How to Use the FastGPT MCP in LangChain

Q: How do I initialize the FastGPT MCP Server in LangChain?

Install the adapter package with pip install langchain-mcp-adapters langgraph and configure the MultiServerMCPClient with your Vinkius endpoint. Call client.gettools() to extract the tools, then pass them directly into your agent constructor.

Q: Can LangChain agents handle concurrent dataset updates in FastGPT?

Yes. Your LangChain agent can run pushdatasetdata and deletedatasetdata inside parallel chain branches. The underlying API handles the concurrency, letting you scale your ingestion pipelines without conflicts.

Q: How does LangSmith trace FastGPT tool execution in LangChain?

Every tool invocation like searchdatasetdata or chatcompletions appears as a distinct step in your LangSmith trace. You get real-time visibility into the exact payload sent to FastGPT, the latency of the request, and the raw text chunks returned.

Q: Can I filter knowledge bases dynamically during a run?

Your agent uses listdatasets to search for specific knowledge bases by keyword or parent ID. Once it finds the correct ID, it passes that value directly into searchdatasetdata for targeted retrieval.

Feed your LangChain chains live knowledge base context and automate document ingestion with FastGPT.

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 LangChain

Create your Vinkius account to connect FastGPT to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain-linked knowledge ingestion in LangChain

`push_dataset_data` feeds raw documents directly into your LangChain runs to build dynamic data pipelines. Your agent grabs fresh data from a web scraping step, runs it through an extraction chain, and writes it straight to your knowledge base without manual exports. You manage the entire lifecycle programmatically inside LangGraph by calling `create_dataset` and `update_dataset_data`. This keeps your retrieval sources fresh because every step in the pipeline feeds into the next tool in the sequence.

Observable semantic search pipelines

`search_dataset_data` queries your knowledge base during LangChain execution to pull ground-truth facts. You see exactly how the agent formulated the query, what semantic matches came back, and how much context was sent to the LLM inside your LangSmith dashboard. Running `get_embeddings` lets you compare vector representations before you push them to the server. You verify alignment between your local text processing steps and the FastGPT backend using a single, traced MCP Server call.

Multi-step conversational context tracking

`chat_completions` keeps track of user interactions across complex LangChain agent loops using explicit session IDs. Your agent retains thread history across dozens of turns without you having to manually manage memory state in your code. Combining this with `list_apps` and `get_app_detail` lets your agent dynamically inspect which FastGPT application configuration matches the current user's intent. The agent switches context on the fly based on the application metadata it reads.

Setup guide

Set up FastGPT MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes FastGPT tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "fastgpt-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent FastGPT transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter package with `pip install langchain-mcp-adapters langgraph` and configure the `MultiServerMCPClient` with your Vinkius endpoint. Call `client.get_tools()` to extract the tools, then pass them directly into your agent constructor.

Yes. Your LangChain agent can run `push_dataset_data` and `delete_dataset_data` inside parallel chain branches. The underlying API handles the concurrency, letting you scale your ingestion pipelines without conflicts.

Every tool invocation like `search_dataset_data` or `chat_completions` appears as a distinct step in your LangSmith trace. You get real-time visibility into the exact payload sent to FastGPT, the latency of the request, and the raw text chunks returned.

Your agent uses `list_datasets` to search for specific knowledge bases by keyword or parent ID. Once it finds the correct ID, it passes that value directly into `search_dataset_data` for targeted retrieval.

All raw text chunks, document metadata, and embeddings processed by `push_dataset_data` run through a secure V8 isolate sandbox on Vinkius. This MCP Server gateway handles your API keys securely and transmits data over HTTPS directly to FastGPT without persistent storage on the proxy.

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