@dpf-it/mcp-server

@dpf-it/mcp-server — retired

This package is retired. DPF now runs a remote MCP server — no install, no npm package, no local Node.js required.

Use the remote server instead

Point your MCP client at:

https://api.dpf-it.com/mcp

VS Code, Cursor, Claude Desktop/Claude.ai, Kiro IDE, and ChatGPT Developer Mode all support this directly: connecting opens a browser login (OAuth 2.1) — your password is typed on DPF's own page, never inside a chat — and the client stores its own session from then on, including for brand-new accounts (the same login page handles sign-up).

Full setup instructions per client: https://dpf-it.com/integration-guide.html#mcp

Tools

Tools exposed by the remote server (https://api.dpf-it.com/mcp), authenticated via OAuth 2.1:

• list_my_workspaces — List my workspaces
• create_workspace — Create a workspace
• onboard_data_source — Onboard a new data source, step 1: create a data spec and get upload URL(s)
• finish_data_source_onboarding — Onboard a new data source, step 2: run analysis after uploading
• update_data_spec — Update an existing data spec
• finish_data_spec_update — Update an existing data spec, step 2: run analysis after uploading
• run_data_job — Run a data processing job, step 1: create job and get upload URL(s)
• finish_data_job — Run a data processing job, step 2: start processing after uploading
• setup_scheduled_pull — Set up a scheduled SFTP or S3 pull into an existing data spec
• manage_connection — Manage an external data-source connection (SFTP, AWS S3)
• manage_trigger — Manage a workspace trigger (SFTP/AWS S3 pull, spec chaining, or schedule)
• list_data — List data specs or jobs
• get_status — Get spec or job status
• delete_data_spec — Delete a data spec
• submit_query — Query workspace data
• call_dpf_api — Call any DPF API action (fallback for requests with no dedicated tool)

If your client doesn't support OAuth yet

A small number of clients (Codex CLI, Kiro CLI) don't yet support the OAuth browser flow that the remote server requires, and this package no longer provides a working local alternative. Check the integration guide for updates once those clients add OAuth support.

Why the change

The remote server give every client a consistent, install-free setup, real per-user attribution (not a shared workspace credential), and is the only way for hosted clients like ChatGPT — which can't spawn a local process at all — to use DPF's MCP server.