Server data from the Official MCP Registry
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
Remote endpoints: streamable-http: https://scan.compuute.se/mcp/
Well-structured API wrapper around compuute-scan with strong input validation, proper error handling, and transparent framing about static analysis limitations. Code quality is high and permissions align with purpose. Minor concerns around subprocess invocation and in-memory caching do not substantially impact security posture for this category. Supply chain analysis found 4 known vulnerabilities in dependencies (0 critical, 3 high severity).
7 files analyzed · 9 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
From the project's GitHub README.
Scan-as-a-Service for MCP servers. HTTP + MCP wrapper around compuute-scan — the MCP-specific static security scanner. Designed for agent-callable consumption.
POST a public GitHub repo URL → get a structured security report scored against 37 MCP-specific rules across 8 languages (TS/JS, Python, Go, Rust, C#, Java, Kotlin).
Honesty note (read first): compuute-scan is a pattern-breadth detector, not an exploitability oracle. Historic false-positive rate after manual validation is ~90% on raw output (verified against modelcontextprotocol/servers: 138 raw findings → 13 confirmed). Every response carries a
_disclaimerfield stating this explicitly. Use findings as a triage queue, not as a list of confirmed vulnerabilities. See docs/FP-RATES.md for per-rule transparency.
| Method | Path | Purpose |
|---|---|---|
| POST | /v1/scan | Scan a public GitHub MCP-server repo |
| GET | /v1/scan/info | Scanner version, limits, capabilities |
| GET | /v1/health | Liveness + scanner-binary check |
| GET | /openapi.json | OpenAPI v3 spec (for agent discovery) |
| /mcp/ | (planned) | MCP server with scan_mcp_server tool |
curl -X POST https://scan.compuute.se/v1/scan \
-H 'Content-Type: application/json' \
-H 'Idempotency-Key: 00000000-0000-0000-0000-000000000001' \
-d '{"repo_url": "https://github.com/modelcontextprotocol/servers"}'
Response (truncated):
{
"repo_url": "https://github.com/modelcontextprotocol/servers",
"scanner": {"name": "compuute-scan", "version": "0.6.2", "layers_covered": ["L0", "L1"]},
"summary": {"critical": 1, "high": 94, "medium": 22, "low": 0, "files_scanned": 77},
"score": 0,
"recommendation": "AVOID — 1 critical and 94 high finding(s)...",
"top_findings": [...],
"performance": {"clone_seconds": 1.2, "scan_seconds": 0.5, "repo_size_bytes": 41234},
"_disclaimer": "PATTERN MATCH — compuute-scan is a static analyzer..."
}
| Feature | How |
|---|---|
| Idempotent retries (24h cache) | Idempotency-Key header |
| HTTP cache | ETag + Cache-Control: public, max-age=1800 |
| Conditional GET | If-None-Match → 304 Not Modified |
| Strict input validation | Pydantic extra="forbid", GitHub-HTTPS-only |
| OpenAPI for discovery | GET /openapi.json with descriptions on every field |
| Honest framing | Every response carries _disclaimer — pattern match, not exploitability claim |
python3 -m venv venv && source venv/bin/activate
pip install -r requirements.txt
export COMPUUTE_SCAN_PATH=$HOME/compuute-scan/compuute-scan.js
uvicorn main:app --reload
pytest tests/ -v
api/services/scan.py — clone + sandbox + scan + parse. Pure functions.api/serializers/scan_serializer.py — Pydantic models, strict validation.api/routes/scan.py — HTTP layer: idempotency, cache, ETag.main.py — FastAPI wiring.Bundled compuute-scan version is configured via COMPUUTE_SCAN_PATH env var.
| Tier | Audience | Price |
|---|---|---|
| Free | Indie devs, agent builders | 3 scans/day |
| Pro | Teams shipping MCP to production | TBD |
| Audit | Manual L2-L4 audit by Compuute AB | $5K-30K — see compuute.se/audit |
| Doc | For |
|---|---|
| docs/ARCHITECTURE.md | Component diagram, request flow, threat model, deployment topology |
| docs/DEVELOPMENT.md | Local setup, layout, code style, common pitfalls — onboard a new dev in 30 min |
| docs/STRATEGY.md | Position, pricing tiers, roadmap, decision log — why we built it this way |
| docs/MONITORING.md | Endpoints to watch, automated checks, runbook for failures |
| docs/agentic-market-submission.md | Three paths to Agentic.market listing with engineering effort estimates |
| scripts/status.sh | 30-second project status check (run anytime) |
Found a vulnerability? See SECURITY.md — email security@compuute.se. We follow a 90-day coordinated disclosure window.
MIT (matches compuute-scan).
Compuute AB — daniel@compuute.se
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.