How to Use the Charity Navigator MCP in AutoGen

Q: How do I load the Charity Navigator MCP Server into AutoGen?

Install autogen-extmcp and use mcpservertools with the Vinkius endpoint. The McpToolAdapter automatically converts the JSON schema so your AssistantAgent can read it.

Q: Does this MCP Server support cause categories?

The getcategories endpoint lists every valid cause area and its parent category. Your routing agent reads this list first to ensure it uses the correct ID for subsequent searches.

Equip your AutoGen agents with live nonprofit data via this 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 Charity Navigator MCP to AutoGen

Create your Vinkius account to connect Charity Navigator 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 Charity Navigator with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen MCP Server Debates

The `search_charities` tool gives your AutoGen researchers the ability to pull raw nonprofit lists based on specific geographic or financial filters. One agent runs the initial query to find organizations matching a cause, then passes the raw JSON to a specialized analyst agent. These agents actively debate the merits of each result. A compliance agent might challenge a recommendation if the expense ratio looks wrong, forcing the researcher to run a new search with stricter parameters.

Debate Financial Health Scores

Your financial agent uses `get_charity_ratings` to extract historical accountability and impact scores. Meanwhile, a secondary agent calls `get_charity` to pull the raw tax filings and current EIN data. They compare the official rating against the raw financial data to reach a consensus. If the transparency score dropped recently, the agents discuss the implications before presenting a final recommendation to the user.

Negotiate Governance Risks

The `get_charity_advisories` tool feeds directly into your risk-assessment agent to flag governance or fundraising violations. If a specific nonprofit looks suspicious, the agent can also check `get_all_advisories` to see if the issue is an isolated event or a sector-wide trend. This creates a strict adversarial review process inside your AutoGen environment. The risk agent aggressively vetoes any organization with an active warning, forcing the primary researcher to find a safer alternative.

Setup guide

Set up Charity Navigator 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 Charity Navigator 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="Charity Navigator_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Charity Navigator 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="Charity Navigator_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Charity Navigator 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 Charity Navigator. 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 Charity Navigator 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 Charity Navigator MCP in AutoGen

Install autogen-ext[mcp] and use mcp_server_tools with the Vinkius endpoint. The McpToolAdapter automatically converts the JSON schema so your AssistantAgent can read it.

Yes, the search endpoint accepts a zero to four rating scale. Your primary researcher agent applies this parameter to ignore poorly rated organizations entirely.

One agent executes the tool call and posts the resulting JSON into the shared chat history. The other agents read that payload and form their own conclusions based on their system prompts.

The get_categories endpoint lists every valid cause area and its parent category. Your routing agent reads this list first to ensure it uses the correct ID for subsequent searches.

The endpoints return public financial health metrics, tax filing summaries, and governance advisories. Vinkius manages the connection via a stateless, ephemeral sandbox, ensuring no persistent tracking of your multi-agent conversations occurs.

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