Trust Card · Static snapshot

mendableai__firecrawl-mcp-server D

45/100 · 6 findings (3 critical) · scope excessive · Ranked #41 of 53 scanned.

Scanned 2026-09-09 · engine v0.1.0 (8 regex rules, OWASP-mapped) · upstream mendableai/firecrawl-mcp-server @ 4db752e (2026-09-08)

Score breakdown

security 0

permissions 35

provenance 90

reliability 85

stability 100

Score constrained by 3 critical and 3 high-severity findings.

Fix first (6 critical/high)

Severity	Rule	Finding	Remediation
CRITICAL	`AT-SEC-002` (LLM02)	Hardcoded Credential or API Secret `tests/mcp-search-profile.test.mjs:112` Evidence: `apiKeyFromIntrospection = 'fc-from-introspection',`	Move credentials to secure environment variables or a key vault. Never commit API keys.
CRITICAL	`AT-SEC-002` (LLM02)	Hardcoded Credential or API Secret `tests/mcp-smoke.test.mjs:328` Evidence: `apiKeyFromIntrospection = 'fc-from-introspection',`	Move credentials to secure environment variables or a key vault. Never commit API keys.
CRITICAL	`AT-SEC-002` (LLM02)	Hardcoded Credential or API Secret `tests/mcp-smoke.test.mjs:2583` Evidence: `const resolvedApiKey = 'fc-resolved-api-key-value';`	Move credentials to secure environment variables or a key vault. Never commit API keys.
HIGH	`AT-SEC-006` (LLM06)	Unfiltered SSRF / Arbitrary Network Egress `src/monitor.ts:74` Evidence: `const response = await fetch(url, {`	Define an explicit egress domain allowlist and block private IP ranges (127.0.0.1, 10.0.0.0/8, 169.254.169.254).
HIGH	`AT-SEC-006` (LLM06)	Unfiltered SSRF / Arbitrary Network Egress `tests/mcp-search-profile.test.mjs:62` Evidence: `const response = await fetch(url);`	Define an explicit egress domain allowlist and block private IP ranges (127.0.0.1, 10.0.0.0/8, 169.254.169.254).
HIGH	`AT-SEC-006` (LLM06)	Unfiltered SSRF / Arbitrary Network Egress `tests/mcp-smoke.test.mjs:32` Evidence: `const response = await fetch(url);`	Define an explicit egress domain allowlist and block private IP ranges (127.0.0.1, 10.0.0.0/8, 169.254.169.254).

Permissions

Scope: excessive · Shell: enabled · Network egress: yes · File deletion: none · Human approval: none

Provenance

License: MIT · Lockfile: yes · Security policy: no · Signals: present (documentary, not a safety verdict)

Independently scanned by the AgentTrust registry (not self-reported by the project). Static analysis only — no code executed, findings need human triage, counts may include test/example code. Static snapshot; re-scan before relying on it: npx @eulogik/agenttrust scan https://github.com/mendableai/firecrawl-mcp-server. Scores move with every upstream commit; pages refresh weekly. How scoring works.