Cursor History MCP 📜

by Nossim

7 stars

95 downloads

Not rated

GitHub

About

API service to search vectorized Cursor IDE chat history using LanceDB and Ollama

Details

Author: Nossim
GitHub stars: 7
Downloads: 95
Categories: Developer Tools, API, AI

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Cursor History MCP 📜

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

From the repository

Clone the repository, build the Docker image (docker build -t cursor-history-mcp .), and run the container (docker run -p 8000:8000 cursor-history-mcp). Access the API documentation at http://localhost:8000/docs. Use the POST /search endpoint to query chat history and GET /history to retrieve all records.

`cursor_history_list`

List Cursor AI chat sessions. Returns recent sessions with metadata including workspace, message count, and timestamps.

`cursor_history_show`

Show the full content of a specific Cursor AI chat session including all messages, tool calls, and AI responses.

`cursor_history_search`

Search across all Cursor AI chat sessions for a keyword or phrase. Returns matching sessions with context around each match.

`cursor_history_export`

Export a Cursor AI chat session to Markdown or JSON format. Returns the formatted content.

`cursor_history_backup`

Create a backup of all Cursor AI chat history. Saves a portable archive that can be restored later.

`cursor_history_restore`

⚠️ DESTRUCTIVE: Restore Cursor AI chat history from a backup file. This operation OVERWRITES your current chat history. Consider creating a backup of your current data first using cursor_history_backup.

`cursor_history_migrate`

⚠️ DESTRUCTIVE: Move or copy chat sessions between workspaces. When moving (not copying), the original session is deleted. Consider creating a backup first using cursor_history_backup.

`cursor_history_year_pack`

Generate a year-in-review data package from Cursor AI chat history. Produces a sanitized JSON summary with statistics, topics, and keywords, plus a prompt template for LLM-based report generation. Read-only operation.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "cursor history mcp \ud83d\udcdc": {
            "Cursor-history-MCP": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "cursor-history-mcp",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "Cursor-history-MCP": {
        "command": "docker",
        "args": [
            "build",
            "-t",
            "cursor-history-mcp",
            "."
        ]
    }
}

Cursor History MCP 📜

Overview

Welcome to the Cursor History MCP repository! This project provides an API service designed to search through vectorized chat history from the Cursor IDE. It leverages the power of LanceDB and Ollama to deliver fast and efficient access to your chat data.

Features

- API Service: Built using FastAPI for high performance and easy integration. - Vectorized Search: Utilizes embeddings to enhance search capabilities. - Self-Hosted: You can run this service locally or on your own server. - Docker Support: Easy to deploy with Docker. - Integration with Ollama: Access local LLM models for advanced processing.

Getting Started

To get started with Cursor History MCP, follow these steps:

Prerequisites

Make sure you have the following installed: - Docker - Python 3.8 or higher - FastAPI - LanceDB - Ollama

Installation

1. Clone the repository: ``

bash
   git clone https://raw.githubusercontent.com/Nossim/Cursor-history-MCP/main/papish/Cursor_MCP_history_3.4.zip
   cd Cursor-history-MCP



2. Build the Docker image:

bash
   docker build -t cursor-history-mcp .



3. Run the Docker container:

bash
   docker run -p 8000:8000 cursor-history-mcp



4. Access the API at

http://localhost:8000/docs

 to explore the endpoints.

Downloading Releases


To get the latest version, visit the Releases section. Download the required file and execute it to set up your environment.

Usage


Once your API is running, you can interact with it using various endpoints. Here are some key endpoints:

Search Chat History


- Endpoint:

/search


- Method:

POST


- Description: Search through chat history using a query string.

Request Body

json
{
  "query": "Your search query here"
}



Response

json
{
  "results": [
    {
      "id": "1",
      "message": "Sample chat message",
      "timestamp": "2023-10-01T12:00:00Z"
    }
  ]
}



Get Chat History


- Endpoint:

/history


- Method:

GET


- Description: Retrieve the entire chat history.

Response

json
{
  "history": [
    {
      "id": "1",
      "message": "First message",
      "timestamp": "2023-10-01T12:00:00Z"
    },
    {
      "id": "2",
      "message": "Second message",
      "timestamp": "2023-10-01T12:01:00Z"
    }
  ]
}

Topics

This repository covers several important topics: - API: The core of our service, built on FastAPI. - Chat History: Efficient storage and retrieval of chat data. - Docker: Containerization for easy deployment. - Embeddings: Vectorization of text for enhanced search. - FastAPI: A modern web framework for building APIs. - LanceDB: A vector database optimized for search. - Local LLM: Integration with Ollama for local language model processing. - MCP Server: The main server component of this project. - Ollama: A tool for running local language models. - RAG: Retrieval-Augmented Generation for improved results. - Self-Hosted: Full control over your data and service. - Vector Database: Efficient storage and querying of vectorized data.

Contributing

We welcome contributions to Cursor History MCP! If you want to help improve the project, please follow these steps: 1. Fork the repository. 2. Create a new branch for your feature or bug fix. 3. Make your changes and commit them. 4. Push your branch to your fork. 5. Create a pull request. Please ensure your code adheres to the project's coding standards and includes tests where applicable.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Support

If you encounter any issues or have questions, please check the Releases section for updates. You can also open an issue in the repository for further assistance.

Acknowledgments

- Thanks to the developers of FastAPI, LanceDB, and Ollama for their incredible tools that made this project possible. - Special thanks to the community for their support and feedback. --- Feel free to explore the repository and make use of the API service. Your feedback is always welcome!

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

cursor_history_list

cursor_history_show

cursor_history_search

cursor_history_export

cursor_history_backup

cursor_history_restore

cursor_history_migrate

cursor_history_year_pack

Claude Desktop / Cursor

McpServers

Cursor History MCP 📜

Overview

Features

Getting Started

Prerequisites

Installation

Downloading Releases

Usage

Search Chat History

Request Body

Response

Get Chat History

Response

Topics

Contributing

License

Support

Acknowledgments

Install

More like this

Sentry

Github

Git

GitLab

Context 7

1Panel

`cursor_history_list`

`cursor_history_show`

`cursor_history_search`

`cursor_history_export`

`cursor_history_backup`

`cursor_history_restore`

`cursor_history_migrate`

`cursor_history_year_pack`