Guard Core security MCP: SecurityConfig validation, docs search, live threat detection.
An MCP server that lets AI coding agents answer questions about the Guard security ecosystem from the libraries themselves, instead of from memory.
Covers the whole family: the Python trio (fastapi-guard, guard-core, guard-agent) by live introspection, and the Go, TypeScript, PHP and Rust engines, their twenty framework adapters, their telemetry agents, and the guard-core-app SaaS ingestion contract from a verified registry and knowledge corpus.
Your agent can already read the docs. What it cannot do is tell you that the redis_failopen in your config is silently doing nothing because the real field is redis_fail_open, or that the flag you are reaching for did not exist until guard-core 3.5.0, or whether a given request would actually be blocked and by which pattern.
This server answers those from the installed package: real pydantic validation, real field metadata, and the real detection engine. It also answers the cross-language questions the libraries cannot answer: which package guards a Gin, Fastify, Laravel or Rocket app, whether it is tagged or still path-dependent, how to wire its telemetry agent, and what response codes the SaaS ingest endpoint returns.
Install it into your project's environment, not as an isolated tool:
uv add --dev guard-core-mcp
claude mcp add guard-core -- uv run guard-core-mcp
uvx guard-core-mcp will start, but an isolated environment contains no guard-core or fastapi-guard for it to introspect, so it can only answer from bundled documentation. Running it inside your own environment is what makes the answers match the versions you actually ship.
| Tool | Answers |
|---|---|
versions | Which Guard libraries are installed here, and at what version |
validate_config | Is this config valid, including typo'd keys pydantic silently ignores |
config_fields | What is this setting, what does it default to, does a setting for X exist |
search_docs | Where do the docs cover this |
get_doc | The full text of one documentation page |
check_payload | Would this request be blocked, and by which pattern |
ecosystem | The full registry matrix: 5 languages, engines, adapters, agents, conformance, SaaS contract |
adapter_setup | Install plus a verified minimal integration for one adapter (e.g. go + gin) |
wire_agent | How to set up the telemetry agent for a language, including the ingestion contract |
The ecosystem tools are pure data, so they work everywhere, with or without the Python libraries installed. Every quick-start snippet is copied verbatim from the sibling repo READMEs, and release_status tells you honestly whether a package is published, tagged, or still untagged (source, main, or path dependency only).
The same tools are also served remotely at https://mcp.guard-core.com/mcp and packaged as a ChatGPT plugin: sign in with a guard-core account, and ChatGPT can validate configs, search the docs and run payloads through the hosted detection engine (the latest published releases, not your local versions). The packaging lives in plugin/, the hosted server in guard_core_mcp.hosting, and the full story (env vars, Docker image, developer-mode test loop, submission checklist) in the ChatGPT plugin guide.
MIT
mcp-name: io.github.Guard-Core/guard-core-mcp
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
uvx guard-core-mcpMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-guard-core-guard-core-mcp": {
"command": "uvx",
"args": [
"guard-core-mcp"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referenceguard-core-mcppypiGuard Core works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.