Loading…
Universal MCP Server with advanced AI memory capabilities and semantic search.
io.github.Lyellr88/marm-mcp-server is an MCP server entry in ChatHome Skills, sourced from Official MCP Registry and scored 76/100. As a Model Context Protocol server, it exposes tools that MCP-compatible LLM clients such as Claude, Cursor, and Copilot can call directly, extending an agent's reach beyond its built-in capabilities. ChatHome Skills discovered this entry through its daily ingest of official registries and GitHub discovery queries, and re-verifies repository facts, freshness signals, and install metadata on every run. The quality score weighs official-registry presence, a working install command, license clarity, GitHub star trajectory, and repository freshness — the full formula is on the Sources page. The install command above is ready to copy. Review the last-pushed date and repository status before adding io.github.Lyellr88/marm-mcp-server to a production agent workflow; the snapshot facts below are point-in-time values from the most recent ingest.
uvx marm-mcp-server==2.60.1Review the upstream source before running this command.
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-12T07:51:08.150651Z",
"publishedAt": "2026-10-12T07:51:08.150651Z",
"statusChangedAt": "2026-10-12T07:51:08.150651Z"
}
},
"server": {
"name": "io.github.Lyellr88/marm-mcp-server",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "2.60.1",
"packages": [
{
"version": "2.60.1",
"transport": {
"type": "stdio"
},
"identifier": "marm-mcp-server",
"runtimeHint": "uvx",
"registryType": "pypi",
"packageArguments": [
{
"type": "positional",
"value": "stdio"
}
]
},
{
"transport": {
"type": "stdio"
},
"identifier": "lyellr88/marm-mcp-server:2.60.1",
"runtimeHint": "docker",
"registryType": "oci",
"runtimeArguments": [
{
"name": "-i",
"type": "named",
"description": "Keep stdin open for the STDIO session"
},
{
"name": "--rm",
"type": "named",
"description": "Remove the container when the session ends; memory stays in the volume"
},
{
"name": "--mount",
"type": "named",
"value": "type=volume,src=marm-data,dst=/home/marm/.marm",
"description": "Keep memory in a named volume across the short-lived STDIO containers"
},
{
"name": "-e",
"type": "named",
"value": "HOME=/home/marm",
"description": "Home directory of the image's user"
},
{
"name": "-e",
"type": "named",
"value": "XDG_CACHE_HOME=/home/marm/.marm/cache",
"description": "Keep model and download caches in the data volume"
},
{
"name": "-e",
"type": "named",
"value": "CBM_CACHE_DIR=/home/marm/.marm/cache/codebase-memory-mcp",
"description": "Keep code indexes in the data volume"
},
{
"name": "--entrypoint",
"type": "named",
"value": "marm-mcp-stdio",
"description": "Start the STDIO server directly, so nothing written while the HTTP settings load reaches the protocol stream"
}
]
}
],
"repository": {
"url": "https://github.com/Lyellr88/marm-memory",
"source": "github"
},
"description": "Universal MCP Server with advanced AI memory capabilities and semantic search."
}
}