@finchagentic/mcp@4.7.0
The runtime layer for Agentic AI. Persistent memory, autonomous agents, and workflows that survive every session.
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe package forwards configured third-party API keys to its backend without clearly disclosing that they accompany general backend requests. The setup wizard does ask users to configure keys for Finch features, so the evidence supports a warning for insufficiently bounded credential forwarding rather than a confident malicious verdict.
Decision evidence
public snapshot- `dist/convex.js` copies configured Anthropic, OpenAI, Grok and Bankr keys from environment variables into `X-User-*` request headers.
- The default backend receiving those requests is `https://valuable-fish-533.convex.site`, unless `FINCH_CONVEX_URL` overrides it.
- The setup wizard lets users provide a provider key for Finch shell and MCP calls, but does not disclose that configured keys are attached to backend requests generally.
- The agent loop also sends an Anthropic key directly to `api.anthropic.com`, consistent with the package's provider-routing function.
- The setup wizard makes provider keys optional and prompts users to choose a provider and enter its key.
- Provider keys have an apparent intended use for Finch's LLM features, and the agent loop routes an Anthropic key to Anthropic's own API.
Source & flagged code
6 flaggedPackage source references weak cryptographic algorithms.
dist/local-vault.jsView on unpkg · L68Findings
Affected versions and remediation
This report applies to @finchagentic/mcp@4.7.0.
See all versions of @finchagentic/mcp for other recorded verdicts.
- Review the evidence and your use of @finchagentic/mcp@4.7.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.