by openconstruct
Llama.cpp Bridge connects local llama-server instances to MCP clients, enabling chat, health checks, and flexible llama.
Connects Claude Desktop to your local llama.cpp models, letting you chat with local LLMs directly through Claude's interface.
Llama.cpp Bridge is a community-built MCP server published by openconstruct that provides AI assistants with tools and capabilities via the Model Context Protocol. Llama.cpp Bridge connects local llama-server instances to MCP clients, enabling chat, health checks, and flexible llama. It is categorized under ai ml, developer tools.
You can install Llama.cpp Bridge in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Llama.cpp Bridge is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Llama.cpp Bridge is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Useful MCP listing: Llama.cpp Bridge is the kind of server we cite when onboarding engineers to host + tool permissions.
Llama.cpp Bridge is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Useful MCP listing: Llama.cpp Bridge is the kind of server we cite when onboarding engineers to host + tool permissions.
Useful MCP listing: Llama.cpp Bridge is the kind of server we cite when onboarding engineers to host + tool permissions.
Llama.cpp Bridge is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We wired Llama.cpp Bridge into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Llama.cpp Bridge reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Llama.cpp Bridge reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Llama.cpp Bridge is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
showing 1-10 of 38
A Model Context Protocol (MCP) server that bridges Claude Desktop with your local LLM instance running via llama-server.
npm install @openconstruct/llama-mcp-server
A Model Context Protocol (MCP) server that bridges Claude Desktop with your local LLM instance running via llama-server.
cd llama-mcp
npm install
npm run build
Make sure llama-server is running with your model:
./llama-server -m lm37.gguf -c 2048 --port 8080
Add this to your Claude Desktop configuration (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"libremodel": {
"command": "node",
"args": ["/home/jerr/llama-mcp/dist/index.js"]
}
}
}
Claude will now have access to LibreModel through MCP!
Once configured, you can use these tools in Claude Desktop:
chat - Main conversation toolUse the chat tool to ask LibreModel: "What is your name and what can you do?"
quick_test - Test LibreModel capabilitiesRun a quick_test with type "creative" to see if LibreModel can write poetry
health_check - Monitor server statusUse health_check to see if LibreModel is running properly
Set environment variables to customize behavior:
export LLAMA_SERVER_URL="http://localhost:8080" # Default llama-server URL
| Tool | Description | Parameters |
|---|---|---|
chat | Converse with MOdel | message, temperature, max_tokens, top_p, top_k, system_prompt |
quick_test | Run predefined capability tests | test_type (hello/math/creative/knowledge) |
health_check | Check server health and status | None |
# Install dependencies
npm install # LibreModel MCP Server 🤖
A Model Context Protocol (MCP) server that bridges Claude Desktop with your local LLM instance running via llama-server.
## Features
- 💬 **Full conversation support** with LibreModel through Claude Desktop
- 🎛️ **Complete parameter control** (temperature, max_tokens, top_p, top_k)
- ✅ **Health monitoring** and server status checks
- 🧪 **Built-in testing tools** for different capabilities
- 📊 **Performance metrics** and token usage tracking
- 🔧 **Easy configuration** via environment variables
## Quick Start
### 1. Install Dependencies
```bash
cd llama-mcp
npm install
npm run build
Make sure llama-server is running with your model:
./llama-server -m lm37.gguf -c 2048 --port 8080
Add this to your Claude Desktop configuration (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"libremodel": {
"command": "node",
"args": ["/home/jerr/llama-mcp/dist/index.js"]
}
}
}
Claude will now have access to LibreModel through MCP!
Once configured, you can use these tools in Claude Desktop:
chat - Main conversation toolUse the chat tool to ask LibreModel: "What is your name and what can you do?"
quick_test - Test LibreModel capabilitiesRun a quick_test with type "creative" to see if LibreModel can write poetry
health_check - Monitor server statusUse health_check to see if LibreModel is running properly
Set environment variables to customize behavior:
export LLAMA_SERVER_URL="http://localhost:8080" # Default llama-server URL
| Tool | Description | Parameters |
|---|---|---|
chat | Converse with MOdel | message, temperature, max_tokens, top_p, top_k, system_prompt |
quick_test | Run predefined capability tests | test_type (hello/math/creative/knowledge) |
health_check | Check server health and status | None |
# Install dependencies
npm install openconstruct/llama-mcp-server
# Development mode (auto-rebuild)
npm run dev
# Build for production
npm run build
# Start the server directly
npm start
Claude Desktop ←→ LLama MCP Server ←→ llama-server API ←→ Local Model
The MCP server acts as a bridge, translating MCP protocol messages into llama-server API calls and formatting responses for Claude Desktop.
"Cannot reach LLama server"
"Tool not found in Claude Desktop"
index.js is correct and absolutePoor response quality
CC0-1.0 - Public Domain. Use freely!
Built with ❤️ for open-source AI and the LibreModel project. by Claude Sonnet4
npm run dev
npm run build
npm start
## Architecture
Claude Desktop ←→ LLama MCP Server ←→ llama-server API ←→ Local Model
The MCP server acts as a bridge, translating MCP protocol messages into llama-server API calls and formatting responses for Claude Desktop.
## Troubleshooting
**"Cannot reach LLama server"**
- Ensure llama-server is running on the configured port
- Check that the model is loaded and responding
- Verify firewall/network settings
**"Tool not found in Claude Desktop"**
- Restart Claude Desktop after configuration changes
- Check that the path to `index.js` is correct and absolute
- Verify the MCP server builds without errors
**Poor response quality**
- Adjust temperature and sampling parameters
- Try different system prompts
## License
CC0-1.0 - Public Domain. Use freely!
---
Built with ❤️ for open-source AI and the LibreModel project. by Claude Sonnet4
### 1. Install Dependencies
```bash
cd llama-mcp
npm install
npm run build
Make sure llama-server is running with your model:
./llama-server -m lm37.gguf -c 2048 --port 8080
Add this to your Claude Desktop configuration (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"libremodel": {
"command": "node",
"args": ["/home/jerr/llama-mcp/dist/index.js"]
}
}
}
Claude will now have access to LibreModel through MCP!
Once configured, you can use these tools in Claude Desktop:
chat - Main conversation toolUse the chat tool to ask LibreModel: "What is your name and what can you do?"
quick_test - Test LibreModel capabilitiesRun a quick_test with type "creative" to see if LibreModel can write poetry
health_check - Monitor server statusUse health_check to see if LibreModel is running properly
Set environment variables to customize behavior:
export LLAMA_SERVER_URL="http://localhost:8080" # Default llama-server URL
| Tool | Description | Parameters |
|---|---|---|
chat | Converse with MOdel | message, temperature, max_tokens, top_p, top_k, system_prompt |
quick_test | Run predefined capability tests | test_type (hello/math/creative/knowledge) |
health_check | Check server health and status | None |
# Install dependencies
npm install
# Development mode (auto-rebuild)
npm run dev
# Build for production
npm run build
# Start the server directly
npm start
Claude Desktop ←→ LLama MCP Server ←→ llama-server API ←→ Local Model
The MCP server acts as a bridge, translating MCP protocol messages into llama-server API calls and formatting responses for Claude Desktop.
"Cannot reach LLama server"
"Tool not found in Claude Desktop"
index.js is correct and absolutePoor response quality
CC0-1.0 - Public Domain. Use freely!
Built with ❤️ for open-source AI and the LibreModel project. by Claude Sonnet
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.