Add mcpscore to LLM & MCP Testing

[a-akimov]

Adds mcpscore, an open-source auditor for MCP servers, to the LLM & MCP Testing section (alphabetical, between mcp-server-fuzzer and OrcaReplay).

It connects to a running server, runs deterministic protocol, tool-schema and security-posture checks, and reports a 0-100 score with a suggested fix for each failed check. Available on PyPI (pip install mcpscore), MIT licensed.

Disclosure: I'm the author.

Summary by Sourcery

Add mcpscore to the LLM and MCP testing resource collection.

New Features:

• Add mcpscore to the LLM and MCP testing resources list, highlighting its MCP server auditing and scoring capabilities.

Documentation:

• Document mcpscore as a deterministic MCP server auditor with CLI, GitHub Action, and SARIF support.

[semanticdiff-com]

Review changes with  

[sourcery-ai]

Reviewer's guide (collapsed on small PRs)

Reviewer's Guide

The README now lists mcpscore between mcp-server-fuzzer and OrcaReplay as an open-source MCP server auditor that deterministically evaluates protocol conformance, tool/schema quality, and security posture, producing scored results and suggested fixes.

File-Level Changes

Change	Details	Files
Add mcpscore to the LLM & MCP Testing resource list in alphabetical order.	Link to the mcpscore GitHub repository. Describe its 0–100 MCP server auditing score, deterministic checks, and remediation guidance. Mention CLI and GitHub Action usage, SARIF output, and MIT licensing.	README.md

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[qodo-code-review]

Code Review by Qodo

Sorry, something went wrong

We weren't able to complete the code review on our side. Please try again manually by commenting /agentic_review on this PR.

[qodo-code-review]

PR Summary by Qodo

List mcpscore in LLM & MCP Testing resources

📝 Documentation 🕐 Less than 5 minutes

AI Description

• Adds mcpscore to the LLM & MCP Testing resource list.
• Describes its MCP server audit scores, suggested fixes, CLI and GitHub Action support.

High-Level Assessment

A README entry is the appropriate approach for adding a resource to this curated list; no architectural alternative is warranted.

Files changed (1) +1 / -0

Documentation (1) +1 / -0

README.mdAdd mcpscore to the LLM & MCP Testing list +1/-0

Add mcpscore to the LLM & MCP Testing list

• Adds a link to mcpscore between mcp-server-fuzzer and OrcaReplay. The entry describes its MCP server audit scope, 0–100 score, suggested fixes, CLI and GitHub Action support, and MIT license.

README.md

[sourcery-ai]

Hey - I've reviewed your changes and they look great!

Sourcery assessment

Approved.

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

[mergify]

Tick the box to add this pull request to the merge queue (same as @mergifyio queue).

• Queue this pull request

[llamapreview]

LlamaPReview — No blocking issues found

This Markdown-only PR adds the requested mcpscore entry to the LLM & MCP Testing list, rewriting no existing content and closing the stated objective; there is no executable, configuration, or contract surface to regress.

Review details and evidence

Material unknowns

• Whether the linked project surface is real as described — the repository at mcp-box/mcpscore is live, public, and MIT-licensed, and it provides the CLI / GitHub Action / SARIF behavior described in the blurb. Deep stated this does not decide the objective (the entry was added as specified) and is not a request-changes reason; it would only matter if maintainers additionally require external-link liveness verification for curated-list entries.
  • Check: No pre-merge action is required by Deep; the optional check is to open the linked repository and package-registry metadata if the maintainers want external-link liveness verified.

LlamaPReview checks

• Reviewed changed regions in README.md.
• Read the complete PR-head file README.md.

---

LlamaPReview is open source. Explore the code behind this review.