Developer · Remote MCP server
PAPI: Persistent Adaptive Project Intelligence
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
Visit PAPI: Persistent Adaptive Project Intelligence's website
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.getpapi/papi- Version
- 0.402.35
- Status
- Active
- Category
- developer
- Transport
- Streamable HTTP, stdio (local process)
- Package
- npm
- Published
- 2026-09-26
- Updated
- 2026-09-26
- Publisher
- getpapi (GitHub)
- Website
- getpapi.ai
- Repository
- github.com/getpapi/papi
- Source
- Registry API entry
Remote endpoints
| Transport | URL | Headers declared |
|---|---|---|
| Streamable HTTP | https://mcp.getpapi.ai/mcp | None |
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| npmruntime: npx | @papi-ai/server | 0.402.35 | stdio |
How to connect PAPI: Persistent Adaptive Project Intelligence
PAPI: Persistent Adaptive Project Intelligence is a remote MCP server: there is nothing to install. Its endpoint is https://mcp.getpapi.ai/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.
No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.
It can also run locally from a Node.js package published to the npm registry: @papi-ai/server version 0.402.35. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @papi-ai/server@0.402.35.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"papi": {
"command": "npx",
"args": [
"-y",
"@papi-ai/server@0.402.35"
]
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Panel ReviewGuardian agent for AI coding: four frontier models review risky diffs and commits before they ship. | Remote · HTTP |
| Panini Connector MCPInstall + verify the panini-connector SDK on self-hosted sites, driven by AI agents. | Local · stdio |
| Paparats – Local Semantic Code Search MCPLocal-first semantic code search across all your repos. Private context for AI coding assistants. | Local · HTTP |
| Paperless-ngxMCP server for Paperless-ngx 3.x — full REST API coverage, schema-aware, token-frugal. | Local · stdio |
| ParallelSandboxRemote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover. | Remote & Local · HTTP, stdio |
| ParaView MCP ServerControl ParaView through arbitrary Python code. | Local · stdio |
| parbakedScaffold invite-only Python/FastAPI apps: auth, admin dashboard, dev server, deploy to fly.io. | Local · stdio |
| ParCADParametric CAD as code: model 3D-printable parts on an exact B-rep kernel, measured. | Local · stdio |