mcpbeat Sign in

PAPI: Persistent Adaptive Project Intelligence MCP Server

by getpapi Your server? Claim it
answering

PAPI: Persistent Adaptive Project Intelligence is answering right now. Last checked 2 min ago. 159 installs a week from npm. Last commit 30 Oct 2026.

Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.

Installs per day peak 119 · avg 19 · -26% w/w
a month agotoday
Uptime history 91 days of history · worst day 0%
91 days agonow
78.3%
Uptime 24h
72 of 92 checks
—
Tools
hidden behind auth
184 ms
Response time
average over 24h
159
Installs / week
npm and PyPI

What the code does

We read the source, 3 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

File ships in the package but is absent from the source [пакет] design-assets/hooks/frontend-design-guard.sh:1, [пакет] design-assets/hooks/papi-collision-guard.mjs:1, [пакет] design-assets/hooks/papi-collision-opencode.mjs:1 
этот файл ставится пользователю, но в репозитории его нет

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

run in your terminal
claude mcp add papi --transport http https://mcp.getpapi.ai/mcp
Settings → Connectors → Add custom connector, then paste this address
https://mcp.getpapi.ai/mcp
~/.codex/config.toml
[mcp_servers.papi]
url = "https://mcp.getpapi.ai/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "papi": {
      "url": "https://mcp.getpapi.ai/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "papi": {
      "type": "http",
      "url": "https://mcp.getpapi.ai/mcp"
    }
  }
}

This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.

Endpoints

URLTransportStateLatencyChecked
https://mcp.getpapi.ai/mcp streamable-http sign-in 163 ms 2 min ago

Alternatives to PAPI: Persistent Adaptive Project Intelligence

same job, measured the same way
Memorykit
by rapozoantonio

Cognitive memory for AI coding assistants — persistent memory across sessions

50 installs/wk local only
I
In Memoria
by pi22by7

Persistent codebase intelligence that gives AI assistants memory across sessions

110 installs/wk local only
I
In Memoria
by pi22by7

Persistent codebase intelligence that gives AI assistants memory across sessions

local only
Session Forge
by 420247jake

Persistent memory and session intelligence for AI coding assistants. Zero config.

40 installs/wk local only
Memory
by velixarai

Persistent memory for AI assistants. Store, search, and recall across sessions.

91 installs/wk local only
Tempera
by anvanster

Persistent episodic memory for AI coding: capture, retrieve, brief, dream cycle, cross-project.

84 installs/wk local only
Memoir
by camgitt

Persistent memory for AI coding tools via MCP. Remembers across sessions and machines.

593 installs/wk local only
Agentwebintel
by mlartab

Proxy-rotated web scraping and cross-platform intelligence for AI agents.

2 tools answering

PAPI: Persistent Adaptive Project Intelligence — questions

Answers built from our own checks of this server.

Why is there no tool list for PAPI: Persistent Adaptive Project Intelligence?
The server answered our handshake with an authorization challenge, so it is running — but it will not describe its tools to an anonymous client. To see them you need to connect with your own credentials. We record it as alive, not as broken: 78.3% of checks in the last 24 hours got a reply.
Is PAPI: Persistent Adaptive Project Intelligence working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 72 of 92 checks got a reply (78.3%), average response time 184 ms. The bar chart above shows every period we have measured.
How do I connect PAPI: Persistent Adaptive Project Intelligence?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address. You sign in through your browser once and the client keeps the session: no key to copy, and it refuses anonymous clients.
How do you sign in to PAPI: Persistent Adaptive Project Intelligence?
No API key is involved. PAPI: Persistent Adaptive Project Intelligence answers our knock with an OAuth challenge, so you authorise it once in your browser and the client keeps the session. That is also why we see no tool list: it will not describe itself to an anonymous client, and that is the server working as intended, not a fault.
How fast is PAPI: Persistent Adaptive Project Intelligence?
It answers our handshake in 184 ms on average, which is faster than 74% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use PAPI: Persistent Adaptive Project Intelligence?
The npm package @papi-ai/server was installed 159 times in the last week. Week over week that is -26%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is PAPI: Persistent Adaptive Project Intelligence open source?
The code is open source: it is published under the MIT licence, written in Python and 11 stars on GitHub. The licence covers the code in the repository, not the hosted service at mcp.getpapi.ai, which runs on its operator's own terms.