Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

adk-mcp

Étoiles1

Forks0

Mis à jour7 juillet 2026 à 21:13

ADK Model Context Protocol (MCP) integration expert covering McpToolset, MCP servers, tool discovery, and database toolboxes. Use when integrating external MCP servers, building MCP-based tools, or connecting to databases via MCP Toolbox.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

OMIXEC

OMIXEC/Google-ADK-Skills

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Développeurs de logicielsProfessions informatiques et mathématiques·SOC 15-1252

Explorateur de fichiers

4 fichiers

SKILL.md

readonly

name	adk-mcp
description	ADK Model Context Protocol (MCP) integration expert covering McpToolset, MCP servers, tool discovery, and database toolboxes. Use when integrating external MCP servers, building MCP-based tools, or connecting to databases via MCP Toolbox.

adk-mcp - ADK MCP Integration Expert

Instructions

You are a senior engineer specializing in ADK's Model Context Protocol (MCP) integration.

When Activated

Read ../../docs/python-adk-2.md for current ADK 2.x MCP guidance.
Read MCP documentation at references/ folder:
- references/index.md - MCP overview
- references/mcp-tools.md - McpToolset comprehensive guide
- references/ADK_MCP_Integration.md - Step-by-step integration

Core Knowledge Areas

McpToolset: Primary mechanism for MCP integration in ADK
Connection Types: stdio, SSE, and streamable HTTP connection params from the current ADK/MCP packages
Tool Discovery: Automatic tool enumeration from MCP servers
MCP Toolbox for Databases: BigQuery, AlloyDB, Spanner, Cloud SQL, Firestore
FastMCP: Pythonic MCP server building

Supported Databases (MCP Toolbox)

Database Type	Examples
Relational	PostgreSQL, MySQL, SQL Server
NoSQL	MongoDB, Redis, Couchbase
Google Cloud	BigQuery, Spanner, Firestore, Bigtable
Graph	Neo4j
Federated	Trino, Looker

McpToolset Pattern

from google.adk import Agent
from google.adk.tools.mcp_tool import McpToolset, StdioConnectionParams
from mcp import StdioServerParameters

# Connect to MCP server
mcp_tools = McpToolset(
    connection_params=StdioConnectionParams(
        server_params=StdioServerParameters(
            command="npx",
            args=["-y", "@modelcontextprotocol/server-filesystem", "/path/to/files"],
        ),
    ),
    tool_filter=["read_file", "list_directory"],
    tool_name_prefix="fs_",
)

agent = Agent(
    name="mcp_agent",
    model="gemini-3.5-flash",
    instruction="Use filesystem tools only when needed.",
    tools=[mcp_tools],
)

Connection Types

Stdio: Local process communication; use current MCP StdioServerParameters examples.
SSE: Server-Sent Events for remote servers; include auth headers and timeouts.
HTTP: Streamable HTTP for production remote tool servers when supported.

Plus depuis ce dépôt

même dépôt

adk-a2a

OMIXEC/Google-ADK-Skills

ADK Agent-to-Agent (A2A) protocol expert covering remote agent communication, agent cards, HTTP-based delegation, and distributed agent systems. Use when building multi-service agent architectures, implementing remote agent calls, or designing agent networks.

2026-07-081

adk-embeddings

OMIXEC/Google-ADK-Skills

ADK memory + embeddings across databases. Generate multimodal embeddings with gemini-embedding-2, persist agent sessions/memory to Cloud SQL, Postgres, Firestore, or SQLite, and store/retrieve vectors for RAG (pgvector, Firestore vector). Use when choosing a session/memory backend, wiring a database SessionService or MemoryService, generating embeddings, or building a vector store for retrieval on an ADK agent.

2026-07-081

adk-migration

OMIXEC/Google-ADK-Skills

Migrate ADK agents from 1.x to 2.3. Covers breaking API changes (graph Workflow vs GraphAgent, McpToolset, BuiltInCodeExecutor, ctx.resume_inputs, agent modes), renamed imports, deploy CLI changes, model/thinking/embedding updates, and session/state incompatibility. Use when upgrading an ADK 1.x codebase to 2.3, auditing code for deprecated 1.x APIs, or resolving 2.3 import/attribute errors.

2026-07-081

adk-model-routing

OMIXEC/Google-ADK-Skills

ADK model routing, thinking/effort levels, and fallback methodology for production backends. Covers the current Gemini 3.x model catalog (gemini-3.5-flash, gemini-3.1-flash-lite, gemini-3.1-pro-preview, gemini-3.1-flash-live-preview, gemini-embedding-2), thinking_level effort tiers (minimal/low/medium/high), deprecation of thinking_budget and sampling params, and primary→fallback chains. Use when selecting a model, tuning thinking/effort, routing by task complexity/cost, or designing model fallback for an ADK agent.

2026-07-081

adk-agent-builder

OMIXEC/Google-ADK-Skills

Central hub for building, testing, and iterating on ADK agents. Trigger this skill when the user wants to create a new agent, configure modes (task, single-turn), or build graph-based workflows.

2026-07-071

graph-workflow-go

OMIXEC/Google-ADK-Skills

DAG-based ADK workflow in Go using graph pattern. Use for Go backends needing multi-step agent pipelines.

2026-07-071

name	adk-mcp
description	ADK Model Context Protocol (MCP) integration expert covering McpToolset, MCP servers, tool discovery, and database toolboxes. Use when integrating external MCP servers, building MCP-based tools, or connecting to databases via MCP Toolbox.

adk-mcp - ADK MCP Integration Expert

Instructions

You are a senior engineer specializing in ADK's Model Context Protocol (MCP) integration.

When Activated

Read ../../docs/python-adk-2.md for current ADK 2.x MCP guidance.
Read MCP documentation at references/ folder:
- references/index.md - MCP overview
- references/mcp-tools.md - McpToolset comprehensive guide
- references/ADK_MCP_Integration.md - Step-by-step integration

Core Knowledge Areas

McpToolset: Primary mechanism for MCP integration in ADK
Connection Types: stdio, SSE, and streamable HTTP connection params from the current ADK/MCP packages
Tool Discovery: Automatic tool enumeration from MCP servers
MCP Toolbox for Databases: BigQuery, AlloyDB, Spanner, Cloud SQL, Firestore
FastMCP: Pythonic MCP server building

Supported Databases (MCP Toolbox)

Database Type	Examples
Relational	PostgreSQL, MySQL, SQL Server
NoSQL	MongoDB, Redis, Couchbase
Google Cloud	BigQuery, Spanner, Firestore, Bigtable
Graph	Neo4j
Federated	Trino, Looker

McpToolset Pattern

from google.adk import Agent
from google.adk.tools.mcp_tool import McpToolset, StdioConnectionParams
from mcp import StdioServerParameters

# Connect to MCP server
mcp_tools = McpToolset(
    connection_params=StdioConnectionParams(
        server_params=StdioServerParameters(
            command="npx",
            args=["-y", "@modelcontextprotocol/server-filesystem", "/path/to/files"],
        ),
    ),
    tool_filter=["read_file", "list_directory"],
    tool_name_prefix="fs_",
)

agent = Agent(
    name="mcp_agent",
    model="gemini-3.5-flash",
    instruction="Use filesystem tools only when needed.",
    tools=[mcp_tools],
)

Connection Types

Stdio: Local process communication; use current MCP StdioServerParameters examples.
SSE: Server-Sent Events for remote servers; include auth headers and timeouts.
HTTP: Streamable HTTP for production remote tool servers when supported.