thewillmoss

anchor-mcp

Community thewillmoss
Updated

Portable agent working state MCP server — tasks, plans, notepads, memory, and rules for any AI coding agent

anchor-mcp

A portable agent working state server. Any AI coding agent drops anchor here.

Anchor is an MCP server that managespersistent working state for AI coding agents — tasks, plans, scratch notes,learnings, and project rules. It works with Claude Code, OpenCode, Codex CLI,Cursor, Windsurf, or any MCP-compatible agent.

Why?

Every AI coding tool has its own proprietary state directory (.claude/,.codex/, .opencode/). None of them share state. Anchor gives every agenta shared home base — the same active task, the same plans, the same memory —regardless of which tool you're using.

What it stores

Per git worktree, Anchor manages:

  • Active task — what you're working on right now
  • Plans — execution blueprints with linked issues and learnings
  • Notepads — freeform scratch notes by topic
  • Memory — tagged learnings, decisions, and patterns
  • Rules — project-specific agent instructions

Quick start

Install

npm install -g anchor-mcp

Configure (Claude Code)

Add to .claude/.mcp.json:

{
  "mcpServers": {
    "anchor": {
      "command": "anchor-mcp"
    }
  }
}

Configure (OpenCode)

Add to ~/.config/opencode/opencode.json:

{
  "mcp": {
    "anchor": {
      "type": "local",
      "command": ["anchor-mcp"],
      "enabled": true,
      "environment": {}
    }
  }
}

Configure (Codex CLI)

Add to .codex/config.toml:

[mcp_servers.anchor]
command = "anchor-mcp"

Configure (Cursor / Windsurf)

Add to your MCP server settings:

{
  "anchor": {
    "command": "anchor-mcp"
  }
}

Tools

Anchor provides 6 grouped tools. Each tool accepts an action parameter:

Tool Actions Description
task_manager get_active, set_active, complete, list Manage the active task and task list
plan_manager get, save, list Manage execution plans with issues and learnings
notepad_manager get, save, list Manage freeform scratch notes by topic
memory_manager add, search, list Store and retrieve learnings, decisions, patterns
rules_manager get, save Manage project-specific agent instructions
promote_learning (single action) Promote plan learnings into project rules

Usage examples

Set an active task:

task_manager(action="set_active", description="Implement user authentication")

Save a plan:

plan_manager(action="save", name="auth-flow", content="# Auth Flow Plan\n\n1. Add login endpoint\n2. Add JWT middleware")

Add a memory:

memory_manager(action="add", content="Always use httpOnly cookies for JWT", tags=["auth", "security"])

Search memories:

memory_manager(action="search", query="authentication")

State directory

Anchor stores state in .anchor/ at your project root:

.anchor/
├── state.json              # Active task + task list (gitignored)
├── plans/
│   └── {plan-name}/
│       ├── plan.md
│       ├── issues.md
│       └── learnings.md
├── notepads/
│   └── {topic}.md
├── memory.jsonl
└── rules.md

Plans, notepads, rules, and memory are designed to be committed to git.state.json is machine-specific and should be gitignored.

License

MIT

MCP Server · Populars

MCP Server · New

    uarlouski

    🚀 TestRail MCP Server

    AI-native MCP server connecting Claude, Cursor, Windsurf, and other AI assistants to TestRail — manage test cases, runs, and results through natural-language conversation, with typed schemas built for LLMs.

    Community uarlouski
    metabase

    Metabase MCP Server

    The easy-to-use open source Business Intelligence and Embedded Analytics tool that lets everyone work with data :bar_chart:

    Community metabase
    mindsdb

    USE CASES

    Platform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.

    Community mindsdb
    reflex-search

    Reflex

    Reflex - The instant, code-aware local search engine.

    Community reflex-search
    Licinexus

    @licinexusbr/mcp

    MCP server for Brazilian public procurement data (PNCP + Receita Federal). Maintained by Licinexus.

    Community Licinexus