# Codeledger

> Codeledger is a freemium MCP server for developer tools. Local repo context bundles and evidence for AI coding agents before and after a task. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** CLI, macOS, Linux, Windows
- **Repository:** https://github.com/codeledgerecf/codeledger
- **MCP Registry name:** io.github.codeledgerECF/codeledger
- **Categories:** [developer tools](https://ai-powered.com/categories/developer-tools), [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-18

## About

CodeLedger scans a repository with deterministic local signals such as dependency structure, churn, tests, contracts and task keywords, then ranks and packs a bounded set of task-relevant files into a bundle at .codeledger/active-bundle.md. The agent reads that first, so it starts with the files most likely to matter. The same task on the same repo state gives the same ranking.

After the work, verification, receipts and session summaries show what changed and whether the selected context helped. Other features include scope contracts, loop detection, multi-agent conflict checks, session checkpoints and handoff commands. The README shows an example benchmark from a mid-sized Node.js service with fewer iterations and tokens, but cautions that results vary and offers a compare command to measure your own repo.

It works with Claude Code, Codex, Cursor, Copilot, Gemini CLI and others, and its MCP server (started with codeledger mcp start) is limited to supported feature tiers. Analysis runs locally and no account is needed for the CLI. The public wrapper is MIT, while the downloaded hardened runtime is under a separate Core License.

## Features

- **Task context bundles:** Selects a bounded, ranked set of files for a given task.
- **Deterministic ranking:** Same task and repo state give the same selection.
- **Scope governance:** Scope contracts, loop detection and conflict checks keep agents on task.
- **Verification receipts:** Records what changed and whether the context was useful.
- **Session continuity:** Checkpoints, summaries and handoff or recovery commands.
- **Local-first:** Runtime analysis runs on your machine without source telemetry by default.

## Good for

- Giving an agent the right files before a bug fix
- Comparing agent runs with and without curated context
- Auditing what an agent changed
- Handing a session over between agents
- Reducing token use on a large repo

## Install

### Claude Code (Terminal)

```sh
claude mcp add codeledger -- npx -y @codeledger/cli
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "codeledger": {
      "command": "npx",
      "args": [
        "-y",
        "@codeledger/cli"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "codeledger": {
      "command": "npx",
      "args": [
        "-y",
        "@codeledger/cli"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "codeledger": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@codeledger/cli"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "codeledger": {
      "command": "npx",
      "args": [
        "-y",
        "@codeledger/cli"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "codeledger": {
      "command": "npx",
      "args": [
        "-y",
        "@codeledger/cli"
      ]
    }
  }
}
```

## FAQ

### Is an account required?

No account is needed for the local CLI flow.

### Does it send my source code anywhere?

The README says runtime analysis is local and source code is not sent through telemetry by default.

### How do I install it?

npm install -g @codeledger/cli, then run codeledger ready --task.

### What is the licence?

The public wrapper and docs are MIT; the downloaded hardened binary uses a separate Core License.

### Is the MCP server available to everyone?

The README says it is offered for supported feature tiers.

### Is Codeledger free?

Codeledger has a free plan, with paid plans for more usage or features.

### How do I add Codeledger to Claude Code?

Run this command in your terminal: claude mcp add codeledger -- npx -y @codeledger/cli

### What are the best alternatives to Codeledger?

The closest alternatives to Codeledger are REA, Context7, Chrome DevTools MCP, Codebase Memory and GitHub.

## Where this comes from

- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Context7](https://ai-powered.com/mcp/context7): Context7 is a freemium MCP server for developer tools.
- [Chrome DevTools MCP](https://ai-powered.com/mcp/chrome-devtools-mcp-2): Chrome DevTools MCP is an open-source MCP server for browser automation.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [awesome-mcp-servers](https://ai-powered.com/mcp/awesome-mcp-servers-2): awesome-mcp-servers is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.

---
Source: https://ai-powered.com/mcp/codeledger
