Skip to main content

connector.json vs MCP

Different Layers, Same Ecosystem

They solve different problems and work together.

MCP: Tool Access Protocol

MCP (Model Context Protocol) lets AI connect to external tools and data:
  • AI calls github.create_pr() → MCP sends request → GitHub API → response
  • AI calls postgres.query() → MCP sends request → database → results
The target is passive. Tools don’t initiate. They respond.

connector.json: AI Orchestration Spec

connector.json lets AI coordinate with other AI:
  • Claude implements → Codex reviews → results synthesized
  • Both are active participants. Both reason, decide, act.
The target is active. Other AI agents that think and respond intelligently.

How They Compose

connector.json includes MCP as a tool configuration:
MCP servers are available inside connector.json sessions. The AI worker can use MCP tools while participating in the connector pipeline.

Comparison Table

Layer Diagram

connector.json sits on top. MCP and PTY-for-AI are execution layers inside it.