Dagpipe MCP Server

Every node's output is independently validated and checkpointed before the next node executes. A failure at node 4 cannot corrupt nodes 1, 2, or 3. Delete nothing. Just re-run. DagPipe resumes exactly where it stopped, automatically. It runs locally over stdio via the published package.

People who work with checkpointing, dag and free tier and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-07-20 · ★ 3 · #75 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Dagpipe

before you install - you'll need

GROQ_API_KEY

Environment variables documented in the project's README - it lists which are required and which have defaults.

Claude Code

claude mcp add devilsfave-dagpipe -- uvx dagpipe-core

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "devilsfave-dagpipe": {
      "command": "uvx",
      "args": [
        "dagpipe-core"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package dagpipe-core - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.devilsfave is GitHub-verified and matches the repo owner

03 · What Dagpipe can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.2.3 · 2026-03-10

This release focuses on optimizing DagPipe's presence on PyPI and standardizing the documentation syntax to ensure a professional, technical presentation. · Enhancements · PyPI Discoverability: Optimized the project…

v0.2.0 · 2026-03-08

What's New · Smart Model Router · Automatically routes tasks to the cheapest model that can handle them. Simple tasks go to free-tier models. Hard tasks escalate. Rate limit failures trigger automatic fallback. · Live…

v0.1.0 · 2026-02-27

DagPipe v0.1.0 - Core Library · First public release. Phase 1 complete. · What's included · dag.py - Generic DAG orchestrator with topological sort · checkpoints.py - JSON crash recovery · constrained.py…

04 · Who maintains Dagpipe

dagpipe is maintained by devilsfave. It's the only MCP server we track from this author; the repo dates to Feb 2026.

05 · Facts

category
AI & ML - ranked #75 of 106 actively-maintained AI & ML servers as of 2026-09-18.
registry
io.github.devilsfave/dagpipe (active, first published 2026-03-15)
packages
pypi:dagpipe-core

06 · Dagpipe FAQ

What is Dagpipe?

Every node's output is independently validated and checkpointed before the next node executes. A failure at node 4 cannot corrupt nodes 1, 2, or 3. Delete nothing. Just re-run. DagPipe resumes exactly where it stopped, automatically. It runs locally over stdio via the published package.

Is Dagpipe still maintained?

Yes - as of 2026-09-18, its last commit was 2026-07-20. We re-verify nightly.

How do I install Dagpipe?

Run `uvx dagpipe-core`. The README documents one environment variable (GROQ_API_KEY) to set first. You can also paste the ready-made client config above.

Does Dagpipe run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Dagpipe