# PMB AI MCP server

> Give AI coding agents persistent local memory for decisions, lessons and facts, stored in a single SQLite file on your disk.

- Listing: https://mcp.tc/i/pmb-ai
- Connect: this is a local (stdio) server; install it on your machine (see Install). The listing link is a page, not an MCP endpoint.
- Type: local (stdio)
- Auth: no API key needed
- Category: [AI & Machine Learning](https://mcp.tc/c/ai-ml)
- Vendor: oleksiijko
- Docs: <https://github.com/oleksiijko/pmb>
- Repository: <https://github.com/oleksiijko/pmb>
- Package: pypi `pmb-ai`

## About

PMB stores decisions, lessons, personal facts, project structure and indexed PDFs in a local workspace, with SQLite as the source of truth and LanceDB search indexes beside it. Agents such as Claude Code, Cursor and Codex read it back over MCP. The prepare tool returns project context, lessons, recent activity and open goals for a message, and recall runs hybrid search (BM25, vector, graph, rerank). The README mentions 27 other tools.

It runs locally over stdio as the PyPI package pmb-ai, started with uvx. No account, API key or cloud service is needed, and the README says nothing leaves your machine. A pmb setup command detects your agent and writes the MCP entry, and a local dashboard is available on 127.0.0.1.

## What it can do

- Recall past decisions and lessons across agent sessions
- Fetch project context, open goals and recent activity with prepare
- Hybrid search over memory with recall
- Record keyed personal facts that keep old values archived
- Index project code structure and PDFs for later retrieval
- Browse memory in a local dashboard on 127.0.0.1
- Export all stored memory to Markdown or JSON

## Example prompts

- "Fix that pricing bug we hit last Tuesday, using what you remember about it."
- "Recall our earlier decision about the auth approach."
- "Remember that this project must never lower the threshold under 25%."
- "Index the PDF paper.pdf so you can answer questions about it later."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport stdio pmb-ai -- uvx pmb-ai
```

2. Start Claude Code and type `/mcp`. **pmb-ai** should show as connected.

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Developer → Edit Config**. It opens `claude_desktop_config.json`. Add:

`claude_desktop_config.json`:

```json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
```

2. Save the file and restart Claude Desktop.

Needs uv (Python) on your computer. The file lives in `~/Library/Application Support/Claude/` on macOS and `%APPDATA%\Claude\` on Windows.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=pmb-ai&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJwbWItYWkiXX0%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=pmb-ai&config=%7B%22type%22%3A%22stdio%22%2C%22command%22%3A%22uvx%22%2C%22args%22%3A%5B%22pmb-ai%22%5D%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"pmb-ai","type":"stdio","command":"uvx","args":["pmb-ai"]}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "pmb-ai": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
```

Needs uv (Python) on your computer.

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf.

### Codex

```bash
codex mcp add pmb-ai -- uvx pmb-ai
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.pmb-ai]
command = "uvx"
args = ["pmb-ai"]
```

Needs uv (Python) on your computer.

### Gemini CLI

```bash
gemini mcp add pmb-ai uvx pmb-ai
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients that start local servers accept this shape:

```json
{
  "mcpServers": {
    "pmb-ai": {
      "command": "uvx",
      "args": [
        "pmb-ai"
      ]
    }
  }
}
```

Zed puts servers under `context_servers` in its settings, with the same `command`, `args` and `env` fields.

Needs uv (Python) on your computer.

## Details

- Server version: 1.1.0
- Last checked: 2026-10-04
- Listed: 2026-10-04
- Updated: 2026-10-04

---
Source: https://mcp.tc/i/pmb-ai (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report