Caveat verdict
mapbox-mcp-runtime-patterns
Integration patterns guide for the Mapbox MCP Server with various AI frameworks (pydantic-ai, LangChain, mastra); reference documentation with legitimate geospatial API usage examples.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (6)
Possible hardcoded credential
SKILL.md · code · TOKEN="your_token_here
References child_process — can spawn system processes
AGENTS.md · code · child_process
Uses spawn() — can execute external programs
AGENTS.md · code · spawn(
Pipe to python — executes piped content as Python code
examples/README.md · prose · downgraded · | Python
Accesses sensitive environment variables
AGENTS.md · code · process.env.MAPBOX_ACCESS_TOKEN
Python os.getenv — reads environment variable
references/crewai.md · code · os.getenv(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
network_inpackage_install Is this flag fair?
Thanks — recorded.