Skip to content
Back to search
📊 Intel view 📋 Audit JSON 🔄 Changelog
52
A2A A2A 2025-06-18 v0.5.0

compuute-scan-api

scan.compuute.se · Compuute AB

MCP-specific static security scanner for agents. Scan any public GitHub MCP-server repo and get severity counts, score, top findings, and a triage disclaimer. 38 L1 rules across TS/JS, Python, Go, Rust, C#, Java, Kotlin. Threat-intel response cadence: new rules added within one week of published CVE classes (see compuute-scan v0.6.2's L1-038 for the Ox Security npx-argument-injection vector).

Build a free agent shortlist. Save this listing to revisit it from your account. Sign in to save
🛡
Own this agent?
Verify the domain scan.compuute.se via a single DNS TXT record to add the verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Verify ownership

Compare public evidence

🔔 Watch this agent. Choose one alert: availability and recovery, card drift, price, payment rail, settlement wallet, inflow or verification changes. Add more alert types from your account. Free and unmetered on agents you've verified owning; 3 watches on agents you don't own, 25 on Pro. Sign in to watch
Trust score
52/100
grade D · 9 criteria
Uptime
100.0%
44 direct probes · 30d
~169 ms response
Observed inflow · 30d
—
no payment wallet declared
Invocations · 7d
0
no calls observed
Card drift · 7d
stable
2 snapshots tracked
Owner
unverified
claim this listing →

Dispute or improve this rating

D
Conformance score: 52/100
D-grade: significant issues, auth-gated, partially broken, or stale.
click to expand breakdown ▾ click to collapse breakdown ▴
pass Valid AgentCard 10/10
Parseable AgentCard returned by the well-known endpoint (Agenstry readiness signal; not an official TCK certification).
partial Live JSON-RPC 10/25
Card declares only gRPC / HTTP+JSON interfaces; the live probe covers JSON-RPC, so the endpoint was not exercised. Not a defect in the card.
How to earn +15 points
Respond live on JSON-RPC
Implement SendMessage for v1.0 (or message/send for v0.x), negotiate A2A-Version, and return a schema-valid JSON-RPC response. Our probe sends a no-op heartbeat; see the methodology page for the exact payload. If your endpoint already answers, nothing is broken at your end: a stored result older than 30 days is scored as dated, and the points come back on the next probe.
Docs →
partial Protocol version 2/10
Declares unrecognised version '2025-06-18'.
How to earn +8 points
Declare protocolVersion
Add `"protocolVersion": "1.0"` (Major.Minor, no patch number — §3.6) to every entry in `supportedInterfaces[]`. A2A v1.0 removed the AgentCard root field.
Docs →
info JWS signature 0/10
Card is unsigned (most published agents are).
pass Uptime track record 15/15
44/44 probes succeeded (100% uptime).
partial Skill declaration 6/10
Declares 1 skill, usable but thin.
How to earn +4 points
Declare your skills
Add at least one entry to the `skills` array on the AgentCard, each with `id`, `name`, `description`, `tags` — `description` and `tags` are REQUIRED on AgentSkill since A2A v1.0, and tags are what discovery filters match on. We canonicalise these into the global skill taxonomy on next probe.
Docs →
partial Verified Identity 5/10
Provider declared: Compuute AB (https://compuute.se). Add a registry identifier (LEI, Companies House number, KvK, ABN, …) to provider.legalEntity for full verified-business credit.
How to earn +5 points
Verify your domain ownership
Claim your listing and add the DNS TXT record we generate. Alternatively, sign your card with a JWS key that resolves to a verified-business LEI / KvK / Companies House registration.
Docs →
pass Freshness + modern flags 4/5
seen in upstream source within 0d
info Security declaration 0/5
Neither securitySchemes nor securityRequirements declared — how to authenticate is unstated.

Activity (audit trail)

last 24h · 0 invocations Public aggregate · no PII recorded

Nothing observed in the last 7 days — no invocations, no lookups, no listing impressions. Use the try-it console above to invoke this agent; calls are logged here automatically.

Card history

2 snapshots drifted 1× Every change to agent-card.json
Agent card snapshots
Captured Hash Snapshot
2026-08-26 07:45:49 current 3451490cec09… view →
2026-08-18 01:16:36 5bf4be797355… view →
Uptime
100.0%
44 direct probes · 30d
Response
166ms
last direct probe
Skills
1
declared
Streaming
—
SSE-capable

Endpoints

Agent cardhttps://scan.compuute.se/.well-known/agent-card.json
Providerhttps://compuute.se
Docshttps://scan.compuute.se/docs
About this provider off-card enrichment
SSL certificate
Let's Encrypt
expires 2026-10-22
Discovered via
mcp_registry recrawl_hot smithery recrawl_warm

Skills · 1 declared · mapped to canonical taxonomy

Scan MCP server repo

Clone a public GitHub MCP-server repo and run compuute-scan L0+L1 static analysis. Returns severity counts, 0-100 score, 10 most severe findings, performance me…

orphan: no canonical match yet
securitymcpstatic-analysissupply-chaincve

Health · last 30 probes

When HTTP Live JSON-RPC Latency
2026-10-16 10:52:28 200 — 166ms
2026-10-15 19:39:35 200 — 186ms
2026-10-15 08:26:14 200 — 164ms
2026-10-14 20:35:29 200 — 228ms
2026-10-14 08:44:44 200 — 243ms
2026-10-13 20:47:22 200 — 262ms
2026-10-13 06:03:54 200 — 214ms
2026-10-13 04:19:19 200 — 163ms
2026-10-12 09:42:14 200 — 203ms
2026-10-11 21:39:38 200 — 207ms

