How to Use the Fastn MCP in CrewAI

Q: How do I configure CrewAI agents to use the Fastn MCP Server?

You can add the server URL directly to your agent's mcps array. For finer control, use the MCPServerHTTP class from crewai.mcp to expose specific MCP tools like executeflow to selected agents.

Q: Can a CrewAI agent update a Fastn workflow dynamically?

Yes, a specialized developer agent can use getworkflow to inspect an existing flow definition, modify the JSON structure, and then call updateworkflow to save the new logic.

Q: How do CrewAI agents handle credential management with Fastn?

Your agents use storecredentials to save API keys for external services securely. When a crew needs to run a job, they reference these credentials via getcredentials without exposing raw keys in the agent prompts.

Q: What is the best way to handle long-running Fastn flows in CrewAI?

Assign a supervisor agent to kick off the process using executeflow. While it runs, the agent can periodically poll getexecution to check on progress without blocking other team members.

Deploy specialized CrewAI agent teams to coordinate, monitor, and run automated Fastn workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fastn MCP to CrewAI

Create your Vinkius account to connect Fastn 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 Fastn with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run collaborative multi-agent teams with this MCP Server

This Fastn MCP Server allows your CrewAI agents to divide and conquer complex automation pipelines by assigning specialized roles. For example, a researcher agent can draft a new process layout while a developer agent uses `create_workflow` to build it. Once the workflow is defined, a separate manager agent can call `publish_workflow` to deploy it. This team-based approach ensures that no single agent is overwhelmed with both planning and executing backend tasks.

Autonomous monitoring and escalation in CrewAI

Fastn gives your CrewAI operations team the visibility needed to track running automations and handle errors without human intervention. An analyst agent can run `list_executions` to scan for failed runs across your system. When a failure is spotted, the analyst passes the run ID to a debugger agent, which queries `get_execution` to find the root cause. If the error is critical, the debugger calls `cancel_execution` and alerts your team on Slack.

Track resource consumption across your CrewAI agents

Fastn provides deep visibility into API limits so your autonomous agent crews don't run up unexpected bills. A supervisor agent can check `get_quota_usage` before dispatching large batch jobs. If the daily limit is running low, the supervisor agent analyzes the breakdown using `get_quota_daily` and `get_quota_summary`. It can then decide to pause non-essential workflows or queue them for the next billing cycle.

Setup guide

Set up Fastn 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 Fastn tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can add the server URL directly to your agent's `mcps` array. For finer control, use the `MCPServerHTTP` class from `crewai.mcp` to expose specific MCP tools like `execute_flow` to selected agents.

Yes, a specialized developer agent can use `get_workflow` to inspect an existing flow definition, modify the JSON structure, and then call `update_workflow` to save the new logic.

Your agents use `store_credentials` to save API keys for external services securely. When a crew needs to run a job, they reference these credentials via `get_credentials` without exposing raw keys in the agent prompts.

Assign a supervisor agent to kick off the process using `execute_flow`. While it runs, the agent can periodically poll `get_execution` to check on progress without blocking other team members.

All connector credentials are encrypted at rest and never exposed to the CrewAI execution logs. When your agents call `rotate_credentials`, the update happens entirely inside the secure Vinkius MCP sandbox, keeping your secrets safe.

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