More screenshots
Works with the AI Agents you already use
MCP Config Safety Check
This skill finds those and eight other MCP config mistakes before you commit or load the config, and tells you how to fix each one.
$5
MCP Config Safety Check
Example session with this skill installed
Check this project with mcp-config-safety-check.
- Read your context and instructions
- Compiled the mcp config safety
$ python3 scripts/check_mcp.py examples/risky
BLOCK .cursor/mcp.json:7 M04 CONTAINER_WITH_HOST_ACCESS
"-v", "/var/run/docker.sock:/var/run/docker.sock",
Why: The server runs in a container with host access: --privileged, --cap-add SYS_ADMIN or ALL, --pid=host, the host's / mounted, or the Docker socket mounted. A tool call the agent makes (also one steered by a prompt injection) can then take over the host; the Docker socket alone gives root on it.
Safer: Drop --privileged and extra capabilities, mount only the folders the server needs (read-only where you can: -v /path/to/project:/workspace:ro), and never mount /var/run/docker.sock into an MCP server.
BLOCK .mcp.json:7 M01 SECRET_IN_MCP_CONFIG
BLOCK .mcp.json:12 M02 REMOTE_SERVER_OVER_HTTP
BLOCK .mcp.json:14 M01 SECRET_IN_MCP_CONFIG
BLOCK .mcp.json:19 M03 DOWNLOAD_PIPED_TO_SHELL
REVIEW .cursor/mcp.json:8 M11 UNPINNED_PACKAGE
REVIEW .cursor/mcp.json:13 M12 CODE_FROM_GIT_OR_URL
REVIEW .cursor/mcp.json:17 M11 UNPINNED_PACKAGE
REVIEW .cursor/mcp.json:17 M15 TLS_VERIFICATION_OFF
REVIEW .gemini/settings.json:8 M15 TLS_VERIFICATION_OFF
REVIEW .gemini/settings.json:10 M14 AUTO_APPROVED_RISKY_TOOLS
REVIEW .mcp.json:5 M11 UNPINNED_PACKAGE
REVIEW .roo/mcp.json:4 M16 SERVER_RUNS_AS_ADMIN
REVIEW .roo/mcp.json:6 M14 AUTO_APPROVED_RISKY_TOOLS
REVIEW .vscode/mcp.json:7 M13 BROAD_FILE_ACCESS
(Each finding also has Why and Safer lines, as in the first one.)
Verdict: BLOCK. Checked 5 files, 5 with MCP config content.
This is a static check of file text. NOT FLAGGED is not a guarantee.
Connects securely to your tools. The creator never sees your data.
About this skill
"GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..." in a committed .mcp.json gives your token to everyone who can read the repository, and npx -y @modelcontextprotocol/server-github with no version runs whatever was published last, every time your editor starts the server. This skill finds those and eight other MCP config mistakes before you commit or load the config, and tells you how to fix each one.
Your agent runs a scanner on your MCP configs: Claude Code (.mcp.json, ~/.claude.json, plugin manifests), Claude Desktop, Cursor (.cursor/mcp.json), VS Code (.vscode/mcp.json with its servers and inputs), Windsurf, Cline, Roo Code and Gemini CLI (.gemini/settings.json). It accepts comments and trailing commas, knows each client's variable syntax (${VAR}, ${env:VAR}, ${input:id}, $VAR), and unwraps cmd /c, sh -c and powershell -Command to see the real command. It never starts a server, installs a package or connects to anything. It returns BLOCK, REVIEW, or NOT FLAGGED, with the file, line, reason, and a safer approach. Secrets are never printed.
What it checks
BLOCK
- M01: API keys, tokens, passwords and Bearer credentials written in env, headers, args, URLs or OAuth settings
- M02: remote servers over plain http:// or ws:// (not localhost, a private address or Tailscale)
- M03: a server command that pipes a download into a shell (curl | bash, iwr | iex)
- M04: Docker servers with --privileged, SYS_ADMIN, --pid=host, the host's / or the Docker socket mounted
REVIEW
- M11: npx, uvx, pipx, bunx and pnpm dlx packages or Docker images without an exact version, or with @latest
- M12: servers installed from a git repo, a GitHub owner/repo shorthand or a tarball URL without a commit hash
- M13: filesystem servers or container mounts given /, a drive root or a home folder
- M14: autoApprove or alwaysAllow lists with * or write and run tools, and Gemini CLI's trust: true
- M15: TLS checks turned off (NODE_TLS_REJECT_UNAUTHORIZED=0, --ignore-https-errors and similar)
- M16: servers started with sudo, doas or runas
What's included
- The scanner (Python 3.9+, standard library only)
- A rules guide with the reason and safer approach for each rule
- A risky and a safe example project (Claude Code, Cursor, VS Code, Roo Code and Gemini CLI configs), and the real report the scanner produces on the risky one
Limits It reads each config as written: values filled in later (environment variables, env files, VS Code inputs, a client's settings screen), approval rules kept in other files, TOML or YAML configs such as Codex config.toml, and what a server's own code does are not checked. NOT FLAGGED is not a guarantee.
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.
Static check of MCP config JSON. User-level configs outside the project are checked only when you pass their path, and plain http:// to a private network or Tailscale address is not flagged. NOT FLAGGED is not a guarantee.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
- Software
- Remote MCPname
Node.js
uv (Python tool runner)@scope/serverandtsx
Permissions
Runs one local Python script in the terminal. It reads your project's files, writes nothing, and makes no network calls. The example configs include clearly fake, inert tokens (NOTREAL, not-a-real-...) and made-up server names and URLs for the scanner to find. Nothing in them is started or contacted.