This MCP server provides Retrieval-Augmented Generation (RAG) capabilities using Contextual AI, acting as a bridge between AI interfaces and a specialized Contextual AI agent.
From the registry: RAG-enabled MCP server using Contextual AI. Supports single-agent and multi-agent modes.
$ git clone https://github.com/ContextualAI/contextual-mcp-server.githttps://github.com/ContextualAI/contextual-mcp-server$ pip install -e .Please install the `contextual-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.10+** — Python 3.10 or higher required.
- **Clone repo** — Clone the contextual-mcp-server repo. Run: `git clone https://github.com/ContextualAI/contextual-mcp-server.git` (https://github.com/ContextualAI/contextual-mcp-server)
- **Install dependencies** — Create a venv and install the package (uses uv for dep management). Run: `pip install -e .`
- **Contextual AI API key and Agent ID** — Obtain API key and Agent ID from Contextual AI platform. (https://docs.contextual.ai/user-guides/mcp-server)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--directory","${workspaceFolder}","run","multi-agent/server.py"]
- required environment variables:
- `API_KEY`: Contextual AI API key. (example: `<your-api-key>`)
- `AGENT_ID`: Contextual AI RAG agent ID. (example: `<your-agent-id>`)
Note: Only stdio transport supported. Also available as a hosted MCP at https://mcp.app.contextual.ai/mcp/ via the Contextual AI platform.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.API_KEYrequiredYour Contextual AI API keyAGENT_IDrequiredYour Contextual AI agent IDAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.