How to Use the Insomnia (Collaborative API Design) MCP in Google ADK

Q: How do I configure Insomnia (Collaborative API Design) within the Google ADK?

Install the package using pip install google-adk and define McpToolset with your Vinkius HTTP transport URL. Pass this as tools=mcptoolset to your LlmAgent to instantly grant Gemini access to tools like listprojects and listfiles via this MCP setup.

Q: Can I limit which Insomnia (Collaborative API Design) tools the Google ADK agent can access?

Yes, you can use the optional toolnames filter in the McpToolset configuration to expose only specific tools like listmocks or listenvironments, blocking access to sensitive user data.

Q: How does the MCP connection protect our API design files from exposure?

Your API files and collections retrieved via getfile are processed inside Vinkius's ephemeral V8 Isolate Sandbox. Credentials are never written to disk, and the zero-trust architecture ensures that only authorized Gemini runtime environments can access the schema payloads during execution.

Connect Gemini's 1M+ token context to Insomnia (Collaborative API Design) via the Google ADK for enterprise schema analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Insomnia (Collaborative API Design) MCP to Google ADK

Create your Vinkius account to connect Insomnia (Collaborative API Design) 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 Insomnia (Collaborative API Design) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Massive Context API Analysis using Google ADK

The `get_file` tool gives Gemini agents the ability to ingest massive API design files directly into their 1M+ token context window. By feeding entire OpenAPI definitions and request collections into the model, your agent can detect design discrepancies across thousands of lines of schema code in a single run. This MCP Server manages this data flow, allowing the agent to first map the workspace using `list_orgs` and `list_projects`. This avoids context fragmentation, letting the model cross-reference live schemas against historical database structures stored in BigQuery.

Enterprise Workspace and Mock Auditing

The `list_mocks` tool lets your Gemini agent locate active mock servers to verify that testing endpoints match actual production schemas. The agent cross-references these mocks with the file directory returned by `list_files`, ensuring that frontend teams are building against accurate, updated specifications. Using the Google ADK, you can filter exposed MCP capabilities using `tool_names` to restrict the agent's access. This ensures the agent only queries mock configurations and file structures without touching sensitive administrative endpoints.

Automated Team Permission Verification

The `list_collaborators` tool lists organization members, emails, and roles, allowing your Gemini agent to audit access control patterns. The agent can cross-reference this list with user profiles fetched by `get_user` to flag inactive accounts or contractors who still have access to proprietary API designs. Running this audit via the Google ADK lets you export the results directly to Google Cloud monitoring tools. It turns manual security audits into an automated background process, ensuring compliance across all your team's API projects.

Setup guide

Set up Insomnia (Collaborative API Design) 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 Insomnia (Collaborative API Design) 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="Insomnia (Collaborative API Design)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Insomnia (Collaborative API Design) 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 Insomnia. 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 Insomnia (Collaborative API Design) 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 Insomnia (Collaborative API Design) MCP in Google ADK

Install the package using `pip install google-adk` and define `McpToolset` with your Vinkius HTTP transport URL. Pass this as `tools=[mcp_toolset]` to your `LlmAgent` to instantly grant Gemini access to tools like `list_projects` and `list_files` via this MCP setup.

Yes, you can use the optional `tool_names` filter in the `McpToolset` configuration to expose only specific tools like `list_mocks` or `list_environments`, blocking access to sensitive user data.

Gemini's million-token window allows the agent to ingest huge schema files retrieved by `get_file` all at once. The agent can analyze complex dependencies across multiple collections without losing track of the design context.

Yes, because the Google ADK natively integrates with Google Cloud, your agent can pull database schemas from BigQuery and compare them directly with API designs retrieved via `list_files` to find database-to-API mapping mismatches.

Your API files and collections retrieved via `get_file` are processed inside Vinkius's ephemeral V8 Isolate Sandbox. Credentials are never written to disk, and the zero-trust architecture ensures that only authorized Gemini runtime environments can access the schema payloads during execution.

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