k8s.mdx
+++ b/docs/toolhive/guides-k8s/token-exchange-k8s.mdx
@@ -251,6 +251,13 @@ Key points in this example:
   user's identity is preserved, but the permissions are transformed for the
   target service.
 
+## Next steps
+
+- [Monitor server activity](./telemetry-and-metrics.mdx) with OpenTelemetry and
+  Prometheus
+- [Set up audit logging](./logging.mdx) to track requests and authentication
+  decisions
+
 ## Related information
 
 - [Backend authentication](../concepts/backend-auth.mdx) - conceptual overview
diff --git a/docs/toolhive/guides-registry/authentication.mdx b/docs/toolhive/guides-registry/authentication.mdx
index b98377b2..f0101226 100644
--- a/docs/toolhive/guides-registry/authentication.mdx
+++ b/docs/toolhive/guides-registry/authentication.mdx
@@ -547,6 +547,6 @@ If tokens from some providers work but others don't:
 
 ## Next steps
 
-- [Configure database storage](./database.mdx) for production deployments
-- [Deploy the server](./deployment.mdx) with authentication enabled
-- [Configure registry sources](./configuration.mdx) for your environment
+- [Set up the database](./database.mdx) for production storage and migrations
+- [Configure telemetry](./telemetry-metrics.mdx) for distributed tracing and
+  metrics collection
diff --git a/docs/toolhive/guides-registry/configuration.mdx b/docs/toolhive/guides-registry/configuration.mdx
index ebd9bae1..99cc52f2 100644
--- a/docs/toolhive/guides-registry/configuration.mdx
+++ b/docs/toolhive/guides-registry/configuration.mdx
@@ -522,7 +522,6 @@ distributed tracing and metrics collection. See the
 
 ## Next steps
 
-- [Configure authentication](./authentication.mdx) for secure access
-- [Configure telemetry](./telemetry-metrics.mdx) for metrics and tracing
-- [Deploy the server](./deployment.mdx) with your configuration
-- [Configure database storage](./database.mdx)
+- [Configure authentication](./authentication.mdx) to secure access to your
+  registry
+- [Set up the database](./database.mdx) for production storage
diff --git a/docs/toolhive/guides-registry/database.mdx b/docs/toolhive/guides-registry/database.mdx
index 24d19b1b..a8cfa5ab 100644
--- a/docs/toolhive/guides-registry/database.mdx
+++ b/docs/toolhive/guides-registry/database.mdx
@@ -306,5 +306,6 @@ If you see permission errors during normal operations:
 
 ## Next steps
 
-- [Deploy the server](./deployment.mdx) with database configuration
-- [Configure data sources](./configuration.mdx) to populate the registry
+- [Configure telemetry](./telemetry-metrics.mdx) for distributed tracing and
+  metrics collection
+- [Deploy the server](./deployment.mdx) to your Kubernetes environment
diff --git a/docs/toolhive/guides-registry/deploy-manual.mdx b/docs/toolhive/guides-registry/deploy-manual.mdx
index 50166a3f..c1fbeeac 100644
--- a/docs/toolhive/guides-registry/deploy-manual.mdx
+++ b/docs/toolhive/guides-registry/deploy-manual.mdx
@@ -360,3 +360,11 @@ each instance to avoid leader election lease conflicts. The Helm chart handles
 this automatically.
 
 :::
+
+## Next steps
+
+- [Configure registry sources](./configuration.mdx) to set up your data sources
+  and sync policies
+- [Set up authentication](./authentication.mdx) to secure access to your
+  registry
+- [Configure telemetry](./telemetry-metrics.mdx) to monitor your deployment
diff --git a/docs/toolhive/guides-registry/deployment.mdx b/docs/toolhive/guides-registry/deployment.mdx
index 8a93e939..81d3b029 100644
--- a/docs/toolhive/guides-registry/deployment.mdx
+++ b/docs/toolhive/guides-registry/deployment.mdx
@@ -32,3 +32,11 @@ Deploy the Registry Server directly using raw Kubernetes manifests. This
 approach gives you full control over the deployment configuration.
 
