TrustData
MCP agent

Quickstart

Issue a token, connect your agent, and run your first tool call in about 2 minutes.

1. Issue an API token

  1. Open the TrustData dashboard and go to Organization Settings → Developer.
  2. In the API tokens card, give the token a name (e.g. "Claude Desktop, home"), pick a rate tier, and select scopes.
    • Use the SEO × GEO playbook preset for the recommended GEO/SEO scope set.
    • Use All scopes to grant everything your account allows.
  3. Click Issue token.
  4. Copy the td_live_… token that appears. This is the only time it's shown. Store it in a password manager.
Scopes = capabilities. A token with read:metrics can only read metrics. Even if the LLM tries to call run_probe, the tool won't be visible. Pick the least-privilege set that covers your workflow.

2. Connect your agent

After issuing, the dashboard shows a Connect an agent panel with install snippets for each agent. You can also paste the snippets below directly.

// ~/Library/Application Support/Claude/claude_desktop_config.json  (macOS)
// %APPDATA%\Claude\claude_desktop_config.json                      (Windows)
{
  "mcpServers": {
    "trustdata": {
      "url": "https://app.trustdata.tech/mcp/",
      "headers": {
        "Authorization": "Bearer td_live_YOUR_TOKEN"
      }
    }
  }
}

Restart the agent. You should see a trustdata connection in its MCP / tools panel.

3. Verify with a first tool call

Ask your agent something that exercises a tool:

"List the TrustData analytics queries available to me."

The agent will call list_analytics_queries and return the set of query types your token's scopes allow. If you see a list of query types (campaigns, channel_summary, geo_visibility, etc.), you're connected.

4. Try the playbook

The real value is letting the agent drive an end-to-end loop. Open the SEO × GEO playbook and paste it as a system prompt. The agent will diagnose, propose hypotheses, and record trackable recommendations in one conversation.

Rate limits

TierRate capBest for
Measure30 requests/minManual exploration, one-off questions
Optimize300 requests/minRecurring reports, dashboards
Prove3000 requests/minAgentic workflows (recommended)

run_probe is separately metered against your GEO add-on's monthly engine-call allowance.

Troubleshooting

SymptomCauseFix
403 SCOPE_DENIEDToken is missing the scope the tool requiresTokens are immutable. Issue a replacement with the needed scope, then revoke the old one.
404 on property_idProperty is in a different organization, or was deletedConfirm the property UUID in the dashboard URL.
422 GUARDRAIL_VIOLATIONHypothesis shorter than 20 chars, or invalid target_prompt_idsWrite a proper "If we X, then Y because Z" hypothesis. Verify prompt IDs belong to your organization.
Agent doesn't see TrustData toolsToken lacks matching scopes, so filtered tools are hidden entirelyIssue a token with the scopes you need, then reconnect the MCP server.
401 UNAUTHENTICATED after it worked beforeToken was revokedIssue a new one in Developer → API tokens.

Need help?

  • Revoke a compromised token: Developer → API tokens → Revoke. The token stops working immediately.
  • Support: [email protected]