An MCP Server to enable global access to Rememberizer
A Model Context Protocol server for interacting with Rememberizer’s document and knowledge management API. This server enables Large Language Models to search, retrieve, and manage documents and integrations through Rememberizer.
Please note that mcp-server-rememberizer is currently in development and the functionality may be subject to change.
The server provides access to two types of resources: Documents or Slack discussions
rememberizer_search
q (string): Up to a 400-word sentence to find semantically similar chunks of knowledgen (integer, optional): Number of similar documents to return (default: 5)from (string, optional): Start date in ISO 8601 format with timezone (e.g., 2023-01-01T00:00:00Z). Use this to filter results from a specific date (default: None)to (string, optional): End date in ISO 8601 format with timezone (e.g., 2024-01-01T00:00:00Z). Use this to filter results until a specific date (default: None)rememberizer_agentic_search
query (string): Up to a 400-word sentence to find semantically similar chunks of knowledge. This query can be augmented by our LLM Agents for better results.n_chunks (integer, optional): Number of similar documents to return (default: 5)user_context (string, optional): The additional context for the query. You might need to summarize the conversation up to this point for better context-awared results (default: None)from (string, optional): Start date in ISO 8601 format with timezone (e.g., 2023-01-01T00:00:00Z). Use this to filter results from a specific date (default: None)to (string, optional): End date in ISO 8601 format with timezone (e.g., 2024-01-01T00:00:00Z). Use this to filter results until a specific date (default: None)rememberizer_list_integrations
rememberizer_account_information
rememberizer_list_documents
page (integer, optional): Page number for pagination, starts at 1 (default: 1)page_size (integer, optional): Number of documents per page, range 1-1000 (default: 100)To install Rememberizer Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp-server-rememberizer --client claude
When using uv, no specific installation is needed. Use uvx to directly run mcp-server-rememberizer.
The following environment variables are required:
REMEMBERIZER_API_TOKEN: Your Rememberizer API tokenYou can register an API key by create your own Common Knowledge in Rememberizer.
Add this to your claude_desktop_config.json:
"mcpServers": {
"rememberizer": {
"command": "uvx",
"args": ["mcp-server-rememberizer"],
"env": {
"REMEMBERIZER_API_TOKEN": "your_rememberizer_api_token"
}
},
}
Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.
You can launch the MCP Inspector via npm with this command:
npx @modelcontextprotocol/inspector uv --directory /path/to/directory/mcp-servers-rememberizer/src/mcp_server_rememberizer run mcp-server-rememberizer
Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