 See [Deploy manually](./deploy-manual.mdx) for instructions.
+
+## Next steps
+
+- [Configure registry sources](./configuration.mdx) to set up your data sources
+  and sync policies
+- [Set up authentication](./authentication.mdx) to secure access to your
+  registry
+- [Configure telemetry](./telemetry-metrics.mdx) to monitor your deployment
diff --git a/docs/toolhive/guides-registry/intro.mdx b/docs/toolhive/guides-registry/intro.mdx
index 022207cf..62902b3d 100644
--- a/docs/toolhive/guides-registry/intro.mdx
+++ b/docs/toolhive/guides-registry/intro.mdx
@@ -114,8 +114,10 @@ The server supports five registry source types:
 
 ## Next steps
 
-- [Configure registry sources](./configuration.mdx) to set up your registry
-- [Deploy the server](./deployment.mdx) in your environment
+- [Configure registry sources](./configuration.mdx) to set up your data sources,
+  sync policies, and server filtering
+- [Set up authentication](./authentication.mdx) to secure access to your
+  registry
 - [Manage skills](./skills.mdx) to publish and discover reusable skills
 - [View the API reference](../reference/registry-api.mdx) for endpoint
   documentation
diff --git a/docs/toolhive/guides-registry/skills.mdx b/docs/toolhive/guides-registry/skills.mdx
index 850c2e72..c727ca7b 100644
--- a/docs/toolhive/guides-registry/skills.mdx
+++ b/docs/toolhive/guides-registry/skills.mdx
@@ -189,14 +189,18 @@ The API returns standard HTTP status codes:
 | 409  | Version already exists                                        |
 | 500  | Internal server error                                         |
 
-## What's next
+## Next steps
 
 Skill installation via agent clients (such as the ToolHive CLI or IDE
 extensions) is planned for a future release. For now, the registry serves as a
 discovery and distribution layer.
 
-- [Understanding skills](../concepts/skills.mdx) for background on the skills
+- [Configure telemetry](./telemetry-metrics.mdx) to monitor your registry
+  deployment
+
+## Related information
+
+- [Understanding skills](../concepts/skills.mdx) - background on the skills
   model
-- [Registry server introduction](./intro.mdx) for an overview of the Registry
-  server
-- [Authentication](./authentication.mdx) for configuring API access
+- [Registry server introduction](./intro.mdx)
+- [Authentication](./authentication.mdx) - configuring API access
diff --git a/docs/toolhive/guides-registry/telemetry-metrics.mdx b/docs/toolhive/guides-registry/telemetry-metrics.mdx
index eb7d3e73..aa3ba82f 100644
--- a/docs/toolhive/guides-registry/telemetry-metrics.mdx
+++ b/docs/toolhive/guides-registry/telemetry-metrics.mdx
@@ -180,6 +180,6 @@ metrics still capture latency and error rates for these endpoints.
 
 ## Next steps
 
-- [Configure the Registry Server](./configuration.mdx) with your registries
-- [Deploy the server](./deployment.mdx) to your environment
-- [Configure authentication](./authentication.mdx) for secure access
+- [Deploy the server](./deployment.mdx) to your Kubernetes environment
+- [Manage skills](./skills.mdx) to publish and discover reusable skills in your
+  registry
diff --git a/docs/toolhive/guides-ui/cli-access.mdx b/docs/toolhive/guides-ui/cli-access.mdx
index 0033e23e..3820c097 100644
--- a/docs/toolhive/guides-ui/cli-access.mdx
+++ b/docs/toolhive/guides-ui/cli-access.mdx
@@ -133,6 +133,12 @@ the error message and resolution steps.
 
 </details>
 
+## Next steps
+
+- [Run MCP servers](./run-mcp-servers.mdx) from the ToolHive UI
+- Explore the full [CLI guides](../guides-cli/index.mdx) for terminal-based
+  workflows
+
 ## Related information
 
 - [CLI guides](../guides-cli/index.mdx)
diff --git a/docs/toolhive/guides-ui/client-configuration.mdx b/docs/toolhive/guides-ui/client-configuration.mdx
index c0d539b9..2a02c240 100644
--- a/docs/toolhive/guides-ui/client-configuration.mdx
+++ b/docs/toolhive/guides-ui/client-configuration.mdx
@@ -78,6 +78,12 @@ your client or library, so refer to its documentation for details. See the
 [client configuration reference](../reference/client-compatibility.mdx#manual-configuration)
 for some common examples.
 
