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

Q: Can a crew of agents collaborate to predict where a new technology fits in NASA's strategy using CrewAI?

Yes. A 'Technologist' agent can take a description and use predicttrex to get initial classifications. It can then pass these to a 'Strategist' agent that uses getprogram to see if those classifications align with well-funded NASA programs.

Q: How would a CrewAI setup use this MCP Server to monitor changes in the NASA TechPort (Technology Projects) API itself?

You could dedicate a 'Monitor' agent to periodically call getapispec. If the agent detects a change in the returned OpenAPI spec, it can trigger an alert for a human developer to review, ensuring your other agents don't break unexpectedly.

Deploy a crew of AI agents to autonomously monitor, analyze, and report on NASA's technology portfolio using CrewAI's collaborative framework.

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 CrewAI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an R&D Intelligence Crew

Assign roles to your CrewAI agents. A 'Researcher' agent can use `list_projects` and `search_opportunities` to constantly scan for new developments. An 'Analyst' agent takes the Researcher's findings and uses `get_project` and `predict_trex` to assess their relevance and technology readiness level. A 'Reporter' agent then synthesizes the Analyst's work, using `export_opportunities` to format a weekly brief. The crew works together, passing context through shared memory, to deliver insights no single agent could produce. It's an automated intelligence team.

Autonomous Opportunity Vetting

Create a crew to vet new NASA funding opportunities. One agent's job is to run `list_opportunities` daily. When it finds a new one, it passes the ID to a 'Due Diligence' agent. This second agent uses `get_opportunity` to check the requirements, `get_program` to understand the parent initiative, and `search_organizations` to see which competitors are likely to bid. The crew can then make a recommendation—pursue or ignore—with zero human input.

Strategic Gap Analysis with a CrewAI MCP Server

Task a 'Cartographer' agent to map out NASA's entire R&D landscape using `get_taxonomy_tree`. It passes this map to a 'Prospector' agent. The Prospector systematically checks each taxonomy node with `search_object_advanced`, looking for areas with low project counts but high strategic importance. This crew autonomously identifies 'blue ocean' R&D areas, giving you a map of where to innovate next. This isn't just data retrieval; it's automated strategy.

Setup guide

Set up NASA TechPort (Technology Projects) MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke NASA TechPort (Technology Projects) tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="NASA TechPort (Technology Projects) Analyst",
    goal="Access and analyze NASA TechPort (Technology Projects) data via MCP.",
    backstory="Expert analyst with direct NASA TechPort (Technology Projects) access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent NASA TechPort (Technology Projects) transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="NASA TechPort (Technology Projects) Analyst",
        goal="Access and analyze NASA TechPort (Technology Projects) data via MCP.",
        backstory="Expert analyst with direct NASA TechPort (Technology Projects) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent NASA TechPort (Technology Projects) transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Assign one agent the role of finding relevant projects using `search_object`. When it finds one, it passes the project ID to a 'Networking' agent, which then uses `list_contacts` and `get_organization` to build a profile of key personnel.

Yes. A 'Technologist' agent can take a description and use `predict_trex` to get initial classifications. It can then pass these to a 'Strategist' agent that uses `get_program` to see if those classifications align with well-funded NASA programs.

You could dedicate a 'Monitor' agent to periodically call `get_api_spec`. If the agent detects a change in the returned OpenAPI spec, it can trigger an alert for a human developer to review, ensuring your other agents don't break unexpectedly.

Break the task down. A 'Manager' agent can define a set of smaller, targeted queries. It then delegates these queries to multiple 'Worker' agents, which run `search_object_all_data` in parallel. This is more resilient and faster than one massive query.

Your CrewAI agents access public NASA TechPort information, like project goals, taxonomy codes, and opportunity deadlines. Vinkius secures the connection by routing all calls through a single authenticated endpoint. The execution environment for each tool is stateless and isolated, preventing any data leakage between agent tasks.

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