How to Use the HigherGov MCP in CrewAI

Q: How do I attach the HigherGov MCP Server to CrewAI?

Pass the Vinkius endpoint URL directly into your agent's mcps array. CrewAI automatically discovers the tools and makes them available to that specific agent.

Q: Can multiple CrewAI agents share HigherGov data?

Yes. A researcher agent can call searchbyid and store the result in shared memory. The writer agent then uses that exact data to draft a summary without calling the API again.

Q: How do I restrict certain HigherGov tools to specific agents?

Use the MCPServerHTTP class from crewai.mcp and apply a toolfilter. You can give the researcher listopportunities while restricting getdocuments to the analyst.

Q: What happens to the procurement data CrewAI processes from HigherGov?

Your agents process public agency budgets from getagency and vendor profiles from getawardee. The Vinkius infrastructure isolates every single tool execution. The connection requires only one endpoint token, and the sandbox wipes all trace of the request the second the payload delivers.

Deploy autonomous GovCon capture teams using CrewAI and the HigherGov 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 HigherGov MCP to CrewAI

Create your Vinkius account to connect HigherGov 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 HigherGov with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy multi-agent proposal teams

`list_opportunities` feeds your researcher agent. This agent scans the federal pipeline for new solicitations matching your core capabilities. It dumps the matching opportunity IDs into the crew's shared memory. Your analyst agent picks up those IDs and calls `get_opportunity` to extract the response deadlines and set-aside requirements. CrewAI manages the handoff. The researcher finds the targets, the analyst qualifies them, and a third agent drafts the bid/no-bid recommendation.

Execute autonomous competitor research

`get_awardee` gives your competitive intelligence agent the exact federal footprint of any vendor. When your crew identifies an incumbent on a target contract, the intelligence agent pulls their past performance and maps their active vehicles. It then uses `list_contracts` to find other contracts that incumbent recently won. The agent builds a threat profile autonomously. You give the crew a NAICS code, and they return a complete breakdown of who owns that market segment.

Monitor agency spending with CrewAI

`list_agencies` lets your tracking agent map the federal market. It finds specific contracting offices and passes their IDs to `get_agency` to pull their historical spending data. The agent watches for budget shifts or sudden spikes in obligations. If the tracking agent spots a massive funding increase, it alerts a moderator agent. The moderator then triggers `list_grants` to see where that money is flowing. You build a crew that acts like a 24/7 federal procurement desk.

Setup guide

Set up HigherGov 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 HigherGov tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent HigherGov 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="HigherGov Analyst",
        goal="Access and analyze HigherGov data via MCP.",
        backstory="Expert analyst with direct HigherGov access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent HigherGov 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 HigherGov. 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 HigherGov 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 HigherGov MCP in CrewAI

Pass the Vinkius endpoint URL directly into your agent's `mcps` array. CrewAI automatically discovers the tools and makes them available to that specific agent.

Yes. A researcher agent can call `search_by_id` and store the result in shared memory. The writer agent then uses that exact data to draft a summary without calling the API again.

Use the `MCPServerHTTP` class from `crewai.mcp` and apply a `tool_filter`. You can give the researcher `list_opportunities` while restricting `get_documents` to the analyst.

You can run your crew on a cron schedule. They wake up, check `list_contracts` for new awards in your sector, update your internal database, and shut down.

Your agents process public agency budgets from `get_agency` and vendor profiles from `get_awardee`. The Vinkius infrastructure isolates every single tool execution. The connection requires only one endpoint token, and the sandbox wipes all trace of the request the second the payload delivers.

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