compuute-scan-api
OfficialSupports x402 micropayments using USDC on Base L2 for autonomous agent scanning.
Provides tool wrappers for integration with CrewAI agent frameworks to enable MCP server scanning.
Scans public GitHub repositories for MCP server security issues.
Provides tool wrappers for integration with LangChain agent frameworks to enable MCP server scanning.
Provides an OpenAI plugin manifest for integration with ChatGPT, enabling scanning of MCP server repositories.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@compuute-scan-apiscan https://github.com/modelcontextprotocol/servers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
compuute-scan-api
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 38 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.
Live at https://scan.compuute.se. Service version reported by /v1/health.
Endpoints
Core scan
Method | Path | Purpose | Auth |
POST |
| Scan a public GitHub MCP-server repo (free tier, rate-limited) | none |
POST |
| Same as above via x402 micropayment ($0.10 USDC on Base L2) |
|
POST /v1/scan/pay with no body to read the payment requirements without paying — the request body is optional precisely so discovery probes reach the 402 instead of body validation. Verify with the Coinbase Agentic Wallet CLI:
npx awal x402 details https://scan.compuute.se/v1/scan/pay| GET | /v1/scan/info | Scanner version + limits + supported ecosystems | none |
| GET | /v1/health | Liveness + scanner-binary availability | none |
Machine-readable contracts
Method | Path | Purpose |
GET |
| OpenAPI v3 spec with per-field descriptions |
GET |
| Swagger UI for the OpenAPI spec |
MCP server (live)
Endpoint | Tool | Transport |
|
| Streamable HTTP |
Install in Claude Code: claude mcp add compuute-scan --transport http --url https://scan.compuute.se/mcp/
Discovery (/.well-known/)
Path | Format | Consumer |
| A2A v1.0 Agent Card (canonical) | A2A protocol clients |
| A2A Agent Card (alias) | pre-1.0 A2A clients/crawlers |
| OpenAI plugin manifest | ChatGPT / OpenAI tools |
| x402 payment manifest | Coinbase Agent.market crawlers, x402 aggregators |
| Alias of | x402 probes without |
| markdown summary | LLM-driven agent-search crawlers (Exa, Perplexity-style) per llmstxt.org |
| crawler policy | search engines |
| URL index | search engines |
Example
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..."
}Related MCP server: github-insight-mcp
Agent-shaped API features
Feature | How |
Idempotent retries (24h cache) |
|
HTTP cache |
|
Conditional GET |
|
Rate-limit headers |
|
Strict input validation | Pydantic |
OWASP security headers | HSTS / X-Frame-Options / X-Content-Type-Options / CSP / Referrer-Policy / Permissions-Policy |
OpenAPI for discovery |
|
MCP for agent discovery |
|
x402 for autonomous purchase |
|
Honest framing | Every response carries |
Pricing
Tier | Audience | Price |
Open Source CLI | Indie devs, agent builders | $0 — |
Hosted API (free) | Agent operators evaluating MCP servers | $0 — |
Hosted API (x402) | Autonomous agents in Agent.market ecosystem | $0.10 USDC/scan — |
MCP Security Audit | Enterprises shipping MCP to production | $5K–$30K SoW |
AI Procurement Risk Audit | CFO/CTO/CISO buying enterprise AI capacity | $5K–$15K SoW |
Full breakdown with JSON-LD: https://compuute.se/pricing.
Local development
python3 -m venv venv && source venv/bin/activate
pip install -r requirements.txt
export COMPUUTE_SCAN_PATH=$HOME/compuute-scan/compuute-scan.js
uvicorn main:app --reloadx402 payment env vars (all optional locally; /v1/scan/pay returns 503 until the wallet is set):
Var | Purpose | Default |
| Base L2 address receiving USDC | unset (x402 disabled) |
| CAIP-2 network id — |
|
| Price per scan |
|
| Facilitator base URL | CDP facilitator (serves both networks) |
| CDP API key for facilitator verify/settle auth | unset (verify will be rejected) |
Rehearsing payments on testnet
Set X402_NETWORK=eip155:84532 to quote prices in Base Sepolia USDC, which is
free from a faucet. The CDP facilitator serves Sepolia too, so a testnet
payment exercises the real verify/settle path and your real CDP API keys —
without moving real money.
Asset address and EIP-712 domain are selected together per network: Base
mainnet USDC signs as "USD Coin", Base Sepolia as "USDC". Mixing them
fails every signature with an error that looks like a bad API key, which is
why they live in one NETWORKS table rather than separate env vars.
