How to Use the FOIA.gov (Freedom of Information) MCP in AutoGen

Q: How do AutoGen agents share data from the FOIA.gov (Freedom of Information) tools?

Agents pass the tool outputs, such as the XML from getannualreportxml, through their conversational context. One agent fetches the data, and another analyzes it to make a strategic filing decision.

Q: Can I limit which AutoGen agents have access to FOIA.gov (Freedom of Information) tools?

Yes. You register the tools like getagencycomponentrequestform only with specific agents in your AutoGen group chat, ensuring only designated validation agents handle schema checks.

Q: How do AutoGen agents handle complex JSON schemas from FOIA.gov (Freedom of Information)?

The McpToolAdapter automatically converts the schemas returned by getagencycomponentrequestform into format-compliant descriptions that AutoGen agents can easily interpret and debate.

Let specialized AutoGen agents debate filing strategies and validate FOIA schemas before submission.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FOIA.gov (Freedom of Information) MCP to AutoGen

Create your Vinkius account to connect FOIA.gov (Freedom of Information) 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 FOIA.gov (Freedom of Information) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate filings through AutoGen multi-agent debate

The `get_agency_component_request_form` tool retrieves the exact parameters needed for a successful submission. In AutoGen, one agent can draft the request while a secondary validation agent reviews it against the retrieved schema. This collaborative check ensures your filings are complete before they ever hit a government desk. The agents debate missing fields and automatically correct formatting errors based on the live form structure.

Cross-reference agency performance metrics

Use `get_annual_report_xml` to pull raw performance data, allowing a research agent to analyze backlog trends. Meanwhile, a strategic planning agent can use this data to recommend which sub-agencies to target for faster response times. The agents negotiate the best path forward based on historical delay metrics. This consensus-driven approach helps you target the offices most likely to process your requests quickly.

Map complex federal structures collaboratively

The `list_agency_components` tool outputs a dense list of federal offices and their relationships. An AutoGen directory agent can parse this list, while a filtering agent refines the selection using sparse fieldsets. Once they agree on the target office, a third agent calls `get_agency_component` to lock in the UUID. This division of labor makes navigating massive bureaucratic directories fast and error-free.

Setup guide

Set up FOIA.gov (Freedom of Information) 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 FOIA.gov (Freedom of Information) 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="FOIA.gov (Freedom of Information)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent FOIA.gov (Freedom of Information) 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="FOIA.gov (Freedom of Information)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent FOIA.gov (Freedom of Information) 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 FOIA.gov. 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 FOIA.gov (Freedom of Information) 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 FOIA.gov (Freedom of Information) MCP in AutoGen

Agents pass the tool outputs, such as the XML from `get_annual_report_xml`, through their conversational context. One agent fetches the data, and another analyzes it to make a strategic filing decision.

Yes. You register the tools like `get_agency_component_request_form` only with specific agents in your AutoGen group chat, ensuring only designated validation agents handle schema checks.

The `McpToolAdapter` automatically converts the schemas returned by `get_agency_component_request_form` into format-compliant descriptions that AutoGen agents can easily interpret and debate.

Federal data is often messy. Having one agent pull XML reports via `get_annual_report_xml` while another agent audits the data for consistency leads to much more reliable research outcomes.

No. The server operates locally or via secure Vinkius sandboxes, handling only public agency structures, form schemas, and XML reports. Your multi-agent conversations and draft filings remain strictly inside your private AutoGen runtime.

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