hot-memory-mcp — Claude Code MCP server: memory, install
Keeps project knowledge across sessions and places frequently used facts into context. Useful when an agent repeatedly asks for the same architecture details.
claude mcp add --env MEMORY_MCP_DB_PATH=<MEMORY_MCP_DB_PATH> --env MEMORY_MCP_EMBEDDING_MODEL=<MEMORY_MCP_EMBEDDING_MODEL> --transport stdio hot-memory-mcp -- uvx hot-memory-mcpWhat hot-memory-mcp does
hot-memory-mcp stores project knowledge in two layers. A hot cache reaches the conversation through SessionStart and UserPromptSubmit hooks, while less-used entries are found with semantic search. Repeatedly recalled facts are promoted automatically, and older ones lose priority.
The server keeps memories separate for each git repository and connects related concepts in a knowledge graph. After setup, run memory-mcp-cli bootstrap once to seed the database from project documents; the hooks do not create the initial set by themselves. Embeddings use sentence-transformers, with the model fetched on first launch.
Python 3.10+ and the embedding model are required for startup. The plugin adds /memory-mcp:remember, /memory-mcp:recall, /memory-mcp:hot-cache, /memory-mcp:stats, and /memory-mcp:bootstrap; the dashboard can inspect stored memories and injection history.
What it helps with
- keep architecture decisions across sessions
- search project facts by meaning
- inject frequent knowledge without a lookup call
- separate memories between git repositories
- inspect stored data in the dashboard
Example prompts for the agent
- Save the API structure decision and associate it with this repository.
- Search memory for the authentication rules that apply to this project.
- Run
/memory-mcp:bootstrapand seed memory from the project documentation.
How to install hot-memory-mcp
Platform CLI
claude mcp add --env MEMORY_MCP_DB_PATH=<MEMORY_MCP_DB_PATH> --env MEMORY_MCP_EMBEDDING_MODEL=<MEMORY_MCP_EMBEDDING_MODEL> --transport stdio hot-memory-mcp -- uvx hot-memory-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from hot-memory-mcp <command>
Platform CLI
codex mcp add hot-memory-mcp --env MEMORY_MCP_DB_PATH=<MEMORY_MCP_DB_PATH> --env MEMORY_MCP_EMBEDDING_MODEL=<MEMORY_MCP_EMBEDDING_MODEL> -- uvx hot-memory-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from hot-memory-mcp <command>
Config file
{
"mcpServers": {
"hot-memory-mcp": {
"command": "uvx",
"args": [
"hot-memory-mcp"
],
"env": {
"MEMORY_MCP_DB_PATH": "<MEMORY_MCP_DB_PATH>",
"MEMORY_MCP_EMBEDDING_MODEL": "<MEMORY_MCP_EMBEDDING_MODEL>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from hot-memory-mcp <command>
Config file
{
"servers": {
"hot-memory-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"hot-memory-mcp"
],
"env": {
"MEMORY_MCP_DB_PATH": "<MEMORY_MCP_DB_PATH>",
"MEMORY_MCP_EMBEDDING_MODEL": "<MEMORY_MCP_EMBEDDING_MODEL>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from hot-memory-mcp <command>
Platform CLI
gemini mcp add -e MEMORY_MCP_DB_PATH=<MEMORY_MCP_DB_PATH> -e MEMORY_MCP_EMBEDDING_MODEL=<MEMORY_MCP_EMBEDDING_MODEL> hot-memory-mcp uvx hot-memory-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from hot-memory-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about hot-memory-mcp
How do I install hot-memory-mcp in Claude Code?
Run claude mcp add hot-memory-mcp -- uvx hot-memory-mcp, then restart Claude Code.
What does hot-memory-mcp do?
It stores project knowledge, injects frequently used entries through hooks, and retrieves other memories by meaning. Related memories can be connected in a knowledge graph.
What must I do after installing hot-memory-mcp?
Run memory-mcp-cli bootstrap once to seed memories from project documents. The embedding model downloads during the first run.
