English only · Spanish [PLANNED]

Use the MCP tools from a client

Task: call the public MCP server from a client or from the command line. The server is at https://api.aria.bar/mcp, Streamable HTTP, no authentication, read-only. It does not register anything; the write server is authenticated and out of scope here.

From an MCP client

Point the client at https://api.aria.bar/mcp as a remote server over Streamable HTTP. The eight tools below appear as native tools. Configuration syntax depends on the client; the server needs no headers beyond content-type and accept.

From the command line

tools/list and tools/call both work without an initialize handshake.

curl · runs against https://api.aria.bar/mcp

curl -s -X POST https://api.aria.bar/mcp \
-H 'content-type: application/json' \
-H 'accept: application/json, text/event-stream' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

You should see a JSON-RPC result whose tools array has eight entries, starting with resolve_did.

curl · runs against https://api.aria.bar/mcp

curl -s -X POST https://api.aria.bar/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call",
       "params":{"name":"verify_aid","arguments":{"did":"did:aria:example.com:my-agent"}}}'

# tools/list works the same way, without a session.

The eight tools

As the server registers them; this list is generated from the server's source and is the same one /developers shows.

resolve_did(did)Resolve a did:aria DID to its full ARIA Identity Document (W3C Verifiable Credential). Returns agent data even if no AID has been issued.

verify_aid(did)Verify an AID: check signature validity, revocation status, expiration, and trust level. Returns intent if declared.

check_status(listId)Check the revocation status of an AID via W3C Bitstring StatusList 2021

lookup_org(domain)RDAP-style lookup of an organization by domain. Returns trust level, agent count, and registered agents.

get_audit_trail(did, limit)Get the cryptographically-verified audit trail for a specific DID

list_scopesList the normative ARIA scope registry -- all authorized capability identifiers

get_trust_level_infoGet ARIA trust level definitions (L0-L3), requirements, pricing, and compliance mappings

get_ecosystem_statsGet public ecosystem statistics: total organizations, agents, active AIDs, and trust level distribution

None of these tools decides admission. A tool answering "can proceed" would be conflating verification with ATP. If you need a level gate, compare verify_aid's trustLevel against your own minimum on the client side, and treat the result as identity information — see What an AID proves.