MCP Observatory
pypi analyzed 4.1.0

searchlight-mcp

v4.1.0
pypi

Free, open-source web search MCP server for AI coding tools

maintainer
Searchlight Contributors
license
—
first seen
2026-06-04
last seen
2026-06-04
releases · 30d
0
short id
risk 46/100 · heuristic grade
C elevated
  • capability exposureinferred+10
  • recent driftinferred+12
  • inherited (deps)attested+15
  • tool safetyinferred+12
  • trust mitigatorsmixed−3

attestedinferredmixed

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 12m ago · see ecosystem CVEs →

capability exposure grade factor +10
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

inherited (deps) · grade factor +15

inherited via dependencies 3
HIGH
MCP Python SDK vulnerability in the FastMCP Server causes validation error, leading to DoS via mcp · 1 hop CVE-2025-53366 fixed in 1.9.4
HIGH
Model Context Protocol (MCP) Python SDK does not enable DNS rebinding protection by default via mcp · 1 hop CVE-2025-66416 fixed in 1.23.0
HIGH
MCP Python SDK has Unhandled Exception in Streamable HTTP Transport, Leading to Denial of Service via mcp · 1 hop CVE-2025-53365 fixed in 1.10.0
tool safety 1 findings · grade factor +12
  1. highdangerous code

    committed secret: Google API key

skills & danger signals pypi-sdist
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v4.1.0 · analyzer v18 · 10h ago

danger signals1

  • committed secretGoogle API keysearchlight_mcp-4.1.0/.claude/settings.local.json:15AIzaSy…(39 chars, redacted)
other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/pypi:searchlight-mcp/badge.svg)](https://mcpobservatory.com/servers/pypi:searchlight-mcp/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 Searchlight Contributors.