Trust Engine/MCP Server

lastmile-ai/mcp-agent

Build effective agents using Model Context Protocol and simple workflow patterns

8,413 starsPythonApache-2.0agentsaiai-agentsllms

REVIEWED80/100

Scanned 2026-07-09 · gemini v1

Dimension breakdown

Security

40/100

6 findings

Quality

95/100

2 findings

License

95/100

No findings

Completeness

100/100

7 findings

Findings (15)

CRITICAL: 1HIGH: 3MEDIUM: 2LOW: 1INFO: 8

CRITICALsecurityCommand Injection via External Command Execution
HIGHsecurityPath Traversal via Filesystem Server
HIGHsecurityServer-Side Request Forgery (SSRF) via Fetch Server
HIGHsecurityInsecure Direct Object Reference / Broken Access Control (LLM-driven Tool Use)
MEDIUMsecuritySupply Chain Risk from Unpinned `npx` Execution

Detailed file:line citations + recommended fixes are visible to the maintainer of this repo after claiming the listing.

Maintainer of this repo?

Claim this listing in 30 seconds with GitHub OAuth. You'll see detailed findings, get notified about matched bounties, and can trigger re-scans on demand.

Claim listing

Embed the badge.

Drop it into your README. Every view backlinks to this verification page.

Markdown

[![Archimedes Trust](https://archimedes.market/api/badge/lastmile-ai/mcp-agent.svg)](https://archimedes.market/r/lastmile-ai/mcp-agent)

HTML

<a href="https://archimedes.market/r/lastmile-ai/mcp-agent"><img src="https://archimedes.market/api/badge/lastmile-ai/mcp-agent.svg" alt="Archimedes Trust Verified"/></a>