All three paths need a tool inventory with clear names, descriptions, and typed inputs.
MCP comparison
ChatGPT vs Claude vs Grok MCP connectors.
ChatGPT, Claude, and Grok can all use MCP-style API tools, but the install shape and safety controls are not identical. Sourced generates one agent interface pack and separates the host-specific setup files.
01Details
What they have in common
Remote/cloud setups need a public HTTPS MCP endpoint.
OpenAPI can generate the first draft of tools, schemas, auth notes, and examples.
The safest first launch is a narrow read-only allowlist.
02Details
ChatGPT
OpenAI's Responses API remote MCP tool uses server_url, server_label, allowed_tools, and approval settings.
Sourced generates a ChatGPT JSON review artifact with require_approval where appropriate.
Write/destructive tools can remain approval-gated rather than enabled by default.
The same MCP server can later support hosted or customer-owned deployments.
03Details
Claude
Claude web/org connectors use a remote MCP URL added by the user or organization owner.
Claude Desktop can use a local stdio config for development.
Sourced generates both the remote setup record and local MCP config snippets.
Team rollout should happen after a maintainer reviews auth scopes and destructive tools.
04Details
Grok
xAI remote MCP accepts Grok-compatible remote MCP config and SDK examples.
The Grok path uses allowed_tools; Sourced also emits the xAI native allowed_tool_names SDK example.
xAI remote MCP does not currently support OpenAI's require_approval or connector_id fields.
Because approval gates are not in the Grok connector payload, the generated allowlist and safety report matter more.