About AnchorRegistry
AnchorRegistry’s MCP server lets AI clients look up artifact provenance by AR-ID or SHA-256 manifest hash. It also returns provenance trees, while forwarding requests to the API without retaining state or credentials.
Key features
- 01Resolve AR-IDs to provenance records
- 02Look up artifacts by SHA-256 hash
- 03Retrieve full provenance trees
- 04Stateless API proxy
Use cases
- 01Check an artifact’s provenance from an AI client
- 02Find a registry entry using its manifest hash
- 03Inspect relationships across a provenance tree
MCP support
Provides three tools to MCP clients for resolving AR-IDs, manifest hashes, and provenance trees. Calls are forwarded to the AnchorRegistry API.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.anchorregistry.ai/mcpclaude mcp add --transport http ar https://mcp.anchorregistry.ai/mcp{"mcpServers":{"ar":{"type":"http","url":"https://mcp.anchorregistry.ai/mcp"}}}Open in Cursor{"servers":{"ar":{"type":"http","url":"https://mcp.anchorregistry.ai/mcp"}}}Open in VS Code{"mcpServers":{"ar":{"type":"http","url":"https://mcp.anchorregistry.ai/mcp"}}}{"mcpServers":{"ar":{"serverUrl":"https://mcp.anchorregistry.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
https://mcp.anchorregistry.ai/mcphttps://mcp.anchorregistry.ai/sseTools
3| Parameter | Type | Required | Description |
|---|---|---|---|
| ar_id | string | Yes | AR-ID such as AR-2026-qnPOJ1z |
Details
From the project READMEar-mcp
The AnchorRegistry MCP server. Resolve any AR-ID, manifest hash, or provenance tree from any MCP-compatible AI client.
Endpoint: https://mcp.anchorregistry.ai/mcp
Install
Claude Desktop
Settings → Integrations → Add server.
URL: https://mcp.anchorregistry.ai/mcp
Claude Code
claude mcp add --transport http anchorregistry https://mcp.anchorregistry.ai/mcp
Cursor
Settings → MCP → Add new MCP server.
Name: anchorregistry · Type: http · URL: https://mcp.anchorregistry.ai/mcp
Tools
ar_verify_arid
Resolves an AR-ID to its full provenance record.
"What's at AR-2026-qnPOJ1z?"
ar_verify_by_hash
Resolves an artifact by SHA-256 manifest hash.
ar_resolve_tree
Returns the full provenance tree for any AR-ID.
How it works
ar-mcp is a thin proxy. Every tool call hits api.anchorregistry.ai
and returns the JSON unchanged. No data is logged, no credentials are
stored, no state is held between requests.
The full surface is documented at:
- https://anchorregistry.ai/llms.txt
- https://anchorregistry.ai/agents.json
- https://api.anchorregistry.ai/openapi.json
Roadmap
v0.2 will add ar_check_balance and ar_register_artifact once the MCP
credential-handling pattern stabilizes across clients. ar_seal_tree is
deferred indefinitely (irreversible action; needs robust user-confirmation
primitives the protocol does not yet provide). The deferred tools are
fully implemented and live in src/future-tools.ts —
enabling them is a one-line flip per tool.
Develop
npm install
npm test # vitest, hits live api.anchorregistry.ai
npm run type-check
npm run dev # wrangler dev — http://localhost:8787
npm run deploy # wrangler deploy
Verify locally with the MCP inspector:
npx @modelcontextprotocol/inspector http://localhost:8787/mcp
License
MIT.
See also
- AnchorRegistry: https://anchorregistry.com
- Python SDK: https://pypi.org/project/anchorregistry/
- Source: https://github.com/AnchorRegistry/ar-mcp
- Spec: https://anchorregistry.ai/agents.json
- Contracts: https://github.com/AnchorRegistry/ar-contracts-v1
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.