MCP server
Your company knowledge as a tool for your agents
Ragen exposes an MCP server. It is a gateway your agents query for company knowledge, and the answer comes back with citations, inside the permissions of the person they act on behalf of.
An agent with no access to company knowledge guesses
Agents are good at doing things. They send the email, open the task, update the CRM record. Knowledge is where it falls apart. Procedures, decisions, contracts and documentation sit in a dozen places, and an agent reaches them only when somebody pastes a fragment into the prompt by hand.
There are two ways out. Load the knowledge into every agent separately and end up with several copies of the same base, each at a different stage of staleness. Or stand up one knowledge layer that all of them use.
Ragen is the second one.
One knowledge base, many agents
Knowledge goes into Ragen
Documents, drives, systems. Ragen indexes them, enforces permissions at the level of a single document, and keeps all of it on your own infrastructure.
Ragen opens the gateway
An AI Assistant built in Ragen becomes a tool that every MCP client in your company can see.
Your agents ask
An agent in Claude Desktop, in Cursor, in your own code, or in a system that does not exist yet. The answer comes back with citations, and only from the documents that person is allowed to see.
What this makes possible
An assistant inside your CRM answers from your own material
A salesperson asks about warranty terms for a customer in food manufacturing. The agent in the CRM pulls the answer from Ragen, together with the contract it came from.
Your Slack bot stops pointing people at the documentation
Instead of a link to a folder you get the answer and its source. The bot keeps no copy of the knowledge, it asks Ragen.
A service desk agent sees what the requester sees
Permissions travel with the question. An agent acting for someone on the production floor will not see board documents.
Your team works with company knowledge in the tools it already uses
Claude Desktop, Cursor and other MCP clients, with no switch to yet another chat window.
You write it once, it works with every client
MCP is an open protocol. The next tool that shows up in the company connects to the same gateway, with no new integration to write and no per-tool plugin to maintain.
The gateway runs one way: Ragen hands knowledge out. Connectors for Google Drive, HubSpot or ClickUp are a separate matter, described under Integrations. That is where Ragen pulls knowledge in.
See the integrationsAn agent gets no more than a person would
Access control works at document level and holds whether the question comes from a person in a browser or from an agent through the gateway. Every answer comes back with citations, so you can check where the agent got what it wrote.
Without that, an agent stays in a sandbox, well away from company knowledge.
For technical teams
Three routes into the same knowledge layer:
MCP server
The Ragen AI Assistant as a tool for external MCP clients, Claude Desktop and Cursor among them.
OpenAI-compatible API
If your code talks to OpenAI, it talks to Ragen.
TypeScript SDK
The official @webamigos/ragen-sdk-ts package, the same one we use ourselves.
The tools the gateway exposes
- ragen_chat
- Send a question to a named assistant and get a finished answer back.
- ragen_search_knowledge_base
- Search an assistant's knowledge base and get the most relevant document fragments back, with no answer generated.
- ragen_list_assistants
- List the assistants available to your API key, to find the id to call.
Underneath: hybrid search (dense and BM25), cross-encoder reranking, citations, multi-tenancy, conversation encryption. Stack: Next.js, NestJS, Temporal, Postgres, Qdrant, Docling. All of it on your own infrastructure, under an open source licence.
MCP client configuration
The block below is the Cursor entry, the .cursor/mcp.json file. The address is your own Ragen instance, and you authenticate with the same API key as the REST API.
.cursor/mcp.json
{
"mcpServers": {
"ragen": {
"url": "https://your-ragen-instance.example.com/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Claude Desktop connects HTTP servers as a custom connector instead: Settings → Connectors → Add custom connector, where you give it the same address. Its local claude_desktop_config.json will not take this shape, because that file launches a process rather than calling a URL. If you would rather keep it in the file, put the mcp-remote bridge in front of it.
Full MCP server documentationConnect your agents to your company knowledge
We will show you what it looks like on our side: the Ragen AI Assistant called from Claude Desktop, with permissions and citations.