Last updated
March 16, 2026
MCP profile
Github Alex Feel Mcp Context Server
An MCP server that provides persistent multimodal context storage for LLM agents.
Developer ToolsPackagePythonOpen SourceExternal
Visibility
Public
ByRegistry
About This MCP 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.
Capabilities
STORAGE_BACKEND: Database backend - sqlite (default) or postgresqlLOG_LEVEL: Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) - defaults to ERRORDB_PATH: Database file location (SQLite only) - defaults to ~/.mcp/context_storage.dbMAX_IMAGE_SIZE_MB: Maximum size per image in MB - defaults to 10MAX_TOTAL_SIZE_MB: Maximum total request size in MB - defaults to 100ENABLE_FTS: Enable full-text search functionality (true/false) - defaults to falseFTS_LANGUAGE: Language for stemming and text search - defaults to english. PostgreSQL supports 29 languages with full stemming. SQLite uses english for Porter stemmer or any other value for unicode61 tokenizer (no stemming).ENABLE_HYBRID_SEARCH: Enable hybrid search combining FTS and semantic search with RRF fusion (true/false) - defaults to falseHYBRID_RRF_K: RRF smoothing constant (1-1000) - defaults to 60. Higher values give more uniform treatment across ranks.ENABLE_CHUNKING: Enable text chunking for embeddings (true/false) - defaults to trueCHUNK_SIZE: Target chunk size in characters - defaults to 1500CHUNK_OVERLAP: Overlap between chunks in characters - defaults to 150
Why Use Github Alex Feel Mcp Context Server?
- Multimodal Context Storage: Store and retrieve both text and images
- Thread-Based Scoping: Agents working on the same task share context through thread IDs
- Flexible Metadata Filtering: Store custom structured data with any JSON-serializable fields and filter using 16 powerful operators
- Date Range Filtering: Filter context entries by creation timestamp using ISO 8601 format
- Tag-Based Organization: Efficient context retrieval with normalized, indexed tags
- Full-Text Search: Optional linguistic search with stemming, ranking, boolean queries (FTS5/tsvector), and cross-encoder reranking
- Semantic Search: Optional vector similarity search for meaning-based retrieval with cross-encoder reranking
- Hybrid Search: Optional combined FTS + semantic search using Reciprocal Rank Fusion (RRF) with cross-encoder reranking
- Cross-Encoder Reranking: Automatic result refinement using FlashRank cross-encoder models for improved search precision (enabled by default)
- Multiple Database Backends: Choose between SQLite (default, zero-config) or PostgreSQL (high-concurrency, production-grade)
- High Performance: WAL mode (SQLite) / MVCC (PostgreSQL), strategic indexing, and async operations
- MCP Standard Compliance: Works with Claude Code, LangGraph, and any MCP-compatible client
Specifications
Status
live
Industry
Developer Tools
Category
General
Server type
Package
Language
Python
License
Open Source
Verified
Yes
Requirements
- uv package manager (install instructions)
- An MCP-compatible client (Claude Code, LangGraph, or any MCP client)
- Ollama (for embedding generation - default behavior):
- Install from ollama.com/download
- Pull embedding model: ollama pull qwen3-embedding:0.6b
Hosting
Hosting Options
- Package
API
Integrate this server into your application. Choose a connection method below.
1
Configure
Configuration
json
{
"mcpServers": {
"context-server": {
"type": "stdio",
"command": "uvx",
"args": ["--python", "3.12", "--with", "mcp-context-server[embeddings-ollama,reranking]", "mcp-context-server"],
"env": {}
}
}
}Performance
Usage
Quick Reference
- Name
- Github Alex Feel Mcp Context Server
- Function
- An MCP server that provides persistent multimodal context storage for LLM agents.
- Transport
- Package
- Language
- Python
- Source
- External (Registry)
- License
- Open Source
Get started
Ready to integrate this MCP server?
Book a demo to see how this server fits your workflow, or explore the full catalog.