massive-context-mcp
A community MCP server that enables agents to handle contexts exceeding 10 million tokens by using chunking, sub-queries, and local inference via Ollama. It allows loading context as external variables, inspecting structure, filtering with regex, and executing Python code against loaded context for final synthesis.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 1 GitHub star
What you can do with it
- Handle massive contexts (10M+ tokens) with chunking
- Sub-query recursively on chunks
- Free local inference via Ollama
- Execute Python code against loaded context
Source and maintenance
- Last repository push
- Latest release
- v3.0.1
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
massive-context-mcp 3.0.1
{
"version": "3.0.1",
"transport": "stdio",
"identifier": "massive-context-mcp",
"registryType": "pypi",
"environmentVariables": [
{
"name": "RLM_DATA_DIR",
"format": "string",
"description": "Directory for storing context data"
},
{
"name": "OLLAMA_URL",
"format": "string",
"description": "URL for Ollama server (default: http://localhost:11434)"
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"massive-context-mcp-mcp": {
"command": "uvx",
"args": [
"massive-context-mcp==3.0.1"
],
"env": {
"RLM_DATA_DIR": "<YOUR_RLM_DATA_DIR>",
"OLLAMA_URL": "<YOUR_OLLAMA_URL>"
}
}
}
}Cline
{
"mcpServers": {
"massive-context-mcp-mcp": {
"command": "uvx",
"args": [
"massive-context-mcp==3.0.1"
],
"env": {
"RLM_DATA_DIR": "<YOUR_RLM_DATA_DIR>",
"OLLAMA_URL": "<YOUR_OLLAMA_URL>"
}
}
}
}VS Code
{
"servers": {
"massive-context-mcp-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"massive-context-mcp==3.0.1"
],
"env": {
"RLM_DATA_DIR": "<YOUR_RLM_DATA_DIR>",
"OLLAMA_URL": "<YOUR_OLLAMA_URL>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"massive-context-mcp-mcp": {
"command": "uvx",
"args": [
"massive-context-mcp==3.0.1"
],
"env": {
"RLM_DATA_DIR": "<YOUR_RLM_DATA_DIR>",
"OLLAMA_URL": "<YOUR_OLLAMA_URL>"
}
}
}
}Let your agent find its tools
Find servers like massive-context-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.