Running ADK agents with MCP tools from a REST API

Description and use

apowerb lets teams manage dozens of ADK agents via REST API, auto‑generating ADK modules and recording execution traces, including MCP tool calls.

Problem

Managing dozens of ADK agents that change weekly and tracking execution details is hard for teams.

Outcome

The agent successfully used the MCP tool to answer a GitHub repository question and listed available tools, demonstrating end‑to‑end REST API control.

Workflow

• Obtain an auth token via POST /api/auth/token
• Create an agent record with MCP server details via POST /api/agents
• Run the agent via POST /api/adk/run with a user message
• Inspect ADK events and trace via /api/adk/sessions and /api/adk/trace

Evidence

Agents are stored as database records, created from a web UI or a REST API, and apowerb builds the ADK objects for you.

Source

The response is the list of ADK events for the turn. On the real run, the events contained a functionCall to the MCP tool ask_wiki_question, followed by the model's answer:

Source

ADK stays in charge of the agent loop. apowerb adds what a team needs around it: a web UI and REST API to create and edit agents without redeploying code; built‑in tools for RAG, Text‑to‑SQL, BI charts, Google Workspace and Microsoft 365; scheduled runs and runs triggered by email; per‑user token quotas and a per‑session audit trail; self‑hosting with Docker Compose or a Helm chart.

Source