Postman MCP Server
com.postman/postman-mcp-server
Give your AI agents trusted access to the full Postman platform.
Install surfaces
How Postman MCP Server runs, per the official MCP registry entry.
- npm
@postman/[email protected] - mcpb
https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.12.3/postman-mcp-server-minimal.mcpb - mcpb
https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.12.3/postman-mcp-server-full.mcpb - mcpb
https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.12.3/postman-mcp-server-code.mcpb - mcpb
https://github.com/postmanlabs/postman-mcp-server/releases/download/v2.12.3/postman-mcp-server-learn.mcpb - streamable-http
https://mcp.postman.com/mcp - streamable-http
https://mcp.postman.com/minimal - streamable-http
https://mcp.eu.postman.com/mcp - streamable-http
https://mcp.eu.postman.com/minimal
Governed execution
How KLA gates calls to Postman MCP Server once it is connected.
A published policy defines which Postman MCP Server actions an agent may take and under what conditions. Each call passes through a policy gate at the tool-call boundary. Permitted actions execute, with the policy basis recorded. Flagged actions execute and are sampled for scheduled human review. High-stakes actions pause and route to a named reviewer on the Decision Desk. The call, the policy decision, and any approval are sealed as an evidence record.
KLA also governs the agents and model providers you already run. See integrations.