How to Use the Candid (GuideStar) MCP in AutoGen

Q: How do I configure Candid (GuideStar) for AutoGen agents?

Use mcpservertools with a StreamableHttpServerParams pointing to your Vinkius URL. Pass the resulting tool list into your AssistantAgent constructor.

Give your AutoGen agents the ability to debate grant approvals via this MCP Server using real Candid data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Candid (GuideStar) MCP to AutoGen

Create your Vinkius account to connect Candid (GuideStar) to AutoGen 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 Candid (GuideStar) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven grant reviews

Approving a large donation requires input from multiple stakeholders. You build an AutoGen system where a compliance agent runs `verify_charity_status` while a financial agent analyzes data from `get_nonprofit_premier`. They share their findings in a shared chat. The agents then debate the merits of the grant. If the financial agent flags a high overhead ratio, the compliance agent counters by pulling recent news via `get_nonprofit_news` to provide context. They negotiate until they reach a final recommendation.

Multi-agent demographic analysis

Foundation boards often mandate specific funding allocations across different communities. A dedicated diversity agent uses this MCP server to call `get_demographics` for every applicant in the pool. It compiles the metrics and presents them to the group. Another agent cross-references those metrics against historical data using `search_grants`. This creates a dynamic feedback loop where agents challenge each other on whether the current applicant pool meets the foundation's stated goals.

Automated due diligence pipelines

Manual vetting takes hours per application. Your setup assigns a researcher agent to run `search_nonprofits` and `get_nonprofit_essentials` the moment a new EIN hits the system. It formats the raw facts and hands them off to an auditor agent. The auditor verifies specific platform rules via `get_nonprofit_eligibility`. If everything checks out, it triggers `get_charity_check_pdf` to lock in the compliance record before the funding agent cuts the check.

Setup guide

Set up Candid (GuideStar) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Candid (GuideStar) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Candid (GuideStar)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Candid (GuideStar) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Candid (GuideStar)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Candid (GuideStar) data")
    print(result.messages[-1].content)

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 Candid (GuideStar). 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 Candid (GuideStar) 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 Candid (GuideStar) MCP in AutoGen

Use `mcp_server_tools` with a `StreamableHttpServerParams` pointing to your Vinkius URL. Pass the resulting tool list into your `AssistantAgent` constructor.

Any agent in your group chat accesses the tools if you provide them in their configuration. They coordinate and decide who should make the specific API calls.

As long as your local model supports function calling, it interacts with this MCP Server. The `McpToolAdapter` automatically converts the JSON schemas for the LLM.

If a tool returns a null value for a specific financial metric, the agent adapts. It might decide to call a different tool or ask a human in the loop for clarification.

Our zero-trust architecture means your API token is the only thing we verify. The EINs you check and the compliance PDFs your agents generate vanish the moment the execution environment spins down.

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