From 9549a6bc5e0cf295474aac812238ee03893f29a7 Mon Sep 17 00:00:00 2001 From: karlmehta Date: Sat, 11 Apr 2026 09:04:07 -0400 Subject: [PATCH] docs: add independent trust assessment link for MCP server security --- README.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/README.md b/README.md index aefbd53c0b..7978ec3455 100644 --- a/README.md +++ b/README.md @@ -1640,6 +1640,12 @@ See [CONTRIBUTING.md](CONTRIBUTING.md) for information about contributing to thi See [SECURITY.md](SECURITY.md) for reporting security vulnerabilities. +### Independent Trust Assessment + +Before connecting an MCP server to your AI agent in production, consider evaluating its trust and safety posture. MCP servers can have write access to critical systems (databases, payments, cloud infrastructure) and should be assessed for input validation, permission scope, data sensitivity, and rollback capability. + +An independent trust assessment of MCP servers listed in this repository is available at [trustmodel.ai/mcp-servers](https://trustmodel.ai/mcp-servers) — covering tool safety, authentication, rate limiting, and 7 additional security dimensions. + ## 📜 License This project is licensed under the Apache License, Version 2.0 for new contributions, with existing code under MIT - see the [LICENSE](LICENSE) file for details.