Context DB MCP
Provides tools for storing and retrieving project context using OpenAI vector stores, enabling semantic search and context recall across sessions.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Context DB MCP (BETA Mode- can make mistakes)
A Model Context Protocol (MCP) server that stores and retrieves project context using OpenAI vector stores. Enable your AI editor to remember and recall project knowledge across sessions. For best results, add this in your agent rules file and force it to use it at the start and the very end of each chat session. Otherwise, in your prompt, ask the agent to use the ingestion or retrieval where necessary.
Features
ingest_document- Store project summaries, design docs, and context in a vector storeretrieve_relevant_chunks- Retrieve relevant context using semantic search
Related MCP server: MCP Memory Keeper
Installation
pip install -e .Requirements: Python 3.11+ and an OpenAI API key
Configuration
Create a .env file (or set environment variables):
# Required
OPENAI_API_KEY=sk-your-api-key-here
# Optional - Vector Store (use ID for existing, NAME to create/find)
CONTEXT_DB_VECTOR_STORE_ID=vs_xxxxx
# OR
CONTEXT_DB_VECTOR_STORE_NAME=context-db-mcp
# Optional - Tuning
CONTEXT_DB_DEFAULT_MAX_RESULTS=10
CONTEXT_DB_REQUEST_TIMEOUT_SECONDS=120.0
CONTEXT_DB_LOG_LEVEL=INFOUse env.example as a template.
Usage
Claude Code
Add to your project root inside .mcp.json (create with exact name and preceeding dot) and paste the following:
{
"mcpServers": {
"context-db": {
"command": "{PATH TO THE BIN FOLDER IN YOUR CLONED REPO for example: {YOUR PATH.....}/Context_DB_MCP/env/bin/context-db-mcp}",
"env": {
"OPENAI_API_KEY": "sk-your-api-key-here",
"CONTEXT_DB_VECTOR_STORE_NAME": "context-db-mcp"
}
}
}
}Restart Claude Code. Tools will be available as:
mcp__context-db__ingest_documentmcp__context-db__retrieve_relevant_chunks
Cursor
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"context-db": {
"command": "{PATH TO THE BIN FOLDER IN YOUR CLONED REPO for example: {YOUR PATH.....}/Context_DB_MCP/env/bin/context-db-mcp}",
"env": {
"OPENAI_API_KEY": "sk-your-api-key-here",
"CONTEXT_DB_VECTOR_STORE_NAME": "context-db-mcp"
}
}
}
}Restart Cursor and access the tools from the MCP integration panel.
Testing
Run the diagnostic script to verify your setup:
python test_mcp_connection.pyRun the test suite:
pip install -e ".[dev]"
pytest tests/ -vTool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Shared project memory that keeps teammates and AI agents aligned across sessions.
Project memory, documentation and controlled secret access for AI coding agents.
Shared project context for AI agents and teams: docs, tasks, and messages that stay current.
Project memory for every AI. Pick up where you left off in Claude, ChatGPT or Cursor, with a team.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceStores and searches AI-generated knowledge about software projects, enabling Cursor to access project structures, design patterns, best practices, and technical documentation.-
- AlicenseNot gradedqualityAmaintenanceProvides persistent context management for AI coding assistants, enabling users to save, search, checkpoint, and restore project context across sessions and parallel workflows.243 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding assistants to persistently save, search, and restore project context across sessions, including decisions, progress, file caches, checkpoints, and channel-based memory. It supports git-aware organization, batch operations, and shared memory across parallel sessions.243 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI coding assistants to maintain persistent context across sessions by saving, searching, organizing, checkpointing, and restoring conversations, decisions, file content, and progress.243 npmMIT