How to Use the DonorsChoose MCP in CrewAI

Q: How do I assign DonorsChoose tools to my CrewAI agents?

You pass the server URL to the agent's mcps parameter. This gives the agent access to all tools like getclassroomprojectdetails automatically.

Q: Can CrewAI agents filter DonorsChoose projects by subject?

They can. Just include listprojectsbysubject in the agent's tool configuration. The agent will then use it whenever the task requires subject-specific data.

Q: Is it possible to list DonorsChoose projects by state in a CrewAI crew?

Yes. Simply provide the listprojectsbystate tool to your crew. The agents will use it to pull project lists for specific regions during their execution phase.

Deploy specialized agent teams to manage DonorsChoose funding operations 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 DonorsChoose MCP to CrewAI

Create your Vinkius account to connect DonorsChoose 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 DonorsChoose with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized agent research

Assign a research agent to call `list_latest_classroom_proposals` while another agent analyzes the data. They share context to find the best projects. This team-based approach works faster than any single agent. Use `search_projects_by_zipcode` to give your research agent a local focus.

Autonomous funding audit

Set up a monitor agent to run `quick_regional_funding_audit` on a loop. It flags projects that need immediate attention for your acting agents. This setup removes the need for manual checks. It keeps your crew informed on changing classroom needs without your intervention.

Priority-based project filtering

Instruct your agents to use `list_high_poverty_needs` to build a list of high-impact opportunities. They can then cross-reference these with other tools. This creates a smart, autonomous pipeline for resource allocation. Your agents effectively filter the noise to find the most critical projects.

Setup guide

Set up DonorsChoose 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 DonorsChoose tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server URL to the agent's `mcps` parameter. This gives the agent access to all tools like `get_classroom_project_details` automatically.

They can. Just include `list_projects_by_subject` in the agent's tool configuration. The agent will then use it whenever the task requires subject-specific data.

Yes. Simply provide the `list_projects_by_state` tool to your crew. The agents will use it to pull project lists for specific regions during their execution phase.

Vinkius manages all authentication via a single endpoint token. This keeps your credentials secure and isolated from the rest of your agent's environment.

The server does not log your personal queries. It acts as a stateless bridge to the API, ensuring your classroom research remains completely private.

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