pickfit

BrowseMCP servers

Mnemo MCP Server

Persistent AI memory with hybrid search stored locally in SQLite.

Tested on Linux

Use it

Linux x86_64

  1. install mnemo-mcp via uv tool install

    uv tool install mnemo-mcp --force
Where the README and reality differ
  • README: uvx --from mnemo-mcp mnemo-mcp launches the MCP server (implied stdio)
    What worked: server speaks Streamable HTTP only (no stdio); launch with mnemo-mcp and probe via http://127.0.0.1:8000/mcp

Check that it works

mnemo-mcp --version 2>&1

The output should contain “2.21.0”.

Add it to your agent

claude mcp add --transport http mnemo http://127.0.0.1:8000/mcp
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "mnemo": {
      "type": "http",
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}

This server speaks HTTP: start it first and keep it running (mnemo-mcp), then add the URL.

Run mnemo-mcp to start the server, then connect your MCP client to it.

What it does

  • Save memories that persist between sessions
    How to use it
    1. Start the server with mnemo-mcp.
    2. From your MCP client, call the add_memory tool with content, a category such as fact, and optional tags.
    Tested
  • Search memories by keywords and meaning
    How to use it
    1. Start the server with mnemo-mcp.
    2. From your MCP client, call the search_memory tool with a query and an optional limit.
    Tested
  • Save typed memories without duplicates
    Not shown working
  • Extract entities and track their relations
    Not shown working

How far pickfit got

Linux x86_64

  1. Installs
  2. Connects
  3. 2 of 4 features work
  4. Works offline

Good for

  • recall topic-relevant memories with context-type filtering
  • capture memories with typed context
  • audit memories for duplicates and contradictions
  • capture session decisions and open questions
  • query point-in-time memory snapshots

An alternative to Mem0, Letta and OpenMemory.

How pickfit tested it

Each run starts from a clean machine and follows the steps above. How pickfit verifies

Linux x86_64

An MCP client called one of its tools

  • Replayed from scratch
  • Works offline
  • Checked on 1 Nov 2026
  • Version 2.21.0

An MCP client handshake over HTTP listed 13 tools, and a call to add_memory returned a result.

How to read a tool card

Stitching
pickfit installed this tool itself. Everything under the stitches comes from that run. A tool pickfit has not run never gets stitches.
Verified on your OS
The install steps ran on the system you chose. “Ran on Linux only” means it has not been run on yours yet.
macOS, Linux and WindowsWhere it ran
Green OS marks: pickfit ran the install steps there. Grey ones: the README says it runs there, and pickfit has not tried.
How far the run got
Installs and starts, its main function works, its service answers, it produces model output. A window means a desktop app opened; a plug, an MCP client used it. The mark sits beside the run’s result, under “Why it fits and how we know” and in “How pickfit tested it”.
Visual check
pickfit looked at screenshots of the app. Green: it looks right. Amber with a number: things that look wrong; open it to see them. Grey and dashed: not checked yet.
Known vulnerabilities
Known high or critical vulnerabilities (OSV.dev) in what it installs. Green: none known. Red with a number: how many; open it for the list, and read it before you install. Grey and dashed: not checked, which does not mean safe.
About the run
The day it ran, and the version that ran.
Source of a reason
Every reason a pick fits rests on one profile field. Open the reason to see the field and the value it relies on.
Hidden gem
High quality, little known.
Quality and popularity
Two scores out of 100. Quality: how well it installed and worked when pickfit tried it, and how good its install docs and upkeep are. Popularity: from stars, downloads and Hacker News.
Features checked
Of the main features the README advertises, how many the run actually exercised (green), and how many failed (red). Grey ones were not checked, and the card says why.
Not verified
A well-known tool Fitz mentions from general knowledge. No run record, no steps, no score.