MCP Server Auditor

Paste one public HTTPS Streamable HTTP MCP endpoint. In about 25 seconds, receive a tool inventory, risk flags, protocol/schema findings, and a readiness score.

$0.15 per successful audit. Useful partial audits are also $0.15; failed, restricted, invalid, unsupported, unreachable, and dependency-failure targets are not charged.

Runtime-surface audit only — no source-code, CVE, OAuth, stdio, SSE, local/private-network, or authenticated-target scanning.

The safe example endpoint is already filled in, so you can run the controlled audit without changing the input. You can also batch-audit up to 25 compatible endpoints.

Quick start

Use the prefilled Sentinel-owned endpoint for a safe, discovery-only first run:

{
  "servers": [{"url": "https://mcp.sentinelsignal.io/audit-fixture/mcp"}],
  "depth": "standard",
  "includeEvidence": false
}

Real report preview

This abbreviated result was produced through the Actor's real service path against the controlled endpoint. Scores and findings depend on the endpoint's current behavior and the active Verify rules.

{
  "status": "success",
  "target": {
    "identifier": "https://mcp.sentinelsignal.io/audit-fixture/mcp"
  },
  "result": {
    "server": {
      "protocolVersion": "2025-03-26",
      "status": "healthy"
    },
    "capabilities": {"toolCount": 3, "resourceCount": 0, "promptCount": 0},
    "tools": [
      {"name": "echo"},
      {"name": "add"},
      {"name": "server_info"}
    ],
    "findings": [],
    "findingCount": 0,
    "summary": {
      "score": 65.1,
      "risk": {"highRiskTools": 0},
      "readiness": {"label": "Safe for evaluation"}
    }
  }
}

See the public Input schema and Output schema for the complete contracts.

Input and batching

servers accepts one to 25 objects with a public HTTPS url. Duplicate URLs are collapsed and produce one result with a warning. depth is currently fixed to standard. Set includeEvidence to false for a smaller result.

Output and failure behavior

Results use the stable API-IFY schemaVersion: "1.0" envelope. The default dataset contains audit or failure records, while RUN_SUMMARY in the default key-value store records processing, delivery, billing, dependency, and budget totals.

restricted means API-IFY rejected the target locally. unreachable means the public endpoint could not complete MCP discovery. unsupported covers unsupported target behavior. dependency_unavailable means Verify was temporarily unavailable. failed is reserved for unexpected audit failures. Failures are isolated per target.

How it works

MCP Server Auditor evaluates public, unauthenticated Streamable HTTP endpoints through Sentinel Verify. It performs MCP initialization and discovery, evaluates the advertised surface, and returns one structured item per unique target. Each target is checked locally against API-IFY's public-network policy before it is sent to Verify. The Actor never invokes advertised MCP tools.

Pricing

One mcp-audit event costs $0.15 and is charged only when a successful or useful partial audit is accepted into the dataset. Restricted, invalid, unreachable, unsupported, dependency-failure, and failed outcomes are uncharged. Work does not start when the caller's remaining event budget cannot cover another audit.

Limitations

• Public, unauthenticated MCP endpoints only.
• HTTPS on port 443 only; credentials and fragments in URLs are rejected.
• Streamable HTTP transport only.
• Private, loopback, link-local, metadata, reserved, and mixed public/private DNS targets are rejected.
• Maximum 25 submitted targets and four concurrent audits per run.
• Audit availability depends on Sentinel Verify and the target MCP server.

Privacy and security

The target endpoint is sent to Sentinel Verify for analysis after local public-network validation. Results are stored in the customer's Apify run dataset and summary store. Do not place credentials in target URLs or query parameters. Published datasets, key-value records, and structured logs redact authorization values, secrets, private keys, and secret-like query parameters.

VERIFY_CLIENT_ID and VERIFY_CLIENT_SECRET are operator-managed Actor secrets used to obtain a short-lived Verify access token at runtime via Sentinel's token-service client-credentials exchange. VERIFY_API_KEY (a static, long-lived JWT) is a deprecated fallback used only when the client-credentials secrets are absent. VERIFY_BASE_URL, TOKEN_SERVICE_BASE_URL, and VERIFY_TIMEOUT_SECONDS are operator settings, not Actor inputs.

Support

For a reproducible support request, provide the Apify run ID, result itemId, and status. Never send credentials or unredacted URLs through support. Contact Sentinel Signal Systems through the support link on the Actor page.