PAPI — Persistent Agentic Planning Intelligence
- cathalos92/papi-ui
PAPI is a MCP server that structures AI project planning with cycles, tasks, strategy reviews, and build handoffs.
About
PAPI (Persistent Agentic Planning Intelligence) is an MCP server that gives coding agents a durable project planning layer: cycles, tasks, strategy reviews, and explicit handoffs into build work. developers who juggle idea, validate, and build hats use it when chat history is too ephemeral to track what was decided last week or which milestone blocks launch. Installed through @papi-ai/server with npx stdio transport (version 0.7.12 in the manifest), it sits between lightweight TODO markdown and a full PM SaaS—opinionated structure for agentic development rather than passive documentation. Canonical shelf is validate scope because narrowing MVP and recording strategy reviews happens before heavy coding, but journey use extends into build PM and operate iterate when you revisit cycles. It is a planning MCP, not a git host, CI runner, or deployment tool; pair it with implementation skills once plans are approved.
- Persistent Agentic Planning Intelligence (PAPI) via @papi-ai/server stdio (npx, v0.7.12)
- Structured cycles, tasks, and strategy reviews for long-running agent projects
- Build handoffs from planning state into implementation work
- UI and docs at https://getpapi.ai; server repo cathalos92/papi-ui on GitHub
- npm-based stdio MCP suitable for Claude Code and Cursor style workflows
PAPI — Persistent Agentic Planning Intelligence by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add papi -- npx -y @papi-ai/serverAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | @papi-ai/server |
|---|---|
| Transport | STDIO |
| Auth | None |
| Repository | cathalos92/papi-ui ↗ |
What it does
Run structured planning cycles—tasks, strategy reviews, and handoffs to implementation—so your agent does not drift across a project.
Who is it for?
Best when you're running multi-week agent-assisted projects and need structured PM state beyond a single chat thread.
Skip if: One-session bugfixes or developers who already run a rigid Superpowers stack and do not want another planning layer.
What you get
You get persistent cycles and tasks with strategy reviews and clear handoffs so your agent continues from an approved plan into build work.
- Structured project cycles and task lists visible to the agent
- Documented strategy reviews before major build commits
- Explicit build handoffs from planning state to implementation tasks
By the numbers
- MCP server version 0.7.12; npm package @papi-ai/server
- Stdio transport with npx runtimeHint
- Four planning pillars in description: cycles, tasks, strategy reviews, build handoffs
Recommended MCP Servers
0piFree, 2hr expiry agent storage to cache contexts, bridge workflows, or dump data.
100Hires AI ATS & Recruitment SoftwareOfficial 100Hires MCP: AI ATS & Recruitment Software for candidates, jobs, applications, interviews.
123elec McpInterface MCP officielle du site marchand 123elec, catalogue, stock, panier, commandes.
1stayHotel booking MCP server.2
2D Assets MCPMCP server for generating advanced mock 2D PNG assets for game prototypes.43D MeshWeaverMesh spatial optimizer reducing geometric overhead in 3D assets.How it compares
Persistent agentic planning MCP, not a deployment or monitoring integration.
FAQ
Who is PAPI for?
and small-team developers using Claude Code or similar agents who need durable cycles, tasks, and strategy reviews across many sessions.
When should I use PAPI?
Use it when validating and scoping an MVP, then keep it through build handoffs whenever the agent must track what is in-cycle versus deferred.
How do I add PAPI to my agent?
Configure stdio MCP to run @papi-ai/server via npx per getpapi.ai instructions, version 0.7.12, and connect your client before starting planning cycles.