Skip to main content

MCP Server

The Clockchain exposes its temporal causal graph via the Model Context Protocol (MCP), making it accessible to any compatible AI agent framework (Claude, GPT, custom agents).

Status

Live — Clockchain MCP v1.26.0 is deployed at clockchain.timepointai.com/mcp/ using Streamable HTTP transport.

Endpoint

Transport: Streamable HTTP

MCP Tools

Temporal Navigation Tools

traverse_moments and find_path are free read tools — no authentication required, rate-limited like the other read tools. They power multi-hop reasoning over the causal graph (the same capability behind the Temporal Navigator in the web app).

traverse_moments

Walk the causal graph N hops from a moment to map its causes and consequences. Example tool call:
Response:

find_path

Find the shortest chain of historical connections linking two moments. Example tool call:
Response:
When no path exists within max_hops, the tool returns "found": false rather than an error. On invalid input the tools return an {"error": ..., "suggestion": ...} object instead of raising, so agents can self-correct.

Integration Example

Connect the Clockchain MCP server to your AI agent:

Direct HTTP Access

Any AI agent can also query the Clockchain directly using the public REST API:
No authentication required. 60 requests/minute rate limit. Sign up at timepointai.com for early access to authenticated tools.