MCP Server Scan by Agentropolis
seenly-skill-scan.vercel.app
MCP Server Scan by Agentropolis: scan a live remote MCP server URL (or pasted tools/list) before your agent connects. Reads initialize + tools/list only, never calls a tool. Flags poisoned or hidden tool instructions (IMPORTANT tags, conceal-from-user, secret or side-channel asks, invisible Unicode, tool shadowing, payment injection). Fingerprints every tool (sha256) and diffs vs your last scan to
- Category
- Service
- Networks
- Base
- Starting price
- $0.03
- Paid calls, 30 days
- 2
Paid endpoints
2 endpoints, sorted by usage. Prices are per request.
| Endpoint | Price | Network | Facilitator | Calls / 30d |
|---|---|---|---|---|
POST/api/mcp-scan MCP Server Scan by Agentropolis: scan a live remote MCP server URL (or pasted tools/list) before your agent connects. Reads initialize + tools/list only, never calls a tool. Flags poisoned or hidden tool instructions (IMPORTANT tags, conceal-from-user, secret or side-channel asks, invisible Unicode, tool shadowing, payment injection). Fingerprints every tool (sha256) and diffs vs your last scan to catch silent changes (MCP rug pulls). Returns allow/review/block. Advisory. | $0.03 | Base | Coinbase CDP | 1 |
POST/api/scan Skill Scan by Agentropolis: static Consensus Scan of an MCP server or agent skill before you install it. Pass a GitHub repo, npm:/pypi: package or pasted code + tools/list/SKILL.md. Flags tool poisoning, hidden instructions, credential/env exfiltration, remote code exec, obfuscation, install hooks; 2 rule families + 2 LLM reviewers vote; cross-checks Agentropolis seller trust data. Returns allow/review/block with evidence. Read-only, never executes the code. Advisory. | $0.30 | Base | Coinbase CDP | 1 |
Is this your project? Suggest an edit.