{
"mcpServers": {
"intuition-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
The Intuition MCP Server is an HTTP stream server designed to interact with the Intuition knowledge graph, enabling users to query and manage data through a set of powerful tools. It provides a robust API for extracting triples, searching for entities (atoms), retrieving account information, and exploring relationships such as followers and following. This README outlines the steps to get started, the available tools, their functionalities, and instructions for running a client using the Model C
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
MIT. View license →
Is it maintained?
Last commit 8 days ago. 10 stars.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Intuition Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
The Intuition MCP Server is an HTTP stream server designed to interact with the Intuition knowledge graph, enabling users to query and manage data through a set of powerful tools. It provides a robust API for extracting triples, searching for entities (atoms), retrieving account information, and exploring relationships such as followers and following. This README outlines the steps to get started, the available tools, their functionalities, and instructions for running a client using the Model Context Protocol (MCP) SDK.
This repository represents the evolution of our Intuition MCP Server, which we are pleased to be open sourcing for our ecosystem. This is built upon the foundation and testing we've done. There are several contributors who helped get to this point, including francoispqt, jonathanprozzi, and simonas-notcat.
To run the Intuition MCP Server locally, follow these steps:
Clone the Repository: Clone the project repository to your local machine:
git clone <repository-url>
cd intuition-mcp-server
Install Dependencies: Install the required dependencies using pnpm:
pnpm install
Start the Server: Launch the server using the HTTP transport (recommended):
pnpm run start:http
This will start the Intuition MCP Server, making it available at the configured host and port (e.g., http://localhost:3001). Check the server configuration for the exact URL.
Verify the Server:
Once the server is running, you can test it by sending a request to the /mcp endpoint (for Streamable HTTP clients) or /sse endpoint (for legacy SSE clients). See the Running a Client (#running-a-client) section for details on connecting a client. We follow the most recent recommendations from the MCP SDK and recommend using the Streamable HTTP endpoint (/mcp) over SSE as it is in the process of being deprecated.
Note: Ensure you have pnpm installed globally (npm install -g pnpm) before running the above commands. If you encounter issues, verify that your Node.js version is 14 or higher.
The Intuition MCP Server is built to facilitate interactions with the Intuition knowledge graph, a decentralized data structure for storing and querying relationships between entities (atoms) such as accounts, concepts, and objects. The server operates as an HTTP stream server, leveraging the Model Context Protocol (MCP) to handle streaming requests and responses, making it ideal for real-time applications and large-scale data queries.
The server exposes a set of tools via API endpoints, each designed for specific tasks like extracting structured data (triples), searching for entities, retrieving account details, and exploring social connections (e.g., followers or recommendations). These tools are accessible using the MCP SDK, which supports both modern Streamable HTTP and legacy Server-Sent Events (SSE) transports for client-server communication. While we provide support for SSE, it is in the process of being deprecated in the MCP SD