modelcontextprotocol / modelcontextprotocol/servers

5 of your servers graded A/B on OpenTrustBench, badges inside

Open
#4,790 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
90.5k
Forks
11.7k
Avg merge
2d 2h
Merged PRs (30d)
5

Description

Hi, I built OpenTrustBench (OSS scanner that grades MCP servers A-F, 8 OWASP-mapped rules, fully local). I scanned the servers repo at d73f99e and yours did well:

mcp-fetch: A (90)
mcp-sequentialthinking: A (90)
mcp-time: B (88)
mcp-everything: B (85)
mcp-git: B (79)
Full file:line evidence per server here: https://www.opentrustbench.com/r/ (each links its own page). If you want badges for your READMEs:

OpenTrustBench
OpenTrustBench
OpenTrustBench
OpenTrustBench
OpenTrustBench

Registry re-scans weekly, happy to re-run on request. And if any finding looks wrong, I want to know, false positives are my problem to fix.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Review the OpenTrustBench report and its linked file:line evidence first, then inspect the relevant server README files. The issue offers badges for five servers but does not specify whether they should be added or define acceptance criteria, so the desired documentation change remains to be confirmed.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
documentation, security
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.