Model Context Provider (MCP) Server
LocalAbout Model Context Provider (MCP) Server
A lightweight MCP server for managing structured context for AI applications. It matches queries to relevant context using keyword search and returns model-ready results.
Key features
- 01Add, update, and retrieve context
- 02Keyword-based context matching
- 03JSON context storage
- 04Load context from JSON files
- 05Debug logs for query processing
Use cases
- 01Store and update application context
- 02Retrieve context relevant to a user query
MCP support
Exposes context management and query methods to MCP clients, including retrieval of structured, model-ready context.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEModel Context Provider (MCP) Server
Overview
The Model Context Provider (MCP) Server is a lightweight and efficient system designed to manage contextual data for AI models. It helps AI applications retrieve relevant context based on user queries, improving the overall intelligence and responsiveness of AI-driven systems.
Features
- Context Management: Add, update, and retrieve structured context data.
- Query-Based Context Matching: Identify relevant contexts using a keyword-based search algorithm.
- JSON-Based Storage: Handles structured AI context data.
- File-Based Context Loading: Load context dynamically from external JSON files.
- Debugging Support: Provides detailed debug logs for query processing.
Installation
To install and run the MCP Server, follow these steps:
# Clone the repository
git clone https://github.com/your-repo/mcp-server.git
cd mcp-server
# Install dependencies
pip install -r requirements.txt
Usage
1. Initialize MCP Server
from mcp_server import ModelContextProvider
mcp = ModelContextProvider()
2. Add Context
mcp.add_context(
"company_info",
{
"name": "TechCorp",
"founded": 2010,
"industry": "Artificial Intelligence",
"products": ["AI Assistant", "Smart Analytics", "Prediction Engine"],
"mission": "To make AI accessible to everyone"
}
)
3. Query Context
query = "What are the features of the AI Assistant product?"
relevant_context = mcp.query_context(query)
print(relevant_context)
4. Provide Context to AI Model
model_context = mcp.provide_model_context(query)
print(model_context)
API Methods
| Method | Description |
|---|---|
add_context(context_id, content, metadata) | Adds or updates a context. |
get_context(context_id) | Retrieves context by ID. |
query_context(query, relevance_threshold) | Finds relevant contexts based on a query. |
provide_model_context(query, max_contexts) | Returns structured model-ready context. |
Contributing
We welcome contributions! If you want to improve MCP Server, feel free to fork the repo and submit a pull request.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.