What tool does Cursor Memory MCP provide?
It provides one tool: `create_cursor_memory`, which creates `.mdc` memory files with task summary, name, description, and project path.
@zjmwqx
Basic information
The Cursor Memory MCP Server provides a powerful tool to assist in coding with cursor, enpower cursor to operate with memory, make coding taste much more dilicious
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"cursor-memory-mcp": {
"command": "uv",
"args": [
"tool",
"install",
"cursor-memory-mcp"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
The Cursor Memory MCP Server is a bridge between AI assistants and Cursor's project memory system through the Model Context Protocol (MCP). It enables AI models to automatically create and manage .mdc memory files in the .cursor/rules/ directory, helping developers preserve task execution context for future reference.
Install the tool globally with uv tool install cursor-memory-mcp, then configure it in Cursor's MCP settings by adding a JSON entry with the command uv tool run cursor-memory-mcp. Add a user rule in Cursor settings instructing the agent to use cursor memory after task completion, then invoke the agent. The server exposes a create_cursor_memory tool with parameters task_summary, task_name, task_description, and project_path.
.cursor/rules/.mdc files per Cursor specificationsIt provides one tool: `create_cursor_memory`, which creates `.mdc` memory files with task summary, name, description, and project path.
`task_summary` (string), `task_name` (string), and `project_path` (string) are required. `task_description` is optional.
Files are stored in the `.cursor/rules/` directory of the specified project, with automatic timestamping if a duplicate name exists.
`task_name` must contain only letters, numbers, underscores, and hyphens. `task_summary` cannot be empty or whitespace only.
The server requires Python 3.11 or later and is installed via `uv` as a tool. It is cross-platform (Windows, macOS, Linux).

Model Context Protocol Servers

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

Exact, shared memory for AI agents: a hierarchical database where totals always add up, every write is attributed to the agent and person behind it, and any figure traces back to its source file. Agents create databases,

Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
Comments