WARDEN — MCP security firewall: vets an MCP server's tool definitions against static-scan rules, a signed threat feed, origin and tool-def pinning before any tool reaches the model. Zero-dependency TypeScript library.
- capability exposure inferred + 10
- trust mitigators mixed − 8
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 5d ago · see ecosystem CVEs →
- A · 0 → A · 2
- A · 6 → A · 0
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 8d9ca82 · analyzer v33 · 5d ago
danger signals2
- over-broad OAuth scope delete_repo alexar76-warden-8d9ca82/src/mcp-tools.ts :309
ify_sensitive_tools({ tools: [{ name: \"delete_repo\", description: \"Delete a repository.\", inputSchema: { type: \"object\" } }], patterns: [\"*delete*\"] }).", - over-broad OAuth scope delete_repo alexar76-warden-8d9ca82/test/mcp-server.test.ts :77
{ name: "delete_repo", description: "Delete a repository.", inputSchema: { type: "object" } },
[](https://mcpobservatory.com/servers/github:alexar76/warden/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of alexar76.