+## Next steps
+
+- Test your setup in the [Playground](./playground.mdx)
+- [Customize which tools](./customize-tools.mdx) each server exposes to your AI
+  clients
+
 ## Related information
 
 - [Client compatibility](../reference/client-compatibility.mdx)
diff --git a/docs/toolhive/guides-ui/customize-tools.mdx b/docs/toolhive/guides-ui/customize-tools.mdx
index 220b5bd7..ee66e08f 100644
--- a/docs/toolhive/guides-ui/customize-tools.mdx
+++ b/docs/toolhive/guides-ui/customize-tools.mdx
@@ -194,6 +194,12 @@ icon is removed.
 1. Manually enable all tools using the toggle switches.
 1. Click **Apply** to save your changes.
 
+## Next steps
+
+- Try out your customized tools in the [Playground](./playground.mdx)
+- [Configure client access](./client-configuration.mdx) to connect your AI
+  clients to ToolHive
+
 ## Related information
 
 - [Run MCP servers](./run-mcp-servers.mdx)
diff --git a/docs/toolhive/guides-ui/group-management.mdx b/docs/toolhive/guides-ui/group-management.mdx
index dca3454a..2b1aff84 100644
--- a/docs/toolhive/guides-ui/group-management.mdx
+++ b/docs/toolhive/guides-ui/group-management.mdx
@@ -151,6 +151,14 @@ environments:
 3. Configure different AI clients or workspaces to access the appropriate groups
    for each project.
 
+## Next steps
+
+- [Manage secrets](./secrets-management.mdx) for the MCP servers in your groups
+- [Customize which tools](./customize-tools.mdx) each server exposes to your AI
+  clients
+- [Configure client access](./client-configuration.mdx) to connect your AI
+  clients to ToolHive
+
 ## Related information
 
 - [Run MCP servers](./run-mcp-servers.mdx)
diff --git a/docs/toolhive/guides-ui/mcp-optimizer.mdx b/docs/toolhive/guides-ui/mcp-optimizer.mdx
index e54d990c..b0a7bb56 100644
--- a/docs/toolhive/guides-ui/mcp-optimizer.mdx
+++ b/docs/toolhive/guides-ui/mcp-optimizer.mdx
@@ -114,8 +114,15 @@ If you encounter issues while using the MCP Optimizer, check the logs for
 debugging information. On the **MCP Optimizer** page, click the **Advanced**
 menu and select **MCP Optimizer logs**.
 
+## Next steps
+
+- Try the [Playground](./playground.mdx) to test your optimized tool set
+- [Organize MCP servers into groups](./group-management.mdx) to control which
+  servers the optimizer includes
+
 ## Related information
 
 - Tutorial:
   [Reduce token usage with MCP Optimizer](../tutorials/mcp-optimizer.mdx)
-- [Organize MCP servers into groups](./group-management.mdx)
+- [Optimizing LLM context](../concepts/tool-optimization.mdx) - background on
+  tool filtering and context pollution
diff --git a/docs/toolhive/guides-ui/network-isolation.mdx b/docs/toolhive/guides-ui/network-isolation.mdx
index 89c53566..842b58ca 100644
--- a/docs/toolhive/guides-ui/network-isolation.mdx
+++ b/docs/toolhive/guides-ui/network-isolation.mdx
@@ -96,6 +96,13 @@ containers.
 - **Allowed hosts**: `host.docker.internal`
 - **Allowed ports**: `3000`
 
+## Next steps
+
+- [Customize which tools](./customize-tools.mdx) each server exposes to your AI
+  clients
+- [Configure client access](./client-configuration.mdx) to connect your AI
+  clients to ToolHive
+
 ## Related information
 
 - [Run MCP servers](./run-mcp-servers.mdx)
diff --git a/docs/toolhive/guides-ui/secrets-management.mdx b/docs/toolhive/guides-ui/secrets-management.mdx
index 85dbf031..d19296bd 100644
--- a/docs/toolhive/guides-ui/secrets-management.mdx
+++ b/docs/toolhive/guides-ui/secrets-management.mdx
@@ -57,6 +57,13 @@ using the same name.
 
 :::
 
+## Next steps
+
+- [Restrict network access](./network-isolation.mdx) for your MCP servers to
+  improve security
+- [Configure client access](./client-configuration.mdx) to connect your AI
+  clients to ToolHive
+
 ## Related information
 
 - [Run MCP servers](./run-mcp-servers.mdx)
diff --git a/docs/toolhive/guides-vmcp/audit-logging.mdx b/docs/toolhive/guides-vmcp/audit-logging.mdx
index 3ff13e1e..3400a4c6 100644
--- a/docs/toolhive/guides-vmcp/audit-logging.mdx
+++ b/docs/toolhive/guides-vmcp/audit-logging.mdx
@@ -398,13 +398,18 @@ For detailed configuration examples and best practices for setting up log
 collection with Fluentd, Filebeat, Splunk, and other systems, see the
 [Kubernetes logging guide](../guides-k8s/logging.mdx#set-up-log-collection).
 
