Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Cactus MCP Server ask why the API returns a 401 and cite the help pages"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cactus (heycactus.ai) learns a product from its codebase, answers its customers live, and keeps its help site and changelog current with every release. Its MCP server lets your team reach that knowledge from Claude, ChatGPT, Cursor, VS Code or any other MCP client.
This repository holds no server code. It lists Cactus's hosted MCP server: how to connect, the tools it offers, and the manifests MCP directories read.
Server: https://mcp.heycactus.ai/mcp
Transport: Streamable HTTP
Sign-in: OAuth 2.0 with your Cactus account (Google or GitHub). Dynamic client registration and client ID metadata documents are supported, with PKCE (S256).
Step-by-step setup for each AI client: https://heycactus.ai/docs/connect-an-ai-client
In Claude Code:
claude mcp add --transport http cactus https://mcp.heycactus.ai/mcpIn Cursor, add this to .cursor/mcp.json:
{
"mcpServers": {
"cactus": {
"url": "https://mcp.heycactus.ai/mcp"
}
}
}You need a Cactus team with a product built from a GitHub repository. Cactus is in open beta: anyone can start at https://app.heycactus.ai, with 14 days of Pro free and no card.
Related MCP server: ProductBrain
On https://mcp.heycactus.ai/mcp, signed in:
Tool | What it does |
| List your team's products |
| Search the product's published help pages |
| Read a help page |
| List help topics |
| Read the product's dated record of releases |
| Read the product map Cactus keeps from your code |
| Search past customer conversations |
| Read a conversation |
| Search past customer conversations and imported help articles |
| Search, and fetch a result |
| Ask Cactus a question. It answers from the published pages, the product map, the product knowledge and past conversations, and cites its sources |
| Investigate a question in the product's code and knowledge, and read the finding |
Every tool carries MCP annotations. No tool edits or deletes anything. Only ask and start_investigation aren't read-only, because each runs a new answer or investigation.
Every product's public help center has its own server, with no sign-in: https://mcp.heycactus.ai/p/<name>/mcp. Cactus's own help center is https://mcp.heycactus.ai/p/cactus/mcp. It offers search_help, read_page, list_topics, read_timeline, ask_help, contact_team, search and fetch.
ask_help answers the way the help center answers a visitor. It starts from the published help pages and reads the product map, the code index and the code when those fall short. contact_team sends the team a message they can reply to.
Website: https://heycactus.ai
Privacy: https://heycactus.ai/privacy
Terms: https://heycactus.ai/terms
Support: support@heycactus.ai
The files in this repository are under the MIT license.
This server cannot be deployed
Connect your team's living knowledge base — docs, data, issues, CRM — to Claude and ChatGPT.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
Make your knowledge agent-ready. One MCP endpoint, 5 connectors, 3 search modes.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
