How to Use the TrueFoundry MCP in CrewAI

Q: How does TrueFoundry integrate with CrewAI?

You pass the MCP Server URL into the Agent configuration list. The crew then treats all exposed tools, like truefoundrygenerateembeddings, as available methods for any agent to use.

Run autonomous operations and specialized agents with CrewAI and MCP Server tooling.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect TrueFoundry MCP to CrewAI

Create your Vinkius account to connect TrueFoundry 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 TrueFoundry with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized Tool Exposure for Agents

You pass the TrueFoundry endpoint URL directly into your agent's configuration. For fine-tuning, use `tool_filter` to selectively expose only the necessary tools—like `truefoundry_list_gateway_models`—to specific agents. This keeps your crew focused and prevents agents from trying to call irrelevant endpoints.

Run Chat Operations for Research Agents

Give a research agent the ability to interact with external knowledge using `truefoundry_run_gateway_chat`. The agent can dynamically query the TrueFoundry gateway, gathering information that feeds into the final report. This allows your multi-agent crew to perform live data collection as part of their collaborative task.

Monitor and Manage Services Collaboratively

The team needs visibility. Agents can check service status or list available tools using `truefoundry_list_mcp_servers` or `truefoundry_get_deployment_status`. The monitor agent compiles this data for the final review. This makes environment management a core part of your autonomous operation.

Setup guide

Set up TrueFoundry 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 TrueFoundry tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the MCP Server URL into the `Agent` configuration list. The crew then treats all exposed tools, like `truefoundry_generate_embeddings`, as available methods for any agent to use.

Yes. One specialized agent can be assigned the role of 'DevOps Manager' whose sole job is calling `truefoundry_deploy_mcp_server` or checking status via `truefoundry_list_deployments`.

The server touches tool schemas, represented as JSON metadata. This is the exact information that defines what capabilities are available to your collaborative agent team.

CrewAI supports stdio, SSE, and Streamable HTTP transports for connecting to MCP Servers. This flexibility ensures reliable communication regardless of how you run the crew.

It's built for it. By providing a unified gateway, TrueFoundry acts as a single source of truth and capability registry for your entire autonomous crew.

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