JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 248
  • Score
    100M100P100Q97925F
  • License Elastic-2.0

PAPI MCP server — AI-powered sprint planning, build execution, and strategy review for software projects

Package Exports

  • @papi-ai/server
  • @papi-ai/server/prompts

Readme

@papi-ai/server

Structured planning for AI-assisted development. PAPI gives Claude Code a persistent planning layer — every cycle builds on the last, so your project gets smarter over time instead of starting fresh every session.

Quick Start

Takes about 2 minutes.

  1. Get your config — Sign up at PAPI and copy your .mcp.json snippet
  2. Add to your project — paste it into .mcp.json in your project root
  3. Restart Claude Code — it will detect the PAPI server automatically
  4. In Claude Code: say run setup, then run plan

That's it. You're planning.

What You Get

  • Cycle planning — the AI planner reads your project history and recommends what to build next, with detailed BUILD HANDOFFs for each task
  • Build tracking — every task gets a build report: actual effort, surprises, discovered issues, architecture decisions
  • Strategy reviews — every 5 cycles, a deep analysis of velocity, estimation accuracy, and project direction
  • Compounding intelligence — cycle 20 is sharper than cycle 1 because it has 19 cycles of context to learn from

Before / After

Without PAPI With PAPI
Start every session by re-explaining the project Orient in one call — cycle state, next action, blocked tasks
Tasks grow in scope mid-build BUILD HANDOFFs define scope boundary and acceptance criteria upfront
Architectural decisions get forgotten Active Decisions persist across cycles with confidence levels
No way to know if you're going faster or slower Estimation accuracy tracked every cycle

Telemetry

PAPI collects anonymous usage data (tool name, duration, project UUID — no code or task content). To opt out, add PAPI_TELEMETRY=off to your .mcp.json env block.

md mode warning

If you start the server without DATABASE_URL (or with PAPI_ADAPTER=md), you'll see a stderr warning: "PAPI is running in md mode — your cycles are not visible on the hosted dashboard." This is intentional. md mode stores everything locally in .papi/ files, but the hosted dashboard at getpapi.ai only sees projects backed by the database adapter.

When the warning fires, PAPI emits an anonymous install-level ping (random UUID stored at ~/.papi/install-id.json, chmod 600) per tool call so we can count installs that haven't connected yet. The ping contains: install UUID, tool name, server version, duration. No project content, no file paths, no user identifiers. Setting PAPI_TELEMETRY=off disables both the hosted-dashboard telemetry and the md-mode ping.

The warning is informational, not an error — md mode is a fully supported way to self-host PAPI without the hosted backend.

License

Elastic License 2.0 — free to use, self-host, and modify. Commercial hosting requires a license.