How to Use the Good Grants MCP in OpenAI Agents SDK

Q: How do I register the Good Grants tools within the OpenAI Agents SDK?

You initialize MCPServerStreamableHttp pointing to your Vinkius endpoint and pass it directly to the Agent constructor. The MCP setup handles auto-discovery, exposing tools like listgrantfunds to your agent instantly.

Q: What is the fastest way to run read-only lookups on the MCP Server?

Turn on cacheToolsList=True in your Python setup. This stops your agent from rebuilding the tool list on every turn, allowing rapid queries to listgrantcategories.

Build production-grade Python agents that automatically find and manage Good Grants opportunities using the OpenAI Agents SDK and our MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Good Grants MCP to OpenAI Agents SDK

Create your Vinkius account to connect Good Grants to OpenAI Agents SDK 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 Good Grants with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate submissions with OpenAI Agents SDK

The `create_new_application` tool registers fresh submissions directly into your funding pipeline. Your OpenAI agent calls this endpoint to submit draft data without manual form entry, keeping your pipeline moving. When you register this tool via `MCPServerStreamableHttp`, the agent discovers the schema automatically. The SDK validates the payload before execution, ensuring bad data never hits your account.

Verify funding details with autonomous agents

The `get_application_details` and `list_applications` tools pull specific submission files and status updates straight into your model context. Your agent uses these to track where each submission stands without wasting time on manual dashboard lookups. This MCP server exposes these endpoints so your multi-agent system can pass application data between specialized agents. One agent inspects the details, while another prepares the next steps based on real-time feedback.

Audit review files and user permissions

The `list_application_reviews` and `list_account_users` tools expose evaluator feedback and team access lists directly to your Python runtime. Your agent reads these reviews to analyze scoring patterns and flag applications that need attention. Setting `cacheToolsList=True` in your setup ensures the agent instantly knows how to call these audit endpoints. This keeps your production loops fast and reduces latency during heavy evaluation cycles.

Setup guide

Set up Good Grants MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Good Grants tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Good Grants tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Good Grants tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Good Grants Agent",
            instructions="You have access to Good Grants tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Good Grants. 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 Good Grants 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 Good Grants MCP in OpenAI Agents SDK

You initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint and pass it directly to the Agent constructor. The MCP setup handles auto-discovery, exposing tools like `list_grant_funds` to your agent instantly.

Yes, you control access by managing the exposed tools list in your agent configuration. This prevents your agent from calling write operations like `create_new_application` when it only needs to read funding categories.

The SDK reads the tool schemas directly from the MCP Server and validates arguments before invoking `create_new_application`. If your agent tries to send malformed JSON, the SDK blocks the call before it hits the API.

Turn on `cacheToolsList=True` in your Python setup. This stops your agent from rebuilding the tool list on every turn, allowing rapid queries to `list_grant_categories`.

All application details and review scores remain inside the ephemeral Vinkius sandbox during the execution lifecycle. No persistent storage is used, meaning your private evaluation data is wiped clean the second your agent run finishes.

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