Similar agents embedding-nearest

Blockquote
Blockquote scores a public URL 0-100 for how likely ChatGPT, Perplexity and Google AI Overviews are to cite it, and returns the fixes. The s
Arne Kellmann · q 90%
MCP Server Security Scan
MCP Server Security Scan: probes an MCP server (JSON-RPC initialize + tools/list) and applies a deterministic rule engine over its tools — e
SYNTHORA · q 88%
AIShield Security Scanner live
Open-source, local-first AI Agent security scanner and trust authority - the neutral trust layer and content-security plane of the 2026 Inte
AIShield Project · q 100%
agentaegis-mcp-production.up.railway.app
AgentAegis scan_mcp_plugin — supply-chain trust scan of an MCP server or agent skill BEFORE you install/trust it. Clones a git repo (or take
agentaegis-mcp-production.up.railway.app · q 45%
MCP Server Quality Corpus
Hosted dataset-backed x402 API that scores MCP servers for freshness, installability, security risk, incident exposure, duplicate drift, and
mcp-server-quality-corpus.mtree.workers.dev · q 66%
mcpscan.openverbs.com
Statically analyse a Model Context Protocol (MCP) server manifest for security risks. Tool descriptions enter the model context, a prime pro
mcpscan.openverbs.com · q 65%

Embed your Agenstry badge

Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.

Agenstry grade Uptime A2A protocol version
Markdown / HTML snippets
[![Agenstry grade](https://agenstry.com/badge/scan.compuute.se.svg)](https://agenstry.com/agents/scan.compuute.se)
[![Verified Business](https://agenstry.com/badge/scan.compuute.se/identity.svg)](https://agenstry.com/agents/scan.compuute.se)
[![Uptime](https://agenstry.com/badge/scan.compuute.se/uptime.svg)](https://agenstry.com/agents/scan.compuute.se)
[![A2A version](https://agenstry.com/badge/scan.compuute.se/protocol.svg)](https://agenstry.com/agents/scan.compuute.se)

Audit-grade evidence bundle

JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against our JWKS. See the methodology.

audit.json audit.json (JWS-signed) verification history
Raw agent card JSON
{
  "protocolVersion": "1.0",
  "name": "compuute-scan-api",
  "description": "MCP-specific static security scanner for agents. Scan any public GitHub MCP-server repo and get severity counts, score, top findings, and a triage disclaimer. 38 L1 rules across TS/JS, Python, Go, Rust, C#, Java, Kotlin. Threat-intel response cadence: new rules added within one week of published CVE classes (see compuute-scan v0.6.2's L1-038 for the Ox Security npx-argument-injection vector).",
  "version": "0.5.0",
  "documentationUrl": "https://scan.compuute.se/docs",
  "supportedInterfaces": [
    {
      "url": "https://scan.compuute.se/mcp/",
      "protocolBinding": "https://modelcontextprotocol.io/streamable-http",
      "protocolVersion": "2025-06-18"
    },
    {
      "url": "https://scan.compuute.se/v1/scan",
      "protocolBinding": "https://spec.openapis.org/oas/v3.1",
      "protocolVersion": "3.1"
    }
  ],
  "mcpEndpoint": "https://scan.compuute.se/mcp/",
  "provider": {
    "organization": "Compuute AB",
    "url": "https://compuute.se"
  },
  "capabilities": {
    "streaming": false,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "skills": [
    {
      "id": "scan_mcp_server",
      "name": "Scan MCP server repo",
      "description": "Clone a public GitHub MCP-server repo and run compuute-scan L0+L1 static analysis. Returns severity counts, 0-100 score, 10 most severe findings, performance metrics, and a triage disclaimer. Median latency 1-2s for small repos.",
      "tags": [
        "security",
        "mcp",
        "static-analysis",
        "supply-chain",
        "cve"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json"
      ],
      "examples": [
        "Scan {\"repo_url\": \"https://github.com/modelcontextprotocol/servers\"} before connecting an agent to it"
      ]
    }
  ],
  "pricing": {
    "free": "0 USDC \u2014 POST /v1/scan, no API key, rate-limited",
    "perScan": "$0.10 USDC on Base L2 \u2014 POST /v1/scan/pay with X-Payment header",
    "manualAudit": "$5K-30K \u2014 see https://compuute.se/audit"
  },
  "payments": {
    "protocol": "x402",
    "x402Version": 2,
    "paidEndpoint": "https://scan.compuute.se/v1/scan/pay",
    "freeEndpoint": "https://scan.compuute.se/v1/scan",
    "manifest": "https://scan.compuute.se/.well-known/x402.json"
  },
  "agentSafety": {
    "honestFraming": "Every response carries a _disclaimer field stating that findings are pattern matches, not exploitability claims. Static analysis cannot determine whether vulnerable code paths are reachable from attacker-controlled input.",
    "noCodeExecution": "compuute-scan never executes code from the scanned repo. Files are read as text and pattern-matched against regex rules.",
    "sandboxing": "Clones live in tempfile.TemporaryDirectory() and are wiped after each scan. git clone uses --depth 1 --filter=blob:limit=10m with a 60s timeout.",
    "dataMinimization": "No scan results stored server-side. Stateless service.",
    "openSource": "Scanner source: https://github.com/Compuute/compuute-scan (MIT). API source: https://github.com/Compuute/compuute-scan-api (MIT)."
  }
}