Ground your agents in verified entity data

The grounding loop

1. 1 · Resolve— turn a raw string (“Anthropic”, “the PBD podcast”) into a canonical Entidex ID with a confidence band, instead of string-matching a name your agent half-recognises.
2. 2 · Verify — check a specific claim against the verified record. You get the verified value with source and date, plus where the AI engines currently diverge (the correction delta) and signed provenance.
3. 3 · Read — pull the layered intelligence view, or fetch the crawlable Knowledge Statement for RAG grounding.
4. 4 · Correct — when your agent finds the record itself is wrong, submit a correction back through a review-gated, append-only channel. Entidex is the canonical place to fix what AI gets wrong about an entity.

Quickstart

Connect over the hosted MCP endpoint — nothing to install or self-host — or call the REST API directly. Full MCP client config (Claude Desktop, Cursor, and other hosts) is on the MCP server page.

{
  "mcpServers": {
    "entidex": {
      "url": "https://entidex.com/api/mcp",
      "headers": { "Authorization": "Bearer entx_live_sk_..." }
    }
  }
}

Tools for agents

• entity_resolve — resolve a raw string to a canonical Entidex ID with a confidence band. (Starter+)
• entity_verify_fact — verify facts against the verified record: verified values with source and date, the correction delta where AI engines diverge, and signed provenance. (Starter+)
• entity_intelligence — the layered intelligence view (profile + scores) for a resolved entity. (Pro+)
• entity_drift — drift history, named events, and lead-lag across surfaces. (Pro+)
• entity_decision_survival — latest decision-survival result with the displacement chain. (Pro+)
• entity_completeness — how fully the record is populated across surfaces, so an agent knows how much to trust a sparse profile. (Pro+)
• entity_submit_feedback — submit a correction back to Entidex. Captured append-only with provenance and reviewed before it affects the published record. (Starter+)

Each tool enforces the same tier gate as its REST equivalent.

Machine-readable records

Every entity carries a public, crawlable Knowledge Statement — verified facts plus corrections to common AI claims, available as Markdown, schema.org ClaimReview, or JSON, and cryptographically signed. For agents and CI, the authed /v1/entities/<id>/ground-truth endpoint returns the same record. Discovery starts at the site-root llms.txt, and a machine descriptor of the MCP server lives at /.well-known/mcp.json.

Free tier: resolution and Knowledge Statement reads, rate-limited. Developer Flat is £29/mo with monthly credits and pay-as-you-go overflow.