An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect FastGPT to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Automate your knowledge base workflows and semantic search pipelines.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 12 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 12 available through FastGPT.

  1. 01

    Create dataset

    This capability initializes a brand new knowledge base dataset.

  2. 02

    Get app detail

    This capability pulls the configuration details for a specific AI application.

  3. 03

    List apps

    This capability provides a list of all AI applications you have created in FastGPT.

  4. 04

    List dataset data

    Use this to see the individual data items currently stored within a specific dataset.

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 12 available through FastGPT.

  1. 05

    Push dataset data

    This capability adds new information or updates existing entries within a dataset.

  2. 06

    Search dataset data

    This capability performs a semantic search against a dataset to find relevant information based on meaning.

  3. 07

    Update dataset data

    Use this to modify existing information already stored in a dataset.

  4. 08

    Chat completions

    This capability sends a message to a FastGPT application and supports session tracking and intermediate step visibility.

Capability set03 / 03

09-12

4 capabilities in this set.

Part of 12 available through FastGPT.

  1. 09

    Get dataset detail

    This capability retrieves specific configuration and metadata for a single dataset.

  2. 10

    List datasets

    This capability returns a list of all your knowledge base datasets, with options to filter by parent ID or search terms.

  3. 11

    Get embeddings

    Use this to generate text embeddings for use in external semantic search tasks.

  4. 12

    Delete dataset data

    Use this to remove specific pieces of data from a dataset.

Real work

What teams actually run

01

Automated Doc Ingestion

An agent reads a new technical manual and pushes the content into a specific FastGPT dataset.

02

RAG Quality Debugging

A developer asks the agent to run semantic searches to check if the right chunks are being retrieved.

03

Dynamic Knowledge Updates

A workflow automatically updates existing dataset entries when company policies change.

04

App Configuration Audits

An agent lists and inspects application details to ensure they are linked to the correct datasets.

Automate a task

Put FastGPT to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

FastGPT works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put FastGPT to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

927ms average. Fast in production.

FastGPT is checked daily against the live service.

Daily averagePeak 1209ms
Oct 3Today
Fastest day
787ms
Slowest day
1209ms
14-day trend
Slowing+10%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 12 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of FastGPT, so you can see the experience inside your AI.

It does not authenticate your account with FastGPT. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

FastGPT Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_5ych6Vwp9PYj4HCpHT5jojSMb56573gZQlH3hDOl/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — FastGPT capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "fastgpt-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_5ych6Vwp9PYj4HCpHT5jojSMb56573gZQlH3hDOl/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up FastGPT in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work FastGPT owners hand off.

This MCP is built for technical users managing large-scale knowledge retrieval systems.

  • 01

    Knowledge Engineers

    They hand off the task of ingesting documentation across multiple datasets to their agent.

  • 02

    RAG Developers

    They use the agent to programmatically debug semantic search and chunking strategies.

  • 03

    System Integrators

    They build complex workflows that require dynamic management of knowledge bases.

FAQ

Questions FastGPT owners ask.

  • 01

    Can I use this with a self-hosted FastGPT instance?

    Yes. You just need to provide your specific Base URL and API Key during setup.

  • 02

    What AI clients can I use with this MCP?

    You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Does this MCP host my data?

    No. This MCP connects to your existing FastGPT instance, whether it is hosted by FastGPT or by you.

  • 04

    How do I get an API key?

    You generate an API key within the API Access section of your App settings in FastGPT.

  • 05

    Can I test my RAG results through my AI agent?

    Yes. You can use the search_dataset_data capability to run semantic queries and check relevance directly.

  • 06

    Can I use this with my self-hosted FastGPT instance?

    Yes! Simply provide your custom domain in the Base URL field (e.g., https://fastgpt.mycompany.com). The MCP will route all requests to your specific instance.

  • 07

    How do I add new data to an existing dataset?

    Use the push_dataset_data capability. You can send a JSON array of objects containing the text content to be indexed. FastGPT will handle the chunking and embedding automatically.

  • 08

    What is the 'goods_sign' used for in Pinduoduo capabilities?

    Wait, this is the FastGPT FAQ. For FastGPT, you mostly need Dataset IDs and App IDs. The 'goods_sign' is specific to the Pinduoduo MCP. Always check you are using the correct capabilities for the specific platform.

Explore

More in Data Management

Suggestions

Connect FastGPT to Claude, Cursor, ChatGPT & more