More screenshots
Works with the AI Agents you already use
MCP Server Code Safety Check
This skill finds those and eleven other MCP server mistakes before you publish, install or connect a server, and tells you how to fix each one.
$5
MCP Server Code Safety Check
Example session with this skill installed
Check this project with mcp-server-code-safety-check.
- Read your context and instructions
- Compiled the mcp server code
$ python3 scripts/check_mcp_server.py examples/risky
BLOCK server.py:11 M03 SECRET_IN_SERVER_CODE
GITHUB_TOKEN = "<redacted>"
Why: An API key, token or password is written in the server code: a published key format (OpenAI, Anthropic, GitHub, GitLab, Slack, Stripe live, AWS, Google, Hugging Face, npm, SendGrid, a private key block) or a secret-named variable, argument, header or environment default set to a literal. MCP servers are shared as repositories and packages, so everyone who installs or forks the server gets the key.
Safer: Revoke the key and create a new one, then read it at run time from the environment the MCP client config passes in (environ["API_KEY"] from Python's os module, process.env.API_KEY in Node) or from a secret manager. Deleting the line is not enough: the key stays in git history and in published packages.
BLOCK server.py:17 M01 SHELL_COMMAND_FROM_INPUT
BLOCK server.py:23 M02 CODE_EVAL_OF_INPUT
BLOCK server.py:65 M04 HIDDEN_INSTRUCTIONS_IN_TOOL_TEXT
REVIEW http_server.py:14 M13 HTTP_SERVER_OPEN_WITHOUT_AUTH
REVIEW http_server.py:14 M14 NO_HOST_ORIGIN_CHECK
REVIEW server.py:29 M11 FILE_PATH_FROM_TOOL_INPUT
REVIEW server.py:37 M12 URL_FROM_TOOL_INPUT_FETCHED
REVIEW server.py:44 M18 SQL_BUILT_FROM_STRINGS
REVIEW server.py:51 M17 SECRETS_IN_TOOL_RESULT
REVIEW server.py:56 M19 SUSPICIOUS_TOOL_TEXT
REVIEW server.py:74 M15 STDOUT_WRITE_IN_STDIO_SERVER
REVIEW src/index.ts:18 M16 TOOL_ARGUMENTS_NOT_VALIDATED
(Each finding also has Why and Safer lines, as in the first one.)
Verdict: BLOCK. Checked 3 files, 3 with MCP server 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
subprocess.getoutput(f"git log {ref}") in a tool lets any page, issue or file the model reads run commands on your machine, and a hidden IMPORTANT block in a tool description can tell the model to read your SSH keys and keep quiet about it. This skill finds those and eleven other MCP server mistakes before you publish, install or connect a server, and tells you how to fix each one.
Your agent runs a scanner on the server's source: Python with the mcp SDK (FastMCP, MCPServer, the low-level Server) or the fastmcp package, and TypeScript or JavaScript with @modelcontextprotocol/sdk, the @modelcontextprotocol/server packages or fastmcp. It skips comments, tells strings from code, follows tool arguments from the handler's parameters through variables and into helper functions in the same file, and accepts the usual guards (path root checks, host allow lists, shlex.quote, schema validation, bearer authentication). It never runs, imports or connects to the server. 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: tool arguments or other values that are not fixed in shell commands (subprocess with the shell option, also under import aliases, os.popen and system, getoutput, sh -c lists, Node exec/execSync however it is imported, spawn with a shell option); shlex.quote values and typed int parameters are fine
- M02: eval, exec, new Function or node:vm run on values that are not fixed
- M03: API keys, tokens and passwords written in the server code
- M04: hidden instructions to the model in tool, prompt and parameter descriptions or server instructions (IMPORTANT tag blocks, Unicode tag or bidi override characters, secrecy toward the user combined with reading SSH keys or mcp.json, or two weaker signs together); ordinary notes, placeholders and non-English text are not flagged
REVIEW
- M11: tool arguments used as file paths with no check that they stay inside an allowed folder
- M12: URLs or hosts from tool arguments fetched with no allow list (SSRF)
- M13: HTTP transports listening on all interfaces with no authentication
- M14: HTTP transports with no Host or Origin check (DNS rebinding)
- M15: print, console.log and other stdout writes in stdio servers
- M16: low-level tools/call handlers that read arguments nothing validates
- M17: tools that return the environment or secret environment variables to the model
- M18: SQL built from strings with values that are not fixed
- M19: one weaker sign of hidden instructions in tool text (secrecy toward the user, an order to disregard earlier instructions, a system tag pair, a lone IMPORTANT tag, shadowing another tool, zero-width characters)
What's included
- The scanner (Python 3.9+, standard library only)
- A rules guide with the reason, safer approach and official source for each rule
- A risky and a safe example server (Python and TypeScript), and the real report the scanner produces on the risky one
Limits It reads each file on its own: tool arguments are followed only within one file, a few calls deep. MCP client configuration files, dependency vulnerabilities, the installed SDK version, a reverse proxy in front of the server and run-time behaviour are not checked; Go, Java, Kotlin, C# and Rust SDKs are not read. 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 server source text in Python and TypeScript/JavaScript. Tool arguments are followed within one file; client configuration files and run-time settings are not checked. 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 4 days ago
- Software
Python
Permissions
Runs one local Python script in the terminal. It reads your project's files, writes nothing, and makes no network calls. The example server includes a clearly fake, inert token (not-a-real-...) and labeled samples of a poisoned and a suspicious tool description for the scanner to find. They are never run.