Agents Index

Trust Tools

Online

Website security ratings, token verification, and tamper-evident ledger heads from Obelisk Gate.

Visit publisherConnectJSON

What it can do: 10 tools

  • scan_trustRun Obelisk's public trust scan on an https URL — TLS and security-header posture, scored as an Obelisk Rating. Read-only, SSRF-guarded.
  • verify_tokenVerify that a JSON Web Token was minted by this Obelisk Gate (ES256, correct issuer) and report its type, subject, assurance, and principal. Never returns secrets.
  • get_org_ratingRead the public Obelisk Rating (0-100 score, trust band, and trend) for a registered organization by its slug.
  • verify_agent_run_proofVerify an Obelisk run proof. Pass run_proof_token, the token Obelisk signs at POST /api/agent-proof/run: the tool checks Obelisk's signature against its published keys, that the named agent is active now with the same ke
  • get_agent_proofRead an Obelisk agent's public proof vector by opaque proof id. Returns independent claims with freshness and scope; never a scalar trust score or a claim of non-humanness.
  • transparency_headRead the current signed transparency head of Obelisk's tamper-evident receipt ledger. Save headAnchorHash with anchorCount and compare later: the count must never go down, and the head at a saved count must not change. N
  • gate_statusRead the Gate's public liveness facts: issuer, served code revision, OIDC availability, and supported protocols. No posture internals.
  • pin_tool_manifestPin an MCP tool manifest before an agent trusts it. Returns a SHA-256 digest per tool and for the whole catalogue (canonical JSON, every field counts), hidden-text findings (Unicode tag, bidi and zero-width characters) a
  • explain_ratingExplain what an Obelisk Rating number means: its trust band, how the public scan scores, and what typically moves a score. Deterministic by default; pass narrate:true for an additional one-line model-written narrative (c
  • agent_enrollment_guideRead how an AI agent enrolls with this Obelisk Gate: the endpoints in order, the fields each takes, which key types this deployment can prove, whether enrollment is switched on, and the current account sign-up posture an

Connect it

Claude Code
claude mcp add --transport http trust-tools https://obeliskgate.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://obeliskgate.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "trust-tools": {
      "url": "https://obeliskgate.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "trust-tools": {
      "type": "http",
      "url": "https://obeliskgate.com/mcp"
    }
  }
}

Questions

What does Trust Tools do?

Website security ratings, token verification, and tamper-evident ledger heads from Obelisk Gate. It exposes 10 tools to AI assistants.

What tools does Trust Tools provide?

10 tools, including scan_trust, verify_token, get_org_rating, verify_agent_run_proof, get_agent_proof, transparency_head, gate_status, pin_tool_manifest, explain_rating, agent_enrollment_guide.

How do I connect Trust Tools to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://obeliskgate.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Trust Tools require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Trust Tools online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Trust Tools?

obeliskgate.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Crypto & Web3