Mainnet is the default and an unknown value falls back to it, so a typo can
never silently ask real agents to pay in worthless testnet USDC. Check which
mode is live with curl -s https://scan.compuute.se/v1/health — the x402
block reports network and testnet.
Tests
pytest tests/ -v
# 34 tests covering scan, x402, MCP, discovery, OpenAPIScripts
Script | What it does |
| Start-of-session check: branch, working tree, tests, live state, next backlog item |
| End-of-session check: committer hygiene, tests, append to |
| 30-second live-state check against scan.compuute.se (4 probes) |
| Generate CycloneDX SBOM, optionally upload to a GitHub Release |
| Pull qualified prospects from GitHub + Anthropic Registry, draft DM angles |
| T0/T1/T2 distribution snapshot per docs/agent-economy-strategy.md §5 — reach, engagement, conversion measured against Railway logs + Base RPC + GitHub stars |
Architecture
api/services/scan.py— clone + sandbox + scan + parse. Pure functions.api/services/x402_service.py— x402 v2 verify / settle on the officialx402SDK; CDP facilitator (Base mainnet) by default; Bazaar discovery extension in 402 bodies.api/services/cdp_auth.py— minimal CDP API-key JWT auth for the facilitator (PyJWT + cryptography; avoids the full cdp-sdk).api/serializers/scan_serializer.py— Pydantic models, strict validation.api/routes/scan.py— HTTP layer for/v1/scan: idempotency, cache, ETag.api/routes/scan_x402.py— HTTP layer for/v1/scan/pay.api/routes/discovery.py—/.well-known/*,/robots.txt,/sitemap.xml.api/mcp_server.py— FastMCP server exposingscan_mcp_server.main.py— FastAPI wiring + middleware (security headers, CORS).
Bundled compuute-scan version is pinned in the Dockerfile (ARG COMPUUTE_SCAN_REF=v0.6.2).
Documentation
Doc | For |
The strategic doc — a16z-verified data, the 11-signal buyer-agent model, two-track strategy, 30-day pivot trigger. Read first if you're trying to understand the company. | |
Position, pricing tiers, roadmap, decision log | |
Component diagram, request flow, threat model, deployment topology | |
Local setup, layout, code style, common pitfalls — onboard a new dev in 30 min | |
Endpoints to watch, automated checks, runbook for failures | |
Per-rule false-positive transparency | |
What this scanner reports when run against its own code | |
MCP Security Methodology v1.0 (Markdown + PDF) | |
Three anonymized engagement reports from the May 2026 batch | |
Public advisories under the | |
Self-pentest reports (90-day cadence) | |
The AI Procurement Risk Audit checklist (lead magnet) | |
SOC 2 Type I readiness statement, TSC control mapping | |
LangChain + CrewAI tool wrappers ready for PR/marketplace | |
Claude Skill package (SKILL.md + scan.sh) — submitted to anthropics/skills#1346 | |
Contributor Covenant 2.1 | |
Show HN draft + posting checklist | |
Status page (BetterStack) + analytics (PostHog) setup guides | |
Three paths to Coinbase Agent.market listing | |
GitHub Issues + Project board roadmap | |
Composted product hypotheses with gating rules | |
How to contribute | |
Vulnerability disclosure policy (90-day window) |
Security
Found a vulnerability? See SECURITY.md — email security@compuute.se. We follow a 90-day coordinated disclosure window.
License
MIT (matches compuute-scan).
Author
Compuute AB — daniel@compuute.se
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Scans remote MCP servers for protocol, security, and TLS issues; exposes scan tools via MCP.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.
Create, deploy, and operate MCP servers directly from your GitHub repositories.
Related MCP Servers
- AlicenseNot gradedqualityFmaintenanceComprehensive MCP server for analyzing GitHub pull requests, detecting security vulnerabilities, assessing code quality, and providing risk ratings across multiple languages.9MIT
- AlicenseNot gradedqualityCmaintenanceCombines GitHub repository analysis, npm/PyPI package info, and deps.dev security advisories into a single MCP server, requiring no API keys.MIT
- FlicenseNot gradedqualityDmaintenanceA simple MCP server that provides repository information (list repos, get repo details) using GitHub's public REST API, without needing any API keys or tokens.-
- AlicenseAqualityAmaintenanceSecurity scanning for MCP servers from the inside out. Provides runtime inspection, AST-based static analysis, config audit, dependency analysis, and OWASP MCP Top 10 compliance in a single MCP server.551505MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Compuute/compuute-scan-api'
If you have feedback or need assistance with the MCP directory API, please join our Discord server