Server data from the Official MCP Registry
Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens.
Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens.
Chronicle is a local chat management tool with reasonable security fundamentals but several concerns warrant attention. Path traversal protections are present but inconsistently applied, file operations lack comprehensive error handling, and there are minor input validation gaps. The server operates entirely locally without network exfiltration risks, but users should be aware of file system access scope and the need for careful configuration of external transcript directories. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue.
4 files analyzed · 12 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-leviathan0x0-chronicle-mcp": {
"args": [
"chronicle-mcp-server"
],
"command": "uvx"
}
}
}From the project's GitHub README.
Chronicle is a tool that links your AI assistants (like ChatGPT or Claude) to your local saved chats. It helps the AI find, search, compare, and copy your past conversations.
Chronicle is on the MCP Marketplace. You can install it with one click there to connect your AI directly.
Please give this repository a star if you used it so I can claim the special offers that are given to open-source contributers.
You need Python version 3.10 or higher on your computer.
Clone the folder from GitHub and go inside it:
git clone https://github.com/Leviathan0x0/Chronicle-MCP.git
cd Chronicle-MCP
Create a private Python setup folder and activate it:
python3 -m venv venv
source venv/bin/activate
Install the helper software packages:
pip install -r requirements.txt
You can save new chats automatically or load your old ones.
When you chat with an AI that has Chronicle connected, the AI will automatically save your chat in the background to your computer.
If you want to load chats from before you had Chronicle:
Go to settings inside ChatGPT or Claude. Click the export data button. You will get a zip file. Unzip this file on your computer.
If your downloaded data is one big file with all your chats inside (like ChatGPT's conversations.json file):
# Activate your python setup folder
source venv/bin/activate
# Run the separator tool to split the big file into separate files
python3 split_chats.py
# Or run it with a custom folder path where you want the chats to go
python3 split_chats.py /path/to/your/folder
If you have separate files for each chat:
Chronicle reads and translates different chat styles automatically:
Chronicle has 25 tools to help your AI manage chats:
list_all_stored_chats: List your saved files page by page.search_chats_by_keywords: Search chats using keywords.read_chat_message_range: Read a range of messages with options to show shortened code to save space.save_current_conversation_state: Save active chats.delete_stored_chat: Delete a saved chat file.get_chat_metadata: See file details like size and date.merge_conversation_into_archive: Add new messages to an old file.export_chat_as_markdown: Export a chat as a text document.search_chats_semantic: Search files using similar meanings.get_chat_summary: Get a short summary of a chat.find_related_chats: Find chats that talk about similar things.filter_chats_by_date_range: Find chats saved between two dates.register_session_for_auto_save: Mark a chat to save later.trigger_auto_save_on_session_end: Save marked chats now.watch_chats_folder: Watch your folders for new or changed files.import_chat_from_content: Import a chat from text.import_chat_from_local_path: Import a chat from a local file.sync_agent_transcripts: Sync saved chats from tools like Cursor, Continue, or Cline.sync_cursor_agent_transcripts: Sync saved chats from Cursor (older version).extract_action_items: Find tasks and to-do lists in your chats.build_knowledge_index: Group your files by topic.compare_two_chats: See what two chats have in common and what is unique.generate_project_brief_from_chats: Combine chats into a project summary document.configure_connector_settings: Change settings like file size limits.compress_old_chat_archives: Compress old files to save space.deduplicate_stored_chats: Find and delete duplicate files.get_server_capabilities: See the list of all tools.If you downloaded the code manually, run this command in your terminal. Note: You must change /absolute/path/to/ to the actual folder path where you saved the files on your computer.
claude mcp add-json chronicle '{"command": "python3", "args": ["/absolute/path/to/Chronicle-MCP/chat_server.py"]}'
If you installed the tool via the marketplace or npm, you do not need to use a folder path. Run this command instead:
claude mcp add-json chronicle '{"command": "npx", "args": ["-y", "chronicle-mcp"]}'
If you downloaded the code manually, go to Cursor settings, find the MCP section, and add a command tool:
python3 /absolute/path/to/Chronicle-MCP/chat_server.pyIf you installed the tool via the marketplace or npm, add this command instead:
npx -y chronicle-mcpYou can run the test tool to make sure everything works:
python3 test_all_tools.py
This project uses the MIT License. See the LICENSE file for details.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.