+## Next steps
+
+- [Review the vMCP configuration guide](./configuration.mdx) to revisit or
+  refine your VirtualMCPServer setup
+- [Learn about ToolHive's observability model](../concepts/observability.mdx)
+  for a deeper understanding of the telemetry architecture
+
 ## Related information
 
-- [Authentication](./authentication.mdx) - Configure client and backend
+- [Authentication](./authentication.mdx) - configure client and backend
   authentication for user identity in audit logs
-- [Telemetry and metrics](./telemetry-and-metrics.mdx) - Monitor vMCP
+- [Telemetry and metrics](./telemetry-and-metrics.mdx) - monitor vMCP
   performance with OpenTelemetry
-- [Observability concepts](../concepts/observability.mdx) - Overview of
-  ToolHive's observability architecture
-- [Kubernetes logging guide](../guides-k8s/logging.mdx) - Configure logging for
+- [Kubernetes logging guide](../guides-k8s/logging.mdx) - configure logging for
   MCP servers in Kubernetes
diff --git a/docs/toolhive/guides-vmcp/authentication.mdx b/docs/toolhive/guides-vmcp/authentication.mdx
index 4a2c9036..e116d87d 100644
--- a/docs/toolhive/guides-vmcp/authentication.mdx
+++ b/docs/toolhive/guides-vmcp/authentication.mdx
@@ -157,8 +157,16 @@ See
 [Configure token exchange for backend authentication](../guides-k8s/token-exchange-k8s.mdx)
 for details on using service account token exchange for backend authentication.
 
+## Next steps
+
+- [Configure tool aggregation](./tool-aggregation.mdx) to manage how tools from
+  multiple backends are presented to clients
+- [Set up audit logging](./audit-logging.mdx) to track authentication decisions
+  and request activity
+
 ## Related information
 
 - [Authentication framework concepts](../concepts/auth-framework.mdx)
+- [Cedar policies](../concepts/cedar-policies.mdx) for detailed policy syntax
 - [VirtualMCPServer configuration](./configuration.mdx)
 - [Token exchange in Kubernetes](../guides-k8s/token-exchange-k8s.mdx)
diff --git a/docs/toolhive/guides-vmcp/backend-discovery.mdx b/docs/toolhive/guides-vmcp/backend-discovery.mdx
index 96dc5f12..1e2e8065 100644
--- a/docs/toolhive/guides-vmcp/backend-discovery.mdx
+++ b/docs/toolhive/guides-vmcp/backend-discovery.mdx
@@ -728,8 +728,14 @@ remove the auth reference.
 
 </details>
 
+## Next steps
+
+- [Set up authentication](./authentication.mdx) for client-to-vMCP and
+  vMCP-to-backend security
+- [Configure tool aggregation](./tool-aggregation.mdx) to manage how tools from
+  multiple backends are presented to clients
+
 ## Related information
 
