# Lockkeeper

Selects only the matching skills and MCP tools for each coding prompt to save context. Includes a local firewall against prompt injections.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 18
- Author: Hannay001
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Hannay001/lockkeeper
- Updated: 2026-10-17
- HTML: https://affpapa.org/en/nevibecode/mcp/lockkeeper

## What it does

Installing numerous agent extensions often fills the prompt window with irrelevant documentation. Lockkeeper indexes skills, commands, and MCP servers across your tools. Instead of loading everything into the active session, it supplies up to 10 relevant capabilities per task alongside direct file locations.

Running as an MCP server exposes three tools: `route`, `search`, and `audit`. The server keeps its catalog cached in memory, ensuring immediate query responses. Its built-in filter inspects skill files and live tool operations, blocking concealed prompt injections and unauthorized data transfers.

Execution relies entirely on the Python 3.11+ standard library without third-party dependencies, extra cloud services, or API credentials. The catalog remains empty until you run `lockkeeper rebuild` to index existing agent configurations.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add lockkeeper -- uvx lockkeeper
```
uvx runs the command named after the package; if the README names another one, use uvx --from lockkeeper <command>

### Codex

**Platform CLI**
```bash
codex mcp add lockkeeper -- uvx lockkeeper
```
uvx runs the command named after the package; if the README names another one, use uvx --from lockkeeper <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "lockkeeper": {
            "command": "uvx",
            "args": [
                "lockkeeper"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from lockkeeper <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "lockkeeper": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "lockkeeper"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from lockkeeper <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add lockkeeper uvx lockkeeper
```
uvx runs the command named after the package; if the README names another one, use uvx --from lockkeeper <command>

## When to use it
- minimize token consumption when working with large skill libraries
- select task-specific MCP tools without cluttering prompt context
- scan external agent plugins for concealed injection attacks
- intercept hostile tool invocations before execution

## Example prompts
- Use Lockkeeper to route capabilities needed for an API refactoring task.
- Run the audit tool on my installed plugins to check for prompt injection.
- Search the local agent library for tools handling data pipeline tests.

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md