io.github.Lyellr88/marm-mcp-server

Universal MCP Server with advanced AI memory capabilities and semantic search.

io.github.Lyellr88/marm-mcp-server · Repository · version 2.60.1 · 435 stars · listed from registry

Install

The sweep installs into a clean prefix, but this is the command a user would run:

uvx marm-mcp-server

Results by platform

Linux

installs and connects2026-11-09 · probed over pypi

4 recorded runs, oldest first.

tools/list returned 16 tools.

marm_smart_recall marm_log_entry marm_log_show marm_delete marm_notebook marm_summary marm_compaction marm_distill marm_graph_index marm_code_lookup marm_code_context marm_graph_trace marm_graph_architecture marm_graph_impact marm_concept_build marm_concept_recall

macOS

MCP handshake failed2026-11-09 · probed over pypi

4 recorded runs, oldest first.

handshake failed: MCP error -32000: Connection closed
--- stderr (tail) ---
error: No solution found when resolving tool dependencies
  cause: Because onnxruntime>=1.24.2 has no wheels with a matching Python ABI tag (e.g., `cp315`) and fastembed>=0.8.0 depends on onnxruntime>=1.24.2, we can conclude that fastembed>=0.8.0 cannot be used.
         And because marm-mcp-server>=2.60.1 depends on fastembed>=0.8.0 and you require marm-mcp-server==2.60.1, we can conclude that your requirements are unsatisfiable.

hint: You require CPython 3.15 (`cp315`), but we only found wheels for `onnxruntime` (v1.31.1) with the following Python ABI tags: `cp311`, `cp312`, `cp313`, `cp313t`, `cp314`, `cp314t`

Windows

installs and connects2026-11-09 · probed over pypi

4 recorded runs, oldest first.

tools/list returned 16 tools.

Badge

Paste this into the project README to show the current result:

[![does it install](https://img.shields.io/endpoint?url=https://doesitinstall.com/badge/io.github.lyellr88__marm-mcp-server.json)](https://doesitinstall.com/s/io.github.lyellr88__marm-mcp-server.html)