Run Playbook
gateway_run_playbookExecute multi-step playbooks by collapsing multiple tool calls into a single invocation through the MCP Gateway server.
Instructions
Execute a multi-step playbook (collapses multiple tool calls into one invocation)
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| arguments | No | Playbook input arguments | |
| name | Yes | Playbook name to execute |
Implementation Reference
- benchmarks/token_savings.py:120-144 (schema)The gateway_invoke tool is the gateway-level tool used to invoke tools on backends. The user asked for 'gateway_run_playbook', but the architectural documentation in the benchmarks file identifies the gateway meta-tools explicitly as gateway_list_servers, gateway_search_tools, and gateway_invoke. 'gateway_run_playbook' is not part of the meta-MCP gateway definition.
"name": "gateway_invoke", "description": ( "Invoke a specific tool on a specific backend server. " "Pass the server name, tool name, and arguments. " "The gateway routes the request and returns the result." ), "inputSchema": { "type": "object", "properties": { "server": { "type": "string", "description": "Name of the backend MCP server.", }, "tool": { "type": "string", "description": "Name of the tool to invoke.", }, "arguments": { "type": "object", "description": "Arguments to pass to the tool.", }, }, "required": ["server", "tool"], }, },