mcpbeat Sign in

Hot Memory MCP Server

by michael-denyer Your server? Claim it
local only

Hot Memory MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 265 installs a week from pypi. Last commit 13 Sep 2026.

Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.

Installs per day peak 95 · avg 33 · -10% w/w
a month agotoday
265
Installs / week
pypi · hot-memory-mcp
9
Stars
0 open issues
13 Sep 2026
Last commit
0 releases in 90 days
MIT
License
Python

What the code does

We read the source, 54 min ago · rules 3dff92dd89df

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

File ships in the package but is absent from the source [пакет] hooks/memory-log-response.sh:1, [пакет] src/memory_mcp/mining.py:1, [пакет] src/memory_mcp/probe.py:1 и ещё 10
этот файл ставится пользователю, но в репозитории его нет
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Builds a database query by concatenation .github/workflows/publish.yml:96
      - name: Update formula and push
        env:
          TAP_TOKEN: ${{ secrets.HOMEBREW_TAP_TOKEN }}

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add hot-memory-mcp -- uvx hot-memory-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "hot-memory-mcp": {
      "args": [
        "hot-memory-mcp"
      ],
      "command": "uvx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.hot-memory-mcp]
command = "uvx"
args = ["hot-memory-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "hot-memory-mcp": {
      "args": [
        "hot-memory-mcp"
      ],
      "command": "uvx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "hot-memory-mcp": {
      "args": [
        "hot-memory-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: MEMORY_MCP_DB_PATH (Path to SQLite database file), MEMORY_MCP_EMBEDDING_MODEL (Embedding model to use (default: all-MiniLM-L6-v2)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Hot Memory MCP

same job, measured the same way
Marm MCP Server
by lyellr88

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

1 796 installs/wk local only
Verbative Memory
by verbative

On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.

366 installs/wk local only
StudioMeyer Memory
by studiomeyer

Bi-temporal AI memory. 56 tools, knowledge graph, semantic search. EU-hosted, free tier.

answering
MCP External Memory
by daedalus

An MCP server that gives LLMs persistent, searchable semantic memory

80 installs/wk local only
Agent Knowledge
by keshrath

Cross-session memory for AI agents - knowledge graph, scoring, semantic search

119 installs/wk local only
Iranti
by nfemmanuel

Persistent, shared memory for AI agents — facts, checkpoints, semantic search.

260 installs/wk local only
webfetch
by firish

Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching

94 installs/wk local only
Claude Memory Manager
by nyxtoolsdev

Cross-session memory for Claude Code — context capture, semantic search, recall

80 installs/wk local only

Hot Memory MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Hot Memory MCP?
Hot Memory MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package hot-memory-mcp was installed 265 times last week.
How do I connect Hot Memory MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls hot-memory-mcp straight from pypi; nothing to host, nothing to sign up for.
How many people use Hot Memory MCP?
The pypi package hot-memory-mcp was installed 265 times in the last week. Week over week that is -10%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Hot Memory MCP open source?
Yes — it is published under the MIT licence, written in Python and 9 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.