Install Massive Context MCP

Pick your client, copy the command, done.

claude mcp add massive-context-mcp -- uvx massive-context-mcp

Environment Variables

Set these before running Massive Context MCP.

VariableDescriptionRequired

RLM_DATA_DIRDirectory path for storing RLM data.No

OLLAMA_URLURL for the Ollama inference service.No

Once configured, Massive Context MCP gives your AI agent access to:

rlm_system_checkVerify system requirements including macOS, Apple Silicon, RAM, and Homebrew.

rlm_setup_ollamaInstall Ollama via Homebrew with managed service and auto-updates.

rlm_setup_ollama_directInstall Ollama via direct download for headless environments.

rlm_ollama_statusCheck Ollama availability to detect if free local inference is available.

rlm_auto_analyzePerform one-step analysis by auto-detecting type, chunking, and querying.

After setup, try these prompts with your AI agent:

→Analyze the provided massive dataset in ~/.rlm-data and summarize the key findings.

→Check if my system is ready for local inference using the rlm_system_check tool.

→Perform an auto-analysis on the document to extract the main themes.

→Verify if Ollama is currently running and available for local processing.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Alternative installation methods

git clone https://github.com/egoughnour/massive-context-mcp.git && cd massive-context-mcp && uv sync

Save the docs, env vars, and workflow around Massive Context MCP in Conare so Claude Code, Codex, and Cursor remember it next time.