MCP Overview

What is MCP?

The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external tools and data sources. Remb implements an MCP server that exposes 12 core MCP tools by default: session start, memory read/write, conversation logging/search, project setup, scan trigger/status, and tool discovery. The full catalog contains 93 active tools, but specialized workflows stay discoverable until an agent needs them.

The key idea: your project's context is not a snapshot of its source files — it's a graph that your AI builds and curates over every session. Memories capture why decisions were made. Feature notes document what each part does. Conversation logs record what was accomplished. Scanning adds structural breadth — but it's optional and additive, not the foundation.

Setup

Via CLI (recommended)

The CLI includes a built-in MCP proxy that connects via stdio:

remb serve

This proxies JSON-RPC messages between stdio and the Remb HTTP API. No tool definitions are hardcoded — the CLI dynamically forwards the tiered server catalog and lets tool_discover reveal advanced workflows.

Direct HTTP

You can also connect directly to the HTTP MCP endpoint:

POST https://www.useremb.com/api/mcp
Authorization: Bearer remb_your_api_key
Content-Type: application/json

{ "jsonrpc": "2.0", "method": "tools/list", "id": 1 }

IDE Configuration

VS Code (GitHub Copilot)

{
  "servers": {
    "remb": {
      "command": "remb",
      "args": ["serve"],
      "env": {}
    }
  }
}

Claude Code

{
  "mcpServers": {
    "remb": {
      "command": "remb",
      "args": ["serve"]
    }
  }
}

Cursor

{
  "mcpServers": {
    "remb": {
      "command": "remb",
      "args": ["serve"]
    }
  }
}

How It Works

1. Your IDE starts the MCP server via remb serve
2. The AI assistant discovers available tools via tools/list
3. At the start of work, the AI calls remb__session_start with a task hint
4. The CLI proxies the request to the Remb API and returns the result
5. All data is persisted server-side across sessions, IDEs, and machines

Tool Budget

Remb returns the core tool surface by default. For focused task-specific lists, pass _meta.tool_budget on tools/list to get the top-K most relevant tools for the current task. Optionally pass _meta.context_hint with a short description of what you’re working on to score relevance. Budgeted lists always keep session_start and tool_discover so the agent can bootstrap context and find specialized tools. Pass _meta.include_discoverable=true or _meta.include_advanced=true when you explicitly want broader listings.

{
  "method": "tools/list",
  "params": {
    "_meta": {
      "tool_budget": 20,
      "context_hint": "refactor authentication"
    }
  }
}

Tool Categories