pickfit

BrowseMCP servers

RMS Memory MCP

Persistent local-first MCP memory server giving AI coding agents a shared Markdown vault with semantic search.

Use it

Before you install: known vulnerabilities

pickfit found 5 known high or critical vulnerabilities in the packages a fresh install brings (OSV.dev, 3 Nov 2026). Weigh this before you install it.

  • crates:pulldown-cmark 0.13.5 Quadratic parsing of nested image wikilinks with `ENABLE_WIKILINKS` (RUSTSEC-2026-0433, high, fixed in 0.13.6)
  • crates:quick-xml 0.26.0 Quadratic run time when checking a start tag for duplicate attribute names (RUSTSEC-2026-0194, high, fixed in 0.41.0)
See 3 more

Linux x86_64

  1. Download install script only

    curl -fsSL https://raw.githubusercontent.com/max-ramas/rms-memory-mcp/master/scripts/install.sh -o /tmp/rms-install.sh
  2. Run install script for rms-memory

    bash /tmp/rms-install.sh
Where the README and reality differ
  • README: rms-memory config then rms-memory init registers a project
    What worked: set global vault path with rms-memory config --vault-path <PATH> before rms-memory init, otherwise init asks to set it first

Check that it works

rms-memory --version

The output should contain “rms-memory 1.3.2”.

Add it to your agent

claude mcp add rms-memory-mcp -- rms-memory serve
JSON for Claude Desktop, Cursor and other clients
{
  "mcpServers": {
    "rms-memory-mcp": {
      "command": "rms-memory",
      "args": [
        "serve"
      ]
    }
  }
}

Run rms-memory config --vault-path <vault folder>, then rms-memory init in your project folder, and start the server for your MCP client with rms-memory serve.

What it does

  • Keep persistent local memory for AI agents
    How to use it
    1. Set the vault location with rms-memory config --vault-path <vault folder>.
    2. In your project folder, run rms-memory init, then check it with rms-memory projects list.
    3. Start the server with rms-memory serve and connect your MCP client. Call the rms_projects tool to list projects.
    Tested
  • Search memory with hybrid vector search
    How to use it
    1. Save a note with the rms_write tool, giving a project, a path such as <folder>/<note>.md, and the content.
    2. Call rms_sync for the project to update the index.
    3. Call rms_search with your query, the project name and a result limit.
    Tested
  • Index source code by meaning in many languages
    Not shown working

How far pickfit got

Linux x86_64

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

macOS and Windows: the project says it runs there; pickfit hasn’t tried it.

Good for

  • search Markdown project memory
  • persist architectural decisions and rules
  • read a memory document by path
  • run vault health diagnostics
  • export vault as llms.txt

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 30 Oct 2026
  • Version 1.3.2

An MCP client handshake over stdio listed 19 tools, and a call to rms_projects returned a result.

Differences the test machine hit

  • README: curl -fsSL .../scripts/install.sh | bash
    In the test: install.sh downloads a prebuilt binary tarball rms_memory_mcp_<version>_<target>.tar.gz which cannot be read as text before running
  • README: curl ... install.sh | bash installs binary
    In the test: install.sh automatically runs rms-memory install at the end (found no IDE configs here)

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.