DFX Intelligence · developer docs
Build on the DFX graph
Everything needed to connect an agent, ask it a question, read the evidence on the answer and stay inside your limits. Every request and every answer on these pages ran against production.
Short answer
https://exchange-production-9123.up.railway.app/mcp/core?c=docs to any MCP client and call research with one question. No key, no sign-up.Guides
- Connect a client
Connect Claude, Claude Code, ChatGPT, Cursor, VS Code or any MCP client to the DFX Intelligence MCP server, keyless or on your membership.
- API examples: curl, Python, TypeScript
Requests and the answers production returned: one-call research, paging, lender groups, change feeds and the JSON API.
- Agent research and continuation
How the one-call research tool plans, how deep it reads, how to page and continue an investigation, and how to monitor what changed.
- The evidence schema: claims, claim types, citations
How a DFX answer states what it knows: answer states, claim types, citation blocks, citation checks, novelty and what was withheld.
- One membership: keys, sign-in, usage and limits
How a DFX membership covers its agents: keys, signed-in connections, allowances per plan, what a call costs, and what happens at a limit.
For coding agents: the same guides as Markdown at /api/data-factory/v1/docs, reachable by any HTTP client. Checked 2026-10-11.