FastGPT

FastGPT MCP Connector for Claude

A+

Manage FastGPT Knowledge Bases — automate dataset creation, document ingestion, and RAG search directly from any AI agent.

12 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your AI workflows to FastGPT, the powerful open-source platform for building knowledge-based AI applications. This MCP provides 12 tools for full lifecycle management of datasets, apps, and RAG (Retrieval-Augmented Generation) pipelines.

What you can do

  • Dataset Orchestration — Create, list, and manage knowledge base datasets with granular control over configurations
  • Document Ingestion — Push text content or chunks directly to datasets for automatic indexing and vectorization
  • Semantic Search — Run advanced semantic queries against your knowledge bases to test relevance and RAG quality
  • Application Management — List and inspect AI applications to monitor their configurations and linked datasets
  • OpenAI-Compatible Chat — Trigger RAG-powered chat completions with full context, session tracking, and intermediate step visibility

How it works

  1. Subscribe to this server
  2. Set up FastGPT (cloud or self-hosted)
  3. Navigate to your App settings and enter the API Access section
  4. Generate an API Key
  5. Identify your Base URL (e.g., https://api.fastgpt.in for cloud)
  6. Insert both into the fields below to start managing your RAG pipelines.

Who is this for?

  • Knowledge Engineers — automate the ingestion of documentation across multiple datasets
  • RAG Developers — debug semantic search results and optimize chunking strategies programmatically
  • System Integrators — build complex AI workflows that require dynamic knowledge base management
fastgptrag-engineknowledge-basesemantic-searchllm-orchestrationopen-source

12 tools expose this connector's capabilities to your AI agent.

chat_completions

Supports chatId for context tracking, streaming, and detailed intermediate steps. Send a message to a FastGPT application

get_embeddings

Useful for semantic search outside of FastGPT. Generate text embeddings

get_app_detail

Get details for a specific AI application

get_dataset_detail

Get details for a specific dataset

create_dataset

Create a new dataset (knowledge base)

delete_dataset_data

Delete specific data from a dataset

list_apps

List AI applications

list_dataset_data

List data items in a dataset

list_datasets

Can filter by parentId or search keyword. List knowledge base datasets

push_dataset_data

Add or update data in a dataset

search_dataset_data

Perform semantic search on a dataset

update_dataset_data

Update existing data in a dataset

See how to talk to your AI agent using FastGPT.

List all my AI applications in FastGPT.

I've retrieved your applications. You have 2 active apps: 'Customer Support' (ID: app_1) and 'Internal HR' (ID: app_2). Which one would you like to inspect?

Search dataset 'ds_123' for 'company refund policy'.

Searching dataset 'ds_123'... I found 2 relevant results: 1. 'Refunds are processed in 5 days' (Score: 0.95), 2. 'Request via portal' (Score: 0.88). Would you like to see the full content?

Create a new dataset named 'Internal Documentation'.

Creating dataset... 'Internal Documentation' has been created successfully. ID: `ds_docs_999`. You can now start pushing data to it using the `push_dataset_data` tool.

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.

Related Connectors