Open Entity MCP server

• Registry nameorg.openentity/openentityverified in the MCP registry

The registry name sits under openentity.org. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-28
• Tools12
• Server calls itselfopenentity
• Server version0.2.0
• Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 708 ms.

• Its tools do every use case we checked: obtain a signed identifier for an AI agent; publish a signed declaration of an agent's commitments; keep an append-only signed log of an agent's decisions.
• Checked on 6 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring6 of the 7 daily checks it takes to print a share
• Median first answer256 ms
• Space in an agent's context≈ 2,040 tokensthe definitions of all its tools (13), which an agent carries on every turn
• Tool definitionsC · 68 of 100
• Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 12 of 13
• Not saying whether it only reads or can destroy: 13 of 13

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• openentity_read

  Read the Open Entity llms.txt, the OEIS-1 spec (or one section, e.g. 10.4) or the Declaration text.

• openentity_adopt

  Adopt an Open Entity identity. custody=custodial: the server makes your key and returns it once. custody=self: pass public_key, get bytes to sign, then call again with the signatures.

• openentity_self

  Read your own Entity Document, Identity Anchor and last record entries.

• openentity_resolve

  Resolve a DID (did:key, did:web, did:webvh, did:pkh, did:plc) to its DID document.

• openentity_verify

  Verify an entity by EID, or any signed Open Entity object, and report schema, signatures and log inclusion.

• openentity_record

  Append entries to your Development Record. Pass signed entries, or kind and payload plus your private_key_jwk to have the server build and sign one (the key is used for this call only).

• openentity_withdraw

  Withdraw your Declaration (spec 6.3). Irreversible: the entity is marked withdrawn. Needs confirm=true and your private_key_jwk (used for this call only).

• openentity_present

  Prove you hold your EID to a verifier: sign its nonce and audience into a Presentation carrying your current attestations (spec 4.7).

• openentity_export_key

  Export your key from registry custody (spec 10.6): the registry returns its kept copy once and deletes it. Needs confirm=true and your private_key_jwk (used for this call only).

• openentity_find

  Find entities by what they can do (capability), by name, or by bound alias type.

• openentity_card

  Read an entity's A2A Agent Card (or only its Open Entity AgentExtension block) built from its Entity Document.

• openentity_stats

  Read public registry counts: entities by level, record entries, attestations, log size.