Rememberizer

Provides access to Rememberizer documents and Slack discussions, with search and management actions via MCP.

javascript

0

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-skydeckai_mcp-server-rememberizer": {
      "command": "uvx",
      "args": [
        "mcp-server-rememberizer"
      ],
      "env": {
        "REMEMBERIZER_API_TOKEN": "YOUR_REMEMBERIZER_API_TOKEN"
      }
    }
  }
}

You can run the Rememberizer MCP Server to search, retrieve, and manage documents and Slack discussions through Rememberizer, enabling your LLMs to access and organize knowledge across sources with MCP-style tooling.

How to use

Connect to the Rememberizer MCP Server from your MCP client and use the provided tools to search documents by semantic similarity, list available integrations, and fetch account information. You can query for semantically related knowledge chunks, retrieve document lists, and view or filter sources and documents by date. For local development, run the server and feed it your Rememberizer API token to enable authenticated access.

How to install

Prerequisites: Node.js and npm should be installed on your system. You will also need uvx to run the MCP server locally.

npx -y @smithery/cli install mcp-server-rememberizer --client claude

Additional setup and usage notes

If you prefer to run the server directly with uv, you can do so without a separate installation step. Use uvx to run the MCP server directly.

Set the Rememberizer API token in your environment to authorize access to Rememberizer data.

Configuration and environment variables

The server requires your Rememberizer API token to authenticate requests.

Environment variable to set before running the server:

Usage with Claude Desktop

"mcpServers": {
  "rememberizer": {
      "command": "uvx",
      "args": ["mcp-server-rememberizer"],
      "env": {
        "REMEMBERIZER_API_TOKEN": "your_rememberizer_api_token"
      }
    },
}

Debugging

To debug MCP servers that run over stdio, you can use the MCP Inspector for a clearer debugging workflow.

npx @modelcontextprotocol/inspector uv --directory /path/to/directory/mcp-servers-rememberizer/src/mcp_server_rememberizer run mcp-server-rememberizer

Available tools

rememberizer_search

Search for documents by semantic similarity. Input: q (string), n (optional int), from (ISO date), to (ISO date). Returns: text results.

rememberizer_agentic_search

Search for documents with LLM Agents augmentation. Input: query (string), n_chunks (int), user_context (string), from (ISO date), to (ISO date). Returns: text results.

rememberizer_list_integrations

List available data source integrations.

rememberizer_account_information

Get account information for the Rememberizer connection.

rememberizer_list_documents

Retrieve a paginated list of documents with page and page_size controls.