PAPI

by getpapi

273 downloads Not rated yet

GitHub Website

About

Persistent Adaptive Planning Intelligence - structured loop engineering for AI coding assistants, with memory that persists across sessions, tools, and teammates.

Explore

- Plan, build, review, and release cycles that persist across sessions.
- Strategy reviews every few cycles to check direction.
- Dashboard at getpapi.ai showing cycles, board, and decisions.
- Memory that compounds—assistant starts every session knowing the project state.
- Methodology embedded in the product: plan, build, review, release loop.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name PAPI

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

From the repository

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

A browser tab opens, you sign in, you're connected. Then tell your assistant: "Run setup, then orient."

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "papi": {
            "papi": {
                "url": "https://mcp.getpapi.ai/mcp"
            }
        }
    }
}

McpServers

{
    "papi": {
        "url": "https://mcp.getpapi.ai/mcp"
    }
}

PAPI keeps you in control of what you're building, across every AI tool you and your team use. AI coding tools write code well and remember nothing. Every new session starts from zero - you re-explain the project, the decisions, the plan. PAPI is the layer that fixes that: structured project memory (plans, builds, reviews, decisions) that persists across sessions, tools, and teammates.

Quick start

claude mcp add --transport http papi https://mcp.getpapi.ai/mcp A browser tab opens, you sign in, you're connected. Then tell your assistant: "Run setup, then orient."

What you get

- plan — breaks goals into right-sized tasks, each with a build handoff your assistant executes directly. - build — tracks what was built, what surprised you, what was discovered. - review / release — close the loop, so every cycle feeds the next plan. - strategy reviews — every few cycles step back and check direction, not just velocity. - dashboard at getpapi.ai — see cycles, board, and decisions without asking. The methodology is the product: a plan/build/review/release loop with memory that compounds. PAPI has been built with PAPI for 320+ cycles. Works with Claude Code, Cursor, VS Code, Windsurf, and Codex.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Explore

Setting up with Highlight

From the repository

Claude Desktop / Cursor

McpServers

Quick start

What you get

More like this

GitLab

Context 7

1Panel

🔎 GPT Researcher