How to Use the FastGPT MCP in CrewAI

Q: Can multiple CrewAI agents query the same FastGPT dataset simultaneously?

Yes. Your agents share memory and can concurrently run searchdatasetdata or listdatasetdata without locking the dataset or blocking each other.

Q: How do I restrict a CrewAI agent from deleting FastGPT data?

Use MCPServerHTTP to filter the MCP tools and define a toolfilter. This lets you block access to destructive tools like deletedatasetdata while keeping search tools active.

Deploy specialized CrewAI agent teams to coordinate, search, and update FastGPT datasets autonomously without human intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FastGPT MCP to CrewAI

Create your Vinkius account to connect FastGPT 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 FastGPT with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent CrewAI research tasks

The `search_dataset_data` tool lets one specialized agent query your knowledge base while another agent analyzes the findings via this MCP server. They share memory, making complex doc retrieval highly coordinated. By splitting the labor, your crew avoids context window bloat. They pull only the exact chunks needed for the current task.

Autonomous dataset curation

The `push_dataset_data` and `get_dataset_detail` tools automate curation by letting a moderator MCP agent monitor files and check ingestion. A separate auditor agent can then inspect the work. If the auditor finds outdated vectors, it instructs a writer agent to run `update_dataset_data` or purge old records with `delete_dataset_data`.

Role-based FastGPT app monitoring

The `list_apps` and `get_app_detail` tools let a dedicated monitoring crew track active deployment configurations. One agent lists active configurations while another pulls specific metrics. This MCP setup turns passive monitoring into an active feedback loop. Your crew can adjust settings or spin up new knowledge bases on the fly.

Setup guide

Set up FastGPT 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 FastGPT tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can pass the server URL directly inside the agent definition using the `mcps` parameter to link the MCP server. This instantly exposes tools like `chat_completions` and `search_dataset_data` to that specific agent.

Yes. Your agents share memory and can concurrently run `search_dataset_data` or `list_dataset_data` without locking the dataset or blocking each other.

Use `MCPServerHTTP` to filter the MCP tools and define a `tool_filter`. This lets you block access to destructive tools like `delete_dataset_data` while keeping search tools active.

It supports stdio, SSE, and Streamable HTTP transports, allowing you to run your crew locally or deploy it to a serverless environment.

Yes. All data processed by the server is handled inside an ephemeral, zero-trust sandbox. Your raw text documents and chat history are never cached, logged, or stored on Vinkius infrastructure.

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