A Model Context Protocol server with Exa for web search and web crawling. Provides real-time web searches with configurable tool selection, allowing users to enable or disable specific search capabilities. Supports customizable result counts, live crawlin
- capability exposure inferred + 10
- tool safety inferred + 5
- trust mitigators mixed − 22
These factors total -7, not 0: the score is bounded to 0–100 after they are summed, so this one is floored at 0. The factors are left as they were applied rather than rewritten to make the column add up.
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.
graded 7m ago · see ecosystem CVEs →
- A · 5 → A · 0
- A · 0 → A · 5
- A · 2 → A · 0
- A · 0 → A · 2
- B · 27 → A · 0
- A · 0 → B · 27
- A · 11 → A · 0
- A · 0 → A · 11
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed v3.4.0 · analyzer v31 · 2d ago
skills & prompt files 2
danger signals1
- dynamic code execution new Function() package/dist/stdio.cjs :2943
const makeValidate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode);
[](https://mcpobservatory.com/servers/npm:exa-mcp-server/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 kesku.