Using PaPut MCP with Coding Agents

This page introduces the Local CLI Mode steps for saving knowledge gained while coding in Claude Code or Codex to PaPut.

When using session scan, pending knowledge candidates, or the local cache, use Local CLI Mode instead of Remote MCP. Remote MCP is for normal operations on memos, notes, and skill sheets, and does not provide tools for reading local sessions or the pending cache.

Prerequisites

Node.js / npx is available
You have a PaPut account
You can use Claude Code or Codex

OAuth login

First, obtain the OAuth token used in Local CLI Mode.

npx -y paput-mcp login

Log in to PaPut in your browser and authorize the integration
The token is saved to ~/.paput/oauth.json
To log out, run the following

npx -y paput-mcp logout

MCP configuration example

Add the following to your Claude Code or Codex MCP configuration.

"paput": {
  "command": "npx",
  "args": ["-y", "paput-mcp"],
  "env": {
    "PAPUT_PROJECT_MATCH": "part of any project name"
  }
}

PAPUT_PROJECT_MATCH is optional
When set, memos can be automatically linked to matching skill sheet projects on creation or update

setup-ai

Add PaPut skills and global usage rules for Claude / Codex.

npx -y paput-mcp setup-ai

This command adds PaPut skills for initialization, syncing, extracting knowledge candidates, and confirming before saving. It also adds usage rules that detect reusable technical knowledge at the end of work and add it to pending candidates.

To update existing settings, add --force.

npx -y paput-mcp setup-ai --force

To target Claude only, add --claude-only.

npx -y paput-mcp setup-ai --claude-only

Automatic pending candidate flow

After setup-ai, PaPut knowledge capture rules are added to the global instructions used by Claude Code or Codex. When work is completed, a problem is solved, or a design decision is settled, the AI checks for reusable technical knowledge and adds non-duplicate, non-sensitive, non-project-specific candidates to pending.

Normally, you do not need to run /paput-capture manually every time. Use /paput-capture only when you explicitly want to extract candidates from a specific conversation or topic.

Example skills you can use

/paput-init: Initialize, sync existing memos, check unprocessed sessions
/paput-sync: Sync existing PaPut memos to the local cache
/paput-capture: Manually add knowledge candidates from the current conversation or a specified topic to pending
/paput-save: Review pending candidates and save only the ones you explicitly approve to PaPut

Recommended workflow

/paput-init
Do your work
Run /paput-save when needed

Useful knowledge is usually added to pending automatically while you work
Before saving, use /paput-save to review candidates and filter out duplicates or project-specific information
Use /paput-capture only when you want to explicitly capture a specific topic
To create skill sheet project summaries, also see Create project AI summaries with MCP

Notes

In Remote HTTP Mode, local session scan, pending cache, and transcript reading are not available
No API key is needed; OAuth is used
Local token and cache are saved under ~/.paput
If you change the MCP configuration on the Claude Code or Codex side, a restart or reload may be required