mcp-context-server 0.1.0

MCP Context Server — a FastMCP-based server providing persistent multimodal context storage for LLM agents.

MCP Context Server

A high-performance Model Context Protocol (MCP) server providing persistent multimodal context storage for LLM agents. Built with FastMCP, this server enables seamless context sharing across multiple agents working on the same task through thread-based scoping.

Key Features

• Multimodal Context Storage: Store and retrieve both text and images (up to 10MB per image, 100MB total)
• Thread-Based Scoping: Agents working on the same task share context through thread IDs
• Tag-Based Organization: Efficient context retrieval with normalized, indexed tags
• High Performance: SQLite with WAL mode, strategic indexing, and async operations
• MCP Standard Compliance: Works with Claude Code, LangGraph, and any MCP-compatible client
• Production Ready: Comprehensive test coverage, type safety, and robust error handling

Prerequisites

• uv package manager (install instructions)
• An MCP-compatible client (Claude Code, LangGraph, or any MCP client)

Adding the Server to Claude Code

There are two ways to add the MCP Context Server to Claude Code:

Method 1: Using CLI Command

claude mcp add context-server -- uvx --from git+https://github.com/alex-feel/mcp-context-server mcp-context-server

For more details, see: https://docs.claude.com/en/docs/claude-code/mcp#option-1%3A-add-a-local-stdio-server

Method 2: Direct File Configuration

Add the following to your .mcp.json file in your project directory:

{
  "mcpServers": {
    "context-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/alex-feel/mcp-context-server",
        "mcp-context-server"
      ],
      "env": {}
    }
  }
}

For configuration file locations and details, see: https://docs.claude.com/en/docs/claude-code/settings#settings-files

Verifying Installation

# Start Claude Code
claude

# Check MCP tools are available
/mcp

Troubleshooting

Common Issues

Server Not Starting

• Verify uv installation: Ensure uv is installed and in PATH
• Network connectivity: Check access to GitHub for package installation
• Check configuration: Verify the server configuration is correct

Server Not Listed

• Check MCP tools with /mcp command in Claude Code
• Verify the configuration was saved correctly
• Restart Claude Code after configuration changes

Common Errors

• "Server not responding": Check if uvx can access GitHub
• "Command not found": Ensure uv is installed and in PATH
• Configuration issues: Check your .mcp.json file or re-run the CLI command

Environment Configuration

Environment Variables

You can configure the server using environment variables in your MCP configuration. The server supports environment variable expansion using ${VAR} or ${VAR:-default} syntax.

Example configuration with environment variables:

{
  "mcpServers": {
    "context-server": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/alex-feel/mcp-context-server",
        "mcp-context-server"
      ],
      "env": {
        "LOG_LEVEL": "${LOG_LEVEL:-INFO}",
        "MCP_CONTEXT_DB": "${MCP_CONTEXT_DB:-~/.mcp/context_storage.db}",
        "MAX_IMAGE_SIZE_MB": "${MAX_IMAGE_SIZE_MB:-10}",
        "MAX_TOTAL_SIZE_MB": "${MAX_TOTAL_SIZE_MB:-100}"
      }
    }
  }
}

For more details on environment variable expansion, see: https://docs.claude.com/en/docs/claude-code/mcp#environment-variable-expansion-in-mcp-json

Supported Environment Variables

• LOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) - defaults to INFO
• MCP_CONTEXT_DB: Database file location - defaults to ~/.mcp/context_storage.db
• MAX_IMAGE_SIZE_MB: Maximum size per image in MB - defaults to 10
• MAX_TOTAL_SIZE_MB: Maximum total request size in MB - defaults to 100

Advanced Configuration

Additional environment variables are available for advanced server tuning, including:

• Connection pool configuration
• Retry behavior settings
• SQLite performance optimization
• Circuit breaker thresholds
• Operation timeouts

For a complete list of all configuration options, see app/settings.py.

API Reference

Tools

store_context

Store a context entry with optional images.

Parameters:

• thread_id (str, required): Unique identifier for the conversation/task thread
• source (str, required): Either 'user' or 'agent'
• text (str, required): Text content to store
• images (list, optional): Base64 encoded images with mime_type
• metadata (dict, optional): Additional structured data
• tags (list, optional): Tags for organization (automatically normalized)

Returns: Dictionary with success status and context_id

search_context

Search context entries with efficient filtering.

Parameters:

• thread_id (str, optional): Filter by thread
• source (str, optional): Filter by source ('user' or 'agent')
• tags (list, optional): Filter by tags (OR logic)
• content_type (str, optional): Filter by type ('text' or 'multimodal')
• limit (int, optional): Maximum results (default: 50, max: 500)
• offset (int, optional): Pagination offset
• include_images (bool, optional): Include image data in response

Returns: List of matching context entries

get_context_by_ids

Fetch specific context entries by their IDs.

Parameters:

• context_ids (list, required): List of context entry IDs
• include_images (bool, optional): Include image data (default: True)

Returns: List of context entries with full content

delete_context

Delete context entries by IDs or thread.

Parameters:

• context_ids (list, optional): Specific IDs to delete
• thread_id (str, optional): Delete all entries in a thread

Returns: Dictionary with deletion count

list_threads

List all active threads with statistics.

Returns: Dictionary containing:

• List of threads with entry counts
• Source type distribution
• Multimodal content counts
• Timestamp ranges

get_statistics

Get database statistics and usage metrics.

Returns: Dictionary with:

• Total entries count
• Breakdown by source and content type
• Total images count
• Unique tags count
• Database size in MB