con un clic
sparkgen-tool
Add, list, test, or remove MCP tools
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Add, list, test, or remove MCP tools
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Generate a new SparkGen-AWS project from the cookiecutter template
Develop and modify the SparkGen-AWS cookiecutter template — variables, hooks, files
Run cookiecutter matrix tests to verify template generates correctly across all variable combinations
Add, modify, remove, list, or show agents in the workflow
Send a chat message to the running agent server and display the response
Switch LLM providers, deployment modes, and manage environment configuration
| name | sparkgen-tool |
| description | Add, list, test, or remove MCP tools |
| user_invokable | true |
| auto_invokable | true |
| auto_invoke_hint | Invoke when the user discusses tools, MCP, or tool definitions |
| arguments | <add|list|test|remove> [tool-name] |
Manage MCP tools defined in app/mcp_server.py and config/ai_workflow.yaml.
Before any action:
app/mcp_server.py — find _define_tools() method for current tool schemasconfig/ai_workflow.yaml — parse tools: sectioncurl -sf http://localhost:8000/v1/tools -H "X-API-Key: ${API_KEY:-dev-local-key}"/sparkgen-tool list)Parse app/mcp_server.py _define_tools() and display:
| Name | Description | Parameters | Target |
Also show which agents have each tool assigned (from workflow YAML agents[].tools).
/sparkgen-tool add <name>)Add a new MCP tool to the project. Modify these files:
Tool schema in app/mcp_server.py — add to _define_tools():
Tool(
name="<name>",
description="<description>",
inputSchema={
"type": "object",
"properties": {
# define parameters
},
"required": [...]
}
)
Handler method in app/mcp_server.py — add async def _handle_<name>(self, args) method
Call routing in app/mcp_server.py — add case to call_tool() method:
elif name == "<name>":
return await self._handle_<name>(arguments)
Workflow entry in config/ai_workflow.yaml — add to tools.tools::
- name: <name>
target: <target_type>
resource: "<resource_id>"
Agent assignment — add tool name to relevant agent(s) tools: list in workflow YAML
Test — add test case in tests/test_mcp_server.py
Validate: Run make validate then pytest tests/test_mcp_server.py -v
/sparkgen-tool test <name>)If server is running:
curl -s -X POST http://localhost:8000/v1/tools/<name>/call \
-H "Content-Type: application/json" \
-H "X-API-Key: ${API_KEY:-dev-local-key}" \
-d '{"arguments": {<test_args>}}'
Otherwise run the unit test: pytest tests/test_mcp_server.py -v -k <name>
/sparkgen-tool remove <name>)_define_tools() in app/mcp_server.py_handle_<name>call_tool()tools.tools: in workflow YAMLtools: lists in workflow YAMLmake validate