How to Use the NASA TechPort (Technology Projects) MCP in AutoGen

Q: How do AutoGen agents handle feedback loops with the NASA TechPort (Technology Projects) server?

Agents can use submitfeedback to report issues or log system notes, or they can use the output of gettaxonomytree to iteratively refine their search queries. This allows them to self-correct and narrow down their research focus over multiple turns.

Q: How is my conversational data protected when using this server?

All agent conversations and intermediate tool outputs from listcontacts remain entirely within your local AutoGen environment. The MCP Server only receives the specific parameters required to execute the API call, ensuring your strategic discussions and contact lists are never exposed.

Deploy AutoGen agents to debate, analyze, and select NASA TechPort funding opportunities autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NASA TechPort (Technology Projects) MCP to AutoGen

Create your Vinkius account to connect NASA TechPort (Technology Projects) 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 NASA TechPort (Technology Projects) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-agent debates on federal technology alignment

Let your AutoGen agents analyze federal research directions from multiple perspectives. One agent can query `list_projects` to find active initiatives, while a separate compliance agent uses `get_project` to evaluate regulatory risks. They debate the findings in a shared conversation to produce a balanced strategic recommendation. This consensus-driven approach ensures your team doesn't miss hidden risks in federal project descriptions. By using the MCP Server, the agents have direct access to the same live data, preventing communication gaps during their deliberations.

Automate federal taxonomy mapping with AutoGen

Mapping complex technology descriptions to federal categories requires careful analysis. In AutoGen, you can task an engineering agent with writing a description and a classification agent with running `predict_trex` to find the right taxonomy nodes. They collaborate to refine the text until it matches NASA's classification standards. If the classification is ambiguous, the agents use `get_taxonomy` to explore adjacent categories. This collaborative loop ensures your project proposals are perfectly aligned with federal research structures before you submit them.

Evaluate funding opportunities via agent negotiation

Finding the right grant requires balancing technical feasibility with financial viability. Set up an AutoGen conversation where a financial agent calls `get_max_funding_amount` and `get_opportunity` to analyze the budget constraints of a solicitation. Meanwhile, a technical agent assesses the development requirements. The agents negotiate to determine if the funding amount justifies the engineering effort. This automated analysis helps your business development team focus only on the most lucrative and technically feasible federal contracts.

Setup guide

Set up NASA TechPort (Technology Projects) 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 NASA TechPort (Technology Projects) 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="NASA TechPort (Technology Projects)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent NASA TechPort (Technology Projects) 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="NASA TechPort (Technology Projects)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent NASA TechPort (Technology Projects) 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 NASA TechPort. 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 NASA TechPort (Technology Projects) 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 NASA TechPort (Technology Projects) MCP in AutoGen

You import the MCP extension and pass the server URL to the `mcp_server_tools` helper. This automatically converts the server's tools into a format that you can pass directly to your AutoGen `AssistantAgent` constructor.

Yes. Because the Vinkius MCP Server runs in a scalable sandbox, multiple agents in your AutoGen conversation can call tools like `search_opportunities` and `get_project` concurrently without blocking each other.

Agents can use `submit_feedback` to report issues or log system notes, or they can use the output of `get_taxonomy_tree` to iteratively refine their search queries. This allows them to self-correct and narrow down their research focus over multiple turns.

The integration supports both stdio and Streamable HTTP transports. AutoGen handles the schema conversion automatically through the tool adapter, allowing your agents to interact with the NASA API directly.

All agent conversations and intermediate tool outputs from `list_contacts` remain entirely within your local AutoGen environment. The MCP Server only receives the specific parameters required to execute the API call, ensuring your strategic discussions and contact lists are never exposed.

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