# Markdown Pipeline

> Markdown Pipeline is an open-source MCP server for files and documents. Keep Jira issues as read-only Markdown files your agent can search, with source links. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** Linux, CLI, self-hosted
- **Website:** https://markdownpipeline.com
- **Repository:** https://github.com/markdown-pipeline/markdown-pipeline
- **MCP Registry name:** io.github.markdown-pipeline/mdpipeline
- **Categories:** files and documents, knowledge and memory, productivity
- **Listing updated:** 2026-11-14

## About

Markdown Pipeline is a local app that copies a team's Jira Cloud issues into plain Markdown files, either in a folder on your computer or a GitHub repo you choose. Each file links back to its source and records when it was synced, and nothing is summarized or rewritten. Edits and deletions in Jira are kept in sync while the app runs, so removed issues stop being cited.

The bundled MCP server exposes `search`, `read`, `list`, `recent_changes` (for questions like what changed since yesterday), `sync_status` and `sync`. No tool writes or edits your files, and the server reads only the Markdown the app wrote plus your `raw/` and `wiki/` folders. `mdpipeline connect --agent claude` or `--agent codex` prints the setup for your agent.

It reads Jira with your own account's API token, so the files hold only what that account can see, and it never changes anything in Jira. A preview comes before anything is written. Linux is tested; macOS is untested and Windows works under WSL 2. Confluence, Google Drive, Notion, Linear and more are listed as coming next. The code is Apache-2.0.

## Features

- **Jira to Markdown:** Syncs Jira Cloud issues into clean Markdown files.
- **Source link on every file:** Each file records where it came from and when.
- **Stays current:** Edits and deletions are mirrored while the app runs.
- **Preview before writing:** Nothing is written until you approve the preview.
- **Read-only MCP tools:** Search, read, list and recent-changes tools that never edit files.
- **Folder or GitHub repo:** Write to a local folder or a team repo.

## Good for

- Let Claude Code or Codex search a team's Jira history
- Ask what changed in the tracker since yesterday
- Build a raw layer for a team LLM wiki
- Avoid agents citing deleted issues

## Install

### Claude Code (Terminal)

```sh
claude mcp add mdpipeline -- uvx mdpipeline
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

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

```json
{
  "servers": {
    "mdpipeline": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "mdpipeline": {
      "command": "uvx",
      "args": [
        "mdpipeline"
      ]
    }
  }
}
```

## Tools

- `search`: Searches the synced Markdown files.
- `read`: Reads a synced file.
- `list`: Lists synced files.
- `recent_changes`: Shows what changed recently, such as since yesterday.
- `sync_status`: Reports the state of the sync.
- `sync`: Triggers a sync.

## FAQ

### Does it change anything in Jira?

No. It only reads, using your own Jira API token.

### Which platforms work?

Linux is tested, macOS is untested and Windows works inside WSL 2.

### What is the licence and price?

Apache-2.0, and free during early access with no account.

### Which sources are supported?

Jira Cloud and local folders today; Confluence, Notion, Google Drive and others are planned.

### Is Markdown Pipeline free?

Yes. Markdown Pipeline is open source, so you can use and self-host it for free.

### How do I add Markdown Pipeline to Claude Code?

Run this command in your terminal: claude mcp add mdpipeline -- uvx mdpipeline

### What are the best alternatives to Markdown Pipeline?

The closest alternatives to Markdown Pipeline are Codebase Memory, XERJ, Ha MCP, Claude Code Ultimate Guide and Nautilus Compass Memory.

## Alternatives

- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ha MCP](https://ai-powered.com/mcp/ha-mcp): Ha MCP is an open-source MCP server for productivity.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Nautilus Compass Memory](https://ai-powered.com/mcp/nautilus-compass-memory): Nautilus Compass Memory is an open-source MCP server for knowledge and memory.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.
- [note1](https://ai-powered.com/mcp/note1): note1 is an MCP server for productivity.
- [ASTra](https://ai-powered.com/mcp/astra): ASTra is a freemium MCP server for files and documents.

---
Source: https://ai-powered.com/mcp/markdown-pipeline
