massive context mcp for VS Code
io.github.egoughnour/massive-context-mcp
Handles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.
client:VS Code
transport:stdio
runtime:pypi
Install massive context mcp in VS Code
.vscode/mcp.json
{
"inputs": [
{
"type": "promptString",
"id": "rlm-data-dir",
"description": "RLM_DATA_DIR",
"password": true
},
{
"type": "promptString",
"id": "ollama-url",
"description": "OLLAMA_URL",
"password": true
}
],
"servers": {
"massive-context-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"massive-context-mcp"
],
"env": {
"RLM_DATA_DIR": "${input:rlm-data-dir}",
"OLLAMA_URL": "${input:ollama-url}"
}
}
}
}
VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs