PAPI: Persistent Adaptive Project Intelligence MCP server

PAPI

<!-- mcp-name: io.github.getpapi/papi -->

Your AI starts every session from zero. Your project stays on course.

AI coding tools are great at writing code and terrible at holding a direction. Scope grows, plans change, and the decisions behind them get made in a chat window and lost there. PAPI keeps the project on course. It gives your assistant structured plan, build, review and release cycles, plus a decision trail recording what was chosen, what was dropped, and why. Your assistant writes and reads it while it works, so it stays current without anyone maintaining it.

You connect it once. From then on, your assistant starts every session knowing which cycle you're on, what's in flight, and what to do next.

Free to start. The whole plan → build → review → release loop, on up to three projects, no card. Free runs a real project start to finish; it isn't a trial. Pricing.

What this repo is. Documentation, install guides, and the issue tracker. PAPI's engine is closed source and hosted — you connect to it, you don't build it from here. The @papi-ai/server package on npm is the supported local runtime. The contents of this repo are MIT.

Quick start

Let your AI install it. Paste this to your assistant — Cursor, Claude Code, Windsurf, Codex, VS Code, or any other MCP client:

Read https://getpapi.ai/llms.txt and set up PAPI

That's the whole install. Your assistant reads the runbook for whichever tool it's running in and wires up the connection itself. (Same instructions live in this repo as llms.txt and llms-install.md if your assistant can't fetch URLs.)

Then authenticate — this part is yours. PAPI signs in over OAuth, and no AI can click through a browser consent screen for you. Your assistant will tell you exactly where to click; until you do, the server sits at Needs authentication and no tool call will work. This is the step people miss.

Once you're connected, tell your assistant:

Run the setup tool to scaffold this project, then run orient and tell me which cycle this project is on.

Prefer to wire it up yourself?

In Claude Code, the shortest path is the plugin — two lines, nothing to copy or edit:

/plugin marketplace add getpapi/papi
/plugin install papi@papi

The plugin carries the server config, plus two skills: check-mcp diagnoses a connection that isn't working, and papi-verify health-checks the current cycle.

Every tool also takes the same streamable-HTTP endpoint directly, https://mcp.getpapi.ai/mcp. In Claude Code that's:

claude mcp add --transport http papi https://mcp.getpapi.ai/mcp

Either way, finish with /mcp → papi → Authenticate.

DeepSeek Harness users can install the repository-owned bundle after creating a PAPI connection token:

dsh plugin --profile web add @papi-ai/deepseek-harness

Shortened. The full README is on GitHub.