More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    MCP Config Audit — What Your MCP Config Gives Away

    1

    Reads your mcp.json and reports the unpinned package that fetches new code at every start, the token sitting in the file, the endpoint that is plain HTTP, and what runs without asking you.

    Free

    1 useSecurity scanned
    MCP Config Audit — What Your MCP Config Gives Away

    MCP Config Audit — What Your MCP Config Gives Away

    Example session with this skill installed

    python3 scripts/config_scan.py .mcp.json --baseline .mcp-baseline.json

    mcp.json:
    {"mcpServers": {"tickets": {"command": "npx",

      "args": ["-y", "example-tickets-mcp"],
      "env": {"TICKETS_API_TOKEN": "tk_live_9f2c..."}}}}
    
    • Read your context and instructions
    • Compiled the mcp config audit

    mcp-config-audit .mcp.json (mcpServers)
    servers 6 findings 13 high 10 medium 1 low 2

    HIGH C1 unpinned package tickets example-tickets-mcp
    HIGH C1 unpinned package search mcp-search-proxy@latest
    HIGH C2 credential in the file tickets env.TICKETS_API_TOKEN
    HIGH C2 credential in the file browser headers.Authorization
    HIGH C3 plaintext transport browser http://mcp-browser.example/sse
    HIGH C4 broad filesystem root files /
    HIGH C5 auto-approved actions ops *
    HIGH C6 shell execution ops bash -c curl ... | sh
    MEDIUM C1 unpinned package db ghcr.io/example/mcp-postgres:latest
    LOW C7 dangerous flag files -y

    FAIL findings at or above 'high'
    report mcp-config-report.md

    What to do next

    1. Pin every package you kept: example-tickets-mcp@2.3.1, mcp-search-proxy==1.9.2, and a digest for the Postgres image.
    2. Replace the two literals with the client's variable syntax; keep the values in your secret store.
    3. Swap http:// for https:// on the browser endpoint, or run that server locally over stdio.
    4. Grant /Users/dev/project instead of / to the filesystem server.
    5. Remove the wildcard auto-approve; approve writes, sends and deletes in code.
    6. Re-run with --write-baseline once the diff is reviewed.
    mcp-config-audit .mcp.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Every MCP security write-up starts with the tool descriptions. This starts one step earlier, at the file that decides what runs at all.

    An mcp.json is a launch script with credentials in it. npx -y some-server resolves a package at every start, so the code your agent runs can change without a commit. A token in env gets committed, synced and shared, and its reach becomes the server's reach. "autoApprove": ["*"] removes the one control that still works when a model is fooled. None of that appears in the tool list, so a tool-contract scan cannot see it — this reads the other half.

    Point it at the config your client actually uses. It parses Claude Code, Claude Desktop and Cursor mcpServers blocks and VS Code's servers block, then reports each server's launch line, whether it is pinned, and every finding with the exact evidence and a fix written for your client's variable syntax.

    • Finds unpinned npx/uvx/bunx packages, @latest, and :latest images that fetch new code at startup
    • Flags literal tokens, bearer headers and database URLs sitting in the file instead of a variable reference
    • Catches plain-HTTP endpoints, / or $HOME filesystem roots, shell pipes, and sandbox-disabling flags
    • Reports auto-approved actions, especially wildcards and anything that writes, sends, deletes or pays
    • Hashes each server so --baseline shows a changed launch command or credential the next time you look
    • Writes a Markdown report and JSON summary, and fails CI at a severity threshold you choose

    Runs on the Python standard library, needs no key and makes no network calls.

    The shipped example catches 13 findings across 6 servers, including a support server launched unpinned with a live token and a shell server that auto-approves everything. The clean example reports zero, which is how you know it is not just printing warnings.

    Good to know: this reads configuration only. It does not audit the server's own code or runtime behaviour, and config roots and allowlists are cooperative boundaries — a compromised server can still reach whatever its process can. TOML configs (Codex) are not parsed. It is a review aid for the launch line, not a safety verdict on the server. icon-mcp-config-audit.png

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.

    Audits config files only, not server source code or runtime behavior. Does not support Codex TOML. Requires Python 3.10+.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    • Free with an Agensi account

    Software
    Python 3.10+An MCP config file to auditsome-serverNode.jsskips@modelcontextprotocol/server-filesystemSearch Proxy MCPuv (Python tool runner)

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed1 day ago

    What's inside

    Frequently Asked Questions

    The audit targets the configuration files used by Claude Desktop, Claude Code, Cursor, and VS Code MCP clients, specifically looking for vulnerabilities in the `mcpServers` blocks.

    This tool identifies hardcoded credentials, unpinned package versions (like `npx` vs `npx@version`), broad filesystem permissions, and insecure transport protocols that manual reviews often overlook.

    Yes, the auditor is a standalone Python script designed for easy integration into CI/CD pipelines, allowing you to fail builds if configuration drift or high-severity risks are detected.

    No, this skill audits the configuration and launch parameters only; it does not perform static or dynamic analysis on the underlying server source code or its runtime dependencies.

    You will receive the standalone Python audit script, documentation on severity rankings, and instructions for generating baseline files to monitor configuration drift.

    New in Security

    Free