https://github.com/phil65/mcp-server-llmling
MCP (Model context protocol) server with LLMling backend
https://github.com/phil65/mcp-server-llmling
Last synced: 6 months ago
JSON representation
MCP (Model context protocol) server with LLMling backend
- Host: GitHub
- URL: https://github.com/phil65/mcp-server-llmling
- Owner: phil65
- License: mit
- Created: 2024-12-05T10:10:16.000Z (11 months ago)
- Default Branch: main
- Last Pushed: 2025-03-27T08:11:52.000Z (7 months ago)
- Last Synced: 2025-04-14T12:41:21.481Z (7 months ago)
- Language: Python
- Size: 306 KB
- Stars: 5
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
- awesome-mcp-servers - **mcp-server-llmling** - MCP (Model context protocol) server with LLMling backend `python` `mcp` `server` `ml` `llm` `pip install git+https://github.com/phil65/mcp-server-llmling` (🤖 AI/ML)
- awesome-mcp-servers - **mcp-server-llmling** - MCP (Model context protocol) server with LLMling backend `python` `mcp` `server` `ml` `llm` `pip install git+https://github.com/phil65/mcp-server-llmling` (AI/ML)
- metorial-index - LLMLing Server - Set up custom LLM servers using YAML configurations, providing access to resources and structured prompts. It facilitates extending capabilities with callable tools while adhering to the Machine Chat Protocol. (Developer Tools)
README
# mcp-server-llmling
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://pypi.org/project/mcp-server-llmling/)
[](https://github.com/phil65/mcp-server-llmling/releases)
[](https://github.com/phil65/mcp-server-llmling/graphs/contributors)
[](https://github.com/phil65/mcp-server-llmling/discussions)
[](https://github.com/phil65/mcp-server-llmling/forks)
[](https://github.com/phil65/mcp-server-llmling/issues)
[](https://github.com/phil65/mcp-server-llmling/pulls)
[](https://github.com/phil65/mcp-server-llmling/watchers)
[](https://github.com/phil65/mcp-server-llmling/stars)
[](https://github.com/phil65/mcp-server-llmling)
[](https://github.com/phil65/mcp-server-llmling/commits)
[](https://github.com/phil65/mcp-server-llmling/releases)
[](https://github.com/phil65/mcp-server-llmling)
[](https://github.com/phil65/mcp-server-llmling)
[](https://github.com/phil65/mcp-server-llmling)
[](https://github.com/phil65/mcp-server-llmling)
[](https://codecov.io/gh/phil65/mcp-server-llmling/)
[](https://github.com/psf/black)
[](https://pyup.io/repos/github/phil65/mcp-server-llmling/)
[Read the documentation!](https://phil65.github.io/mcp-server-llmling/)
# LLMling Server Manual
## Overview
mcp-server-llmling is a server for the Machine Chat Protocol (MCP) that provides a YAML-based configuration system for LLM applications.
[LLMLing](https://phil65.github.io/LLMling/), the backend, provides a YAML-based configuration system for LLM applications.
It allows to set up custom MCP servers serving content defined in YAML files.
- **Static Declaration**: Define your LLM's environment in YAML - no code required
- **MCP Protocol**: Built on the Machine Chat Protocol (MCP) for standardized LLM interaction
- **Component Types**:
- **Resources**: Content providers (files, text, CLI output, etc.)
- **Prompts**: Message templates with arguments
- **Tools**: Python functions callable by the LLM
The YAML configuration creates a complete environment that provides the LLM with:
- Access to content via resources
- Structured prompts for consistent interaction
- Tools for extending capabilities
## Key Features
### 1. Resource Management
- Load and manage different types of resources:
- Text files (`PathResource`)
- Raw text content (`TextResource`)
- CLI command output (`CLIResource`)
- Python source code (`SourceResource`)
- Python callable results (`CallableResource`)
- Images (`ImageResource`)
- Support for resource watching/hot-reload
- Resource processing pipelines
- URI-based resource access
### 2. Tool System
- Register and execute Python functions as LLM tools
- Support for OpenAPI-based tools
- Entry point-based tool discovery
- Tool validation and parameter checking
- Structured tool responses
### 3. Prompt Management
- Static prompts with template support
- Dynamic prompts from Python functions
- File-based prompts
- Prompt argument validation
- Completion suggestions for prompt arguments
### 4. Multiple Transport Options
- Stdio-based communication (default)
- Server-Sent Events (SSE) for web clients
- Support for custom transport implementations
## Usage
### With Zed Editor
Add LLMLing as a context server in your `settings.json`:
```json
{
"context_servers": {
"llmling": {
"command": {
"env": {},
"label": "llmling",
"path": "uvx",
"args": [
"mcp-server-llmling",
"start",
"path/to/your/config.yml"
]
},
"settings": {}
}
}
}
```
### With Claude Desktop
Configure LLMLing in your `claude_desktop_config.json`:
```json
{
"mcpServers": {
"llmling": {
"command": "uvx",
"args": [
"mcp-server-llmling",
"start",
"path/to/your/config.yml"
],
"env": {}
}
}
}
```
### Manual Server Start
Start the server directly from command line:
```bash
# Latest version
uvx mcp-server-llmling@latest
```
### 1. Programmatic usage
```python
from llmling import RuntimeConfig
from mcp_server_llmling import LLMLingServer
async def main() -> None:
async with RuntimeConfig.open(config) as runtime:
server = LLMLingServer(runtime, enable_injection=True)
await server.start()
asyncio.run(main())
```
### 2. Using Custom Transport
```python
from llmling import RuntimeConfig
from mcp_server_llmling import LLMLingServer
async def main() -> None:
async with RuntimeConfig.open(config) as runtime:
server = LLMLingServer(
config,
transport="sse",
transport_options={
"host": "localhost",
"port": 8000,
"cors_origins": ["http://localhost:3000"]
}
)
await server.start()
asyncio.run(main())
```
### 3. Resource Configuration
```yaml
resources:
python_code:
type: path
path: "./src/**/*.py"
watch:
enabled: true
patterns:
- "*.py"
- "!**/__pycache__/**"
api_docs:
type: text
content: |
API Documentation
================
...
```
### 4. Tool Configuration
```yaml
tools:
analyze_code:
import_path: "mymodule.tools.analyze_code"
description: "Analyze Python code structure"
toolsets:
api:
type: openapi
spec: "https://api.example.com/openapi.json"
namespace: "api"
```
## Server Configuration
The server is configured through a YAML file with the following sections:
```yaml
global_settings:
timeout: 30
max_retries: 3
log_level: "INFO"
requirements: []
pip_index_url: null
extra_paths: []
resources:
# Resource definitions...
tools:
# Tool definitions...
toolsets:
# Toolset definitions...
prompts:
# Prompt definitions...
```
## MCP Protocol
The server implements the MCP protocol which supports:
1. **Resource Operations**
- List available resources
- Read resource content
- Watch for resource changes
2. **Tool Operations**
- List available tools
- Execute tools with parameters
- Get tool schemas
3. **Prompt Operations**
- List available prompts
- Get formatted prompts
- Get completions for prompt arguments
4. **Notifications**
- Resource changes
- Tool/prompt list updates
- Progress updates
- Log messages