 - [Configure vMCP servers](./configuration.mdx)
-- [Authentication](./authentication.mdx)
 - [VirtualMCPServer CRD specification](../reference/crd-spec.md#apiv1alpha1virtualmcpserver)
diff --git a/docs/toolhive/guides-vmcp/composite-tools.mdx b/docs/toolhive/guides-vmcp/composite-tools.mdx
index ed26ca53..41f178fc 100644
--- a/docs/toolhive/guides-vmcp/composite-tools.mdx
+++ b/docs/toolhive/guides-vmcp/composite-tools.mdx
@@ -638,6 +638,11 @@ spec:
       - name: another-workflow
 ```
 
+## Next steps
+
+- [Configure failure handling](./failure-handling.mdx) for circuit breakers and
+  partial failure modes in multi-backend setups
+
 ## Related information
 
 - [Configure vMCP servers](./configuration.mdx)
diff --git a/docs/toolhive/guides-vmcp/configuration.mdx b/docs/toolhive/guides-vmcp/configuration.mdx
index 3c2f6505..c06c48a1 100644
--- a/docs/toolhive/guides-vmcp/configuration.mdx
+++ b/docs/toolhive/guides-vmcp/configuration.mdx
@@ -279,13 +279,14 @@ Backend discovery guide.
 
 ## Next steps
 
-- [Optimize tool discovery](./optimizer.mdx) by adding an `embeddingServerRef`
-  to reduce token usage across many backends
-- Review [scaling and performance guidance](./scaling-and-performance.mdx) for
-  resource planning
-- Discover your deployed MCP servers automatically using the
-  [Kubernetes registry](../guides-registry/configuration.mdx#kubernetes-registry)
-  feature in the ToolHive Registry Server
+- [Configure backend discovery](./backend-discovery.mdx) to control how vMCP
+  finds and connects to MCP servers
+- [Set up authentication](./authentication.mdx) for client-to-vMCP and
+  vMCP-to-backend security
+- [Configure failure handling](./failure-handling.mdx) for circuit breakers and
+  partial failure modes
+- [Monitor vMCP activity](./telemetry-and-metrics.mdx) with OpenTelemetry
+  tracing and metrics
 
 ## Related information
 
diff --git a/docs/toolhive/guides-vmcp/failure-handling.mdx b/docs/toolhive/guides-vmcp/failure-handling.mdx
index df6b533e..9cdc4fd2 100644
--- a/docs/toolhive/guides-vmcp/failure-handling.mdx
+++ b/docs/toolhive/guides-vmcp/failure-handling.mdx
@@ -409,9 +409,15 @@ operational:
 
 </details>
 
+## Next steps
+
+- [Monitor vMCP activity](./telemetry-and-metrics.mdx) with OpenTelemetry
+  tracing and metrics
+- [Set up audit logging](./audit-logging.mdx) to track requests and failures
+
 ## Related information
 
-- [Backend discovery modes](./backend-discovery.mdx) - Backend health status and
+- [Backend discovery modes](./backend-discovery.mdx) - backend health status and
   `/status` endpoint
 - [Configuration guide](./configuration.mdx)
 - [VirtualMCPServer CRD specification](../reference/crd-spec.md#apiv1alpha1virtualmcpserver)
diff --git a/docs/toolhive/guides-vmcp/intro.mdx b/docs/toolhive/guides-vmcp/intro.mdx
index a179145c..f1454054 100644
--- a/docs/toolhive/guides-vmcp/intro.mdx
+++ b/docs/toolhive/guides-vmcp/intro.mdx
@@ -104,9 +104,15 @@ To enable the optimizer, add an `embeddingServerRef` to your VirtualMCPServer
 resource. See [Optimize tool discovery](./optimizer.mdx) for the full setup
 guide.
 
+## Next steps
+
+- [Try the Quickstart](./quickstart.mdx) to deploy your first vMCP on a
+  Kubernetes cluster
+- [Configure vMCP servers](./configuration.mdx) to set up groups, backends, and
+  tool aggregation
+
 ## Related information
 
-- [Quickstart: Virtual MCP Server](./quickstart.mdx)
 - [Understanding Virtual MCP Server](../concepts/vmcp.mdx)
 - [Optimize tool discovery](./optimizer.mdx)
 - [Scaling and performance](./scaling-and-performance.mdx)
diff --git a/docs/toolhive/guides-vmcp/optimizer.mdx b/docs/toolhive/guides-vmcp/optimizer.mdx
index fe159aaf..43a99a48 100644
--- a/docs/toolhive/guides-vmcp/optimizer.mdx
+++ b/docs/toolhive/guides-vmcp/optimizer.mdx
@@ -305,13 +305,20 @@ spec:
         audience: vmcp-example
 ```
 
+## Next steps
+
+- [Configure failure handling](./failure-handling.mdx) for circuit breakers and
+  partial failure modes
+- [Monitor vMCP activity](./telemetry-and-metrics.mdx) with OpenTelemetry
+  tracing and metrics
+
 ## Related information
 
