What it does
This server runs over stdio and connects any MCP-compatible client to the SecurityScorecard API. Its nine tools cover security scores and grades, risk prioritisation, remediation roadmaps, asset inventories, SPF, DMARC and DKIM email checks, issue type breakdowns, cross-tool data verification, and direct API queries. Its API discovery search covers 535 indexed endpoints and returns matching paths, parameters and curl examples. Each tool offers minimal, standard and detailed response modes.
It suits users who work with SecurityScorecard data and want to query it from clients such as Claude Desktop, Claude Code, Cursor or VS Code. Optional settings include a default company domain, verbose debug logging, and rate limiting and caching.
Setup requires Node.js and a SecurityScorecard API token. The server can be launched with npx from npm or run from a local source build. You add its configuration block to your client's MCP settings, set the API token and restart the client.
Limitations and requirements
Independent, unofficial project, not affiliated with or endorsed by SecurityScorecard, Inc. You must supply your own API token and comply with SecurityScorecard's terms of service. Requires Node.js. An invalid or expired token returns 401 Unauthorized. On Windows with WSL, dependencies installed under WSL can cause semantic search to fall back to keyword-only results.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CallMarcus/securityscorecard-mcp
Community-built, comprehensive MCP server for the SecurityScorecard API (unofficial).
v2.0.0As shown on registry.modelcontextprotocol.io when we last read it