Agent-Native Brain MCP Server

io.github.BuilderIO/agent-native-brain

Access company knowledge from Slack, meetings, and transcripts as an AI agent tool.

What is the Agent-Native Brain MCP server?

The Agent-Native Brain MCP server exposes company knowledge from Slack, meetings, transcripts, and decisions as tools for AI agents. It integrates with the Agent-Native framework to provide agents with contextual information from your organization's communication and decision history.

This MCP server connects agents to your company's institutional knowledge stored in Slack, meeting recordings, transcripts, and documented decisions. It enables agents to retrieve and reference cited company information when performing tasks, making them more context-aware and aligned with organizational decisions and communication.

How to install Agent-Native Brain

Copy-paste configuration for popular MCP clients.

transport: http

Config generated by PluginBench — verify against the source before use.

~/.cursor/mcp.json

{
  "mcpServers": {
    "agent-native-brain": {
      "url": "https://brain.agent-native.com/mcp"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

Knowledge retrieval — Access cited company knowledge from Slack, meetings, transcripts, and decisions

Use cases

Retrieve company policies and decisions when agents need to make decisions aligned with organizational guidelines
Access meeting transcripts and notes to provide agents with context about past discussions and decisions
Query Slack conversations to find relevant company information and communication history
Provide agents with institutional knowledge to improve decision-making and reduce hallucinations
Enable agents to cite sources when referencing company knowledge in their responses

Agent-Native Brain MCP server FAQ

What is the Agent-Native Brain MCP server?

It's an MCP server that gives AI agents access to your company's knowledge stored in Slack, meetings, transcripts, and documented decisions. Agents can retrieve and cite this information when performing tasks.

How do I install it in Claude or Cursor?

The server is available as a remote streamable-HTTP endpoint at https://brain.agent-native.com/mcp. You can configure it in your MCP client settings to connect to this remote server.

Is it free to use?

The README does not specify pricing or free tier information. Check the Agent-Native website or contact Builder.io for details.

What sources of knowledge does it access?

It pulls knowledge from Slack channels, meeting recordings and transcripts, decision logs, and other company communication and documentation.

Does it require authentication?

The README does not detail authentication requirements. You may need to configure credentials for your Slack workspace and other connected services.

Can agents cite sources when using this knowledge?

Yes, the server is designed to provide cited knowledge, allowing agents to reference the original source (Slack message, meeting, transcript, decision) when they use information.

README (reference)

Source of truth, from the repository.

Agent-Native

Agent-Native is an open-source TypeScript framework for building agents that pair autonomous work with a purpose-built UI. Define each capability once as an action: the agent uses it as a tool, and the UI calls it from code.

Quick start

npx --yes @agent-native/core@latest create my-agent --standalone --template chat

Follow the getting started guide for a full intro to the framework.

Why build agents with UIs?

Coding agents work with more than a text box. Their environment provides context, tools, files, tests, and previews that make their capabilities and results visible.

Knowledge work needs that same kind of environment. A UI shows what an agent can do and gives people familiar ways to inspect, edit, approve, and share its work.

How Agent-Native works

Shared actions. The agent calls each capability as a tool, and the UI calls it from code. Both paths use the same validation, permissions, and implementation.
Shared data. Work done by the agent appears in the UI, and work done in the UI is available to the agent.
Shared application state. The agent receives relevant UI state, such as the current page, selected record, or active view.

The agent does not click through the UI. It works through the same action layer as the UI.

Example: a shared action

Create actions/hello.ts:

import { defineAction } from "@agent-native/core/action";
import { z } from "zod";

// One action powers every app surface: UI, agent, HTTP, MCP, A2A, and CLI.
export default defineAction({
  description: "Return a friendly greeting.",
  schema: z.object({
    name: z.string().default("world").describe("Name to greet"),
  }),
  http: { method: "GET" },
  run: async ({ name }) => {
    return { message: `Hello, ${name}!` };
  },
});

The agent receives hello as a tool. React calls the same function with useActionQuery("hello", { name: "Alex" }). Agent-Native also exposes it through HTTP, MCP, A2A, and the CLI.

Included

Agent chat: Let people delegate work, ask questions, and review results in the same UI.
Authentication and permissions: Control who can access and change shared work.
Skills and memory: Give agents reusable expertise and persistent context.
Automations: Run agent work on schedules or events.
Agent teams: Delegate work to specialist agents in the same workspace or across connected agents.
PostgreSQL backend: Use PostgreSQL in production and PGlite for local development on any Nitro-compatible host.

Example: edit a running app visually

Use /visual-edit in Claude Code to edit a running app on a canvas instead of prompting for each small UI nudge. Compare live pages together, then ask Claude to apply the chosen edits to your source. For example:

/visual-edit the onboarding flow, plus home at every breakpoint

Review the onboarding screens alongside Home at desktop, tablet, and mobile sizes, adjust a button's color or spacing directly, then ask Claude to apply the pending edits to your source. See the Visual Edit guide for the full walkthrough and sharing details.

Bring your LLM, SQL database, tools, and infrastructure. Everything you build stays yours.

See Agent-Native in action:

https://github.com/user-attachments/assets/ef51644b-6506-46d8-8083-0af7b7e5b65c