DID.is evidence

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Read-only checks for DIDs, credentials, MCP servers, A2A cards and agent delegation.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "DID.is evidence": {
      "url": "https://did.is/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• resolve_did read-only

  Resolve a DID (did:key, did:jwk, did:web, did:webvh) and report which evidence dimensions are established and which are not. Read-only; fetches the DID document from its origin.

  Parameters:

  • did (required) — string — The DID, e.g. did:web:did.is

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• verify_credential read-only

  Verify a W3C Verifiable Credential or SD-JWT VC (JSON object or compact string): signature, validity period and status list. Optional requiredClaims checks issuer-signed claim values. Read-only.

  Parameters:

  • credential (required) — Credential as a JSON object (W3C VC with Data Integrity proof) or compact string (VC-JWT, SD-JWT VC).
  • expectedNonce — string
  • requiredClaims — array
  • expectedAudience — string
  • trustedIssuerCertificates — array

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• inspect_mcp_server read-only

  Inspect a remote MCP server over Streamable HTTP: protocol version, tool inventory fingerprints, declared annotations versus DID.is side-effect heuristics, and changes since the last observation. Read-only; never authenticates to the server.

  Parameters:

  • endpoint (required) — string — https URL of the MCP endpoint

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• inspect_a2a_agent read-only

  Fetch an A2A agent card (agent URL or card URL) and report its signature status, interfaces and skills. Read-only.

  Parameters:

  • url (required) — string — Agent base URL or agent card URL

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• authorize_tool_call read-only

  Check whether a DID.is delegation chain (compact JWTs, root first) allows an agent to call a given tool. Returns ALLOW or DENY with the verified chain. Read-only; nothing is stored.

  Parameters:

  • chain (required) — array
  • tool (required) — string
  • trustedRoots — array

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• evaluate_policy read-only

  Evaluate a DID against declarative rules (allowed methods, curves, domain binding, TLS, linked accounts, verifiable history, credential status). Returns PASS, FAIL or INDETERMINATE (not a pass). Read-only.

  Parameters:

  • did (required) — string
  • policy (required) — object
  • credential — Credential as a JSON object (W3C VC with Data Integrity proof) or compact string (VC-JWT, SD-JWT VC).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• search_directory read-only

  Search the public DID.is directory of DIDs whose controllers proved control and chose to be listed. Matches names and domains. Read-only.

  Parameters:

  • q — string
  • limit — integer
  • cursor — string
  • method — string

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.