MCP Integration

Query BRO risk scores directly from Claude Code, Cursor, or any MCP-compatible AI tool. The MCP server wraps the REST API with natural language tooling.

auto_awesome

Why MCP?

chat

Zero-Code Queries

Ask for risk scores in plain English. No API calls, no parsing, no boilerplate. Your AI tool handles everything.

Tool Discovery

MCP-compatible agents automatically discover available tools and their schemas. Plug in and start querying.

data_object

Structured Results

Every response returns typed JSON with scores, verdicts, and dimensions. Machine-readable by default.

terminal

Setup

Add the BRO MCP server to your project's .mcp.json:

.mcp.json

{
  "mcpServers": {
    "bro-oracle": {
      "command": "npx",
      "args": ["@blackhart/bro-mcp"],
      "env": {
        "BRO_API_KEY": "your-key-here"
      }
    }
  }
}

Available Tools

bro_get_score()slug: string

Get the full BRI score, Forge Scale, and all 12 dimension scores for a protocol.

bro_compare()slugs: string[]

Side-by-side comparison of multiple protocols across all dimensions.

bro_check_risk()slug: string, threshold: number

Pass/fail risk gate. Returns whether the protocol meets a minimum BRI.

bro_history()slug: string, days?: number

Score trend over time. Shows BRI changes and the events that triggered them.

bro_search()query: string

Search protocols by name, category, or chain. Returns matching scores.

forum

Usage Examples

Once configured, use natural language in your AI tool:

Natural language queries

# In Claude Code or Cursor, just ask:

"What's the BRO score for Aave?"
→ Returns: BRI 895, MITHRIL, all 12 dimensions

"Compare Morpho vs Euler security"
→ Returns: side-by-side table with dimension breakdown

"Which lending protocols are rated below DAMASCUS?"
→ Returns: filtered list with scores and categories

"Has Uniswap's score changed in the last 30 days?"
→ Returns: history with timestamps and deltas

← API Plans Contracts →