Redbird MCP lets your AI tools — Claude, ChatGPT, and others — reach directly into Redbird's AI agents, automation workflows, and data outputs through the Model Context Protocol. Ask your AI to run a workflow, query a dataset, or trigger an analysis. Redbird handles the execution.
{ "mcpServers": { "redbird": { "command": "npx", "args": ["-y", "@redbird/mcp"], "env": { "REDBIRD_API_KEY": "your-api-key", "REDBIRD_PROJECT_ID": "your-project-id" } } } }
Initializing Redbird MCP server... ✓ Authenticated · Project: acme-analytics ✓ Loaded 24 AI agents ✓ Loaded 11 workflow triggers ✓ Loaded 38 datasets ───────────────────────────────────── → Ready · Waiting for tool calls
Your AI tools are great at thinking — planning, drafting, reasoning, summarizing. But ask them to pull your latest sales data, run a pipeline analysis, or trigger an automated report and they hit a wall. They can talk about doing things. They can't actually do them. Model Context Protocol (MCP) is the open standard that closes that gap. Redbird MCP makes Redbird's AI agents, automation workflows, and data outputs available to your AI tools through that standard — so a conversation with Claude or ChatGPT can trigger real work inside Redbird and return real results.
Your AI tool can invoke any Redbird AI agent and receive the results directly in the conversation.
Trigger any Redbird workflow from your AI tool by describing what you need. Redbird runs the workflow and returns the output.
Query datasets and reports produced by Redbird workflows — your AI gets structured, current data to reason about, not stale exports.
MCP is an open protocol. Your Redbird connection works with every AI tool that adopts MCP — today and as new ones emerge.
Claude, ChatGPT, and any other AI tool that supports MCP can connect to Redbird through the same interface — one server, every client.
Redbird's AI agents handle the hardest data work — connecting to sources, cleaning and transforming data, running analysis, tagging content, matching records, and generating reports. Through Redbird MCP, your AI tools can invoke any of these agents directly from a conversation — passing inputs, triggering execution, and receiving structured outputs without any manual workflow setup.
// Your AI calls the Redbird MCP tool { "tool": "redbird_list_agents", "arguments": { "category": "all" } }
[ { "id": 1, "name": "Connector Agent", "category": "data-collection", "description": "Pull from any connected source" }, { "id": 7, "name": "Autotagger Agent", "category": "classification", "description": "Classify and tag records at scale" }, { "id": 14, "name": "Analysis & Insights Agent", "category": "analysis", "description": "Run analytics via natural language" }, ... ]
Every automation workflow built in Redbird — from a simple data pull to a multi-step pipeline that collects, transforms, analyzes, and reports — can be triggered through Redbird MCP. Your AI tool receives the workflow output and can reason about the results, ask follow-up questions, or trigger the next step.
The outputs of Redbird workflows — processed datasets, analysis results, reports — can be queried through Redbird MCP and returned to your AI tool as structured context. Your AI doesn't have to guess or work from stale information — it gets current, workflow-produced data it can reason about accurately.
Redbird MCP is built on the open Model Context Protocol standard — the same protocol being adopted across the AI ecosystem. As more AI tools add MCP support, Redbird becomes accessible to them automatically. One connection. Every AI client that speaks MCP.
Built on the open MCP standard · New AI clients supported automatically
Talk to our team to get set up and connect your AI tools to Redbird's agents, workflows, and data.