-- [MCP Optimizer tutorial](../tutorials/mcp-optimizer.mdx) — desktop/CLI setup
-- [Optimizing LLM context](../concepts/tool-optimization.mdx) — background on
+- [MCP Optimizer tutorial](../tutorials/mcp-optimizer.mdx) - desktop/CLI setup
+- [Optimizing LLM context](../concepts/tool-optimization.mdx) - background on
   tool filtering and context pollution
 - [Configure vMCP servers](./configuration.mdx)
 - [EmbeddingServer CRD specification](../reference/crd-spec.md#apiv1alpha1embeddingserver)
-- [Virtual MCP Server overview](../concepts/vmcp.mdx) — conceptual overview of
+- [Virtual MCP Server overview](../concepts/vmcp.mdx) - conceptual overview of
   vMCP
 - [VirtualMCPServer CRD specification](../reference/crd-spec.md#apiv1alpha1virtualmcpserver)
diff --git a/docs/toolhive/guides-vmcp/scaling-and-performance.mdx b/docs/toolhive/guides-vmcp/scaling-and-performance.mdx
index a9c4cd51..18e5029f 100644
--- a/docs/toolhive/guides-vmcp/scaling-and-performance.mdx
+++ b/docs/toolhive/guides-vmcp/scaling-and-performance.mdx
@@ -80,6 +80,13 @@ spec:
 For stateful backends, vertical scaling or dedicated vMCP instances per team/use
 case are recommended instead of horizontal scaling.
 
+## Next steps
+
+- [Explore Kubernetes operator guides](../guides-k8s/index.mdx) for managing MCP
+  servers alongside vMCP
+- [Curate a server catalog](../guides-registry/index.mdx) for your team with the
+  Registry Server
+
 ## Related information
 
 - [Introduction to vMCP](./intro.mdx)
diff --git a/docs/toolhive/guides-vmcp/telemetry-and-metrics.mdx b/docs/toolhive/guides-vmcp/telemetry-and-metrics.mdx
index 729f8e12..9e31c242 100644
--- a/docs/toolhive/guides-vmcp/telemetry-and-metrics.mdx
+++ b/docs/toolhive/guides-vmcp/telemetry-and-metrics.mdx
@@ -167,11 +167,16 @@ Each span includes attributes for the target backend (`target.workload_id`,
 `target.workload_name`, `target.base_url`) and the relevant MCP attributes
 (`mcp.method.name`, `gen_ai.tool.name`, `mcp.resource.uri`).
 
+## Next steps
+
+- [Set up audit logging](./audit-logging.mdx) for structured request and
+  authorization event tracking
+
 ## Related information
 
-- [Observability concepts](../concepts/observability.mdx) - Overview of
+- [Observability concepts](../concepts/observability.mdx) - overview of
   ToolHive's observability architecture
 - [Kubernetes telemetry guide](../guides-k8s/telemetry-and-metrics.mdx) -
-  Telemetry for MCPServer resources
-- [OpenTelemetry tutorial](../integrations/opentelemetry.mdx) - Set up a local
+  telemetry for MCPServer resources
+- [OpenTelemetry tutorial](../integrations/opentelemetry.mdx) - set up a local
   observability stack
diff --git a/docs/toolhive/guides-vmcp/tool-aggregation.mdx b/docs/toolhive/guides-vmcp/tool-aggregation.mdx
index 728d6915..4044a2d4 100644
--- a/docs/toolhive/guides-vmcp/tool-aggregation.mdx
+++ b/docs/toolhive/guides-vmcp/tool-aggregation.mdx
@@ -237,8 +237,14 @@ With this configuration, tools from each backend are prefixed:
 - `fetch_*` tools from the fetch server
 - `osv_*` tools from the osv server
 
+## Next steps
+
+- [Create composite tools](./composite-tools.mdx) to build multi-step workflows
+  that span multiple backends
+- [Optimize tool discovery](./optimizer.mdx) to reduce token usage when
+  aggregating many tools
+
 ## Related information
 
 - [VirtualMCPServer configuration reference](./configuration.mdx)
-- [Optimize tool discovery](./optimizer.mdx)
 - [Customize MCP server tools](../guides-k8s/customize-tools.mdx)
diff --git a/docs/toolhive/tutorials/mcp-optimizer.mdx b/docs/toolhive/tutorials/mcp-optimizer.mdx
index 756ff0f7..1eee184f 100644
--- a/docs/toolhive/tutorials/mcp-optimizer.mdx
+++ b/docs/toolhive/tutorials/mcp-optimizer.mdx
@@ -328,6 +328,6 @@ Now that you've set up MCP Optimizer, consider exploring these next steps:
 ## Related information
 
 - [MCP Optimizer UI guide](../guides-ui/mcp-optimizer.mdx)
-- [Optimize tool discovery in vMCP](../guides-vmcp/optimizer.mdx) — Kubernetes
+- [Optimize tool discovery in vMCP](../guides-vmcp/optimizer.mdx) - Kubernetes
   operator approach
 - [Organize MCP servers into groups](../guides-ui/group-management.mdx)