How to Use the Context7 MCP in Google ADK

Q: How do I initialize the Context7 MCP Server within a Google ADK project?

Import McpToolset and pass the server URL using StreamableHttpServerParameters. Then, add this toolset to your LlmAgent tools array to expose the documentation lookup capabilities.

Feed real-time library documentation to your Google ADK agents to power long-context reasoning with Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Context7 MCP to Google ADK

Create your Vinkius account to connect Context7 to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Context7 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose Context7 Tools to your Google ADK Agents

Give your Gemini models the ability to fetch documentation on demand. By wrapping the Context7 MCP Server in `McpToolset`, your Google ADK agent can call `resolve_library` to map fuzzy framework names to deterministic paths. This integration feeds live documentation into Gemini's massive context window. Your agent can digest entire libraries of code examples at once, eliminating the need to fine-tune models on rapidly changing software APIs.

Targeted Code Fetching for Enterprise Workflows

Use `query_docs` to pull specific code examples directly into your Google Cloud agent pipelines. If your agent is processing data from BigQuery, it can instantly look up the correct client library syntax to write clean, working SQL or Python. You can restrict which tools are visible to your `LlmAgent` using the optional tool name filter. This keeps your Google ADK agent focused only on documentation lookups, saving token costs and reducing execution latency.

Scalable HTTP Transport for Cloud Deployments

Run your documentation toolset in production using the built-in HTTP transport. By configuring `StreamableHttpServerParameters`, your Google ADK system communicates with the external MCP Server over a secure, cloud-ready connection. This setup scales effortlessly alongside your Vertex AI workloads. Your agents can query library structures concurrently without worrying about local subprocess bottlenecks or complex environment setups.

Setup guide

Set up Context7 MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Context7 tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Context7_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Context7 tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Context7. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Context7 now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Context7 MCP in Google ADK

Import `McpToolset` and pass the server URL using `StreamableHttpServerParameters`. Then, add this toolset to your `LlmAgent` tools array to expose the documentation lookup capabilities.

Yes. You can use the framework's tool filtering options to expose only `query_docs` or `resolve_library`, depending on what your agent needs to accomplish.

Gemini can hold over a million tokens, allowing your agent to ingest large blocks of code examples returned by `query_docs` and reason over complex library structures without running out of memory.

Yes, the framework natively handles both transport layers, allowing you to run the MCP server locally during development or host it in the cloud for production.

All search queries and requested library IDs are processed ephemerally to fetch the matching documentation. Your search terms are never stored, keeping your internal development queries completely private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript