Categories › AI & Agents › Agent memory & context
Read-only checks for DIDs, credentials, MCP servers, A2A cards and agent delegation.
Remote server: your requests and data go to did.is. Claude Code: claude mcp add --transport http did-is-evidence https://did.is/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
resolve_did — Resolve a DID (did:key, did:jwk, did:web, did:webvh) and report which evidence dimensions are established and which are not. Read-only; fetcverify_credential — Verify a W3C Verifiable Credential or SD-JWT VC (JSON object or compact string): signature, validity period and status list. Optional requirinspect_mcp_server — Inspect a remote MCP server over Streamable HTTP: protocol version, tool inventory fingerprints, declared annotations versus DID.is side-effinspect_a2a_agent — Fetch an A2A agent card (agent URL or card URL) and report its signature status, interfaces and skills. Read-only.authorize_tool_call — 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 verievaluate_policy — Evaluate a DID against inline declarative rules or a saved team policyRef (allowed methods, curves, domain binding, TLS, linked accounts, vesearch_directory — Search the public DID.is directory of DIDs whose controllers proved control and chose to be listed. Matches names and domains. Read-only.Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.