Karrio MCP Server
Karrio ships a first-party MCP server, @karrio/mcp, that exposes its multi-carrier shipping surface to MCP clients. It is a local server: it runs on the operator's machine (stdio) or as a self-run Streamable HTTP process, and it talks to whatever Karrio instance the operator points it at. Karrio does not host an MCP endpoint an agent can call.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport
Tools
get_shipping_rates— Get shipping rate quotes from multiple carriers for a package; returns ranked rates with carrier, service, price and estimated delivery.create_shipment— Create a shipment and purchase a shipping label. Marked destructive in the source because it incurs a charge.get_shipment— Get details of an existing shipment by ID.list_shipments— List shipments with status, carrier and date filters; paginated.cancel_shipment— Cancel a shipment and void its label. Reverses a label purchase.track_package— Track a package by tracking number; returns status, location, ETA and full event history.list_carriers— List all supported carrier integrations in the Karrio catalog with their capabilities.list_carrier_connections— List carrier accounts connected to the instance, with carrier_id, display_name, capabilities and connection status.schedule_pickup— Schedule a carrier pickup for one or more shipments at a specified address and time window.create_manifest— Create an end-of-day manifest (SCAN form) consolidating shipments into a single carrier document.list_api_logs— List API request logs with filters; returns path, method, status code, response time and timestamps.get_api_log— Get full details of one API log entry including request data, response body and carrier tracing records.list_tracing_records— List raw carrier API request/response tracing records for carrier-level debugging.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.