MCP

Use Biggy action plans via remote MCP tools so your own AI agents can discover and call them using the standard Model Context Protocol.

Each enabled action plan in your organization becomes an MCP tool. Tool descriptions are derived from the action plan's description and whenToSelect fields, giving external agents enough context to choose the right tool autonomously.

🚧 Authentication
All BigPanda APIs require Bearer Token Authorization in the call headers.
This API uses the User API Key type of Authorization token.

❗ Rate limitations
To maintain quality of service, the Biggy API is limited to 100 requests per minute. Additional requests will return a 429 response code and the request will need to be retried.

Quick Start

The single /mcp endpoint handles the full MCP lifecycle over standard HTTP POST. Each request is a JSON-RPC 2.0 message. The method field determines the operation (initialize, tools/list, tools/call).

GET and DELETE calls return 405 Method Not Allowed (stateless mode does not use sessions or server-sent event (SSE) streams).

The following methods are available via the /mcp endpoint.

1. Initialize

Initialize the MCP connection. This must be the first interaction sent.

Request

Response

{
    "jsonrpc": "2.0",
    "id": 1,
    "result": {
      "protocolVersion": "2025-11-25",
      "capabilities": { "tools": {}, "logging": {} },
      "serverInfo": { "name": "biggy-action-plans", "version": "1.0.0" }
    }
}

2. List available tools

List all available action plans.

Request

Response

{
    "jsonrpc": "2.0",
    "id": 2,
    "result": {
      "tools": [
          {
              "name": "TroubleshootHistoricalAnalysis",
              "title": "Troubleshoot",
              "description": "Troubleshoots an issue by analyzing historical data...\n\nWhen to select:\nUser asks about past incidents, alerts, or historical patterns.",
              "inputSchema": {
                  "type": "object",
                  "properties": {
                      "query": { "type": "string", "description": "The user query to run against this action plan." },
                      "responseFormat": { "type": "string", "enum": ["markdown", "plain-text"] },
                      "reasoningEffort": { "type": "string", "enum": ["low", "medium", "high"] }
                  },
                  "required": ["query"]
              },
              "_meta": { "isCustom": false }
          }
      ]
   }
}

Tool input schema

All action plan tools share the same input schema:

Field	Type	Required	Description
`query`	string	Yes	The natural-language query to run against the action plan
`responseFormat`	string	No	`"markdown"` (default) or `"plain-text"`
`reasoningEffort`	string	No	Reasoning level: `"low"`, `"medium"`, or `"high"`

3. Call a Tool

Call an action plan.

Request

Response

{
    "jsonrpc": "2.0",
    "id": 3,
    "result": {
      "content": [
        {
          "type": "text",
          "text": "Based on the historical data..."
        }
      ]
    }
}

Connecting an MCP client

Any MCP-compatible client can connect to this endpoint. The following is an example configuration for clients that accept a remote MCP server URL:

{
    "mcpServers": {
      "biggy": {
        "url": "https://api.biggy.io/mcp",
        "headers": {
          "Authorization": "Bearer your-api-key"
        }
      }
    }
}

Quick Start#

1. Initialize#

2. List available tools#

Tool input schema#

3. Call a Tool#

Connecting an MCP client#

Quick Start

1. Initialize

2. List available tools

Tool input schema

3. Call a Tool

Connecting an MCP client