Hugging Face
OfficialIntegrates with Hugging Face's ecosystem to search models, datasets, and papers while dynamically co...
HTTP HEADERS — Authorization (Hugging Face token)
- Go to https://huggingface.co and sign in to your account. (huggingface.co)
- Open your profile → Settings → Access Tokens (or visit Settings → Access Tokens). (huggingface.co)
- Click "New token" / "Create new token". Give it a descriptive name (e.g., "FastMCP Integration") and select an appropriate role:
- Choose "read" if you only need read/inference access.
- Choose "write" (or a fine‑grained token granting specific scopes) only if you must push or modify repos. For production, prefer fine‑grained tokens to limit scope. (huggingface.co)
- Create the token and copy it immediately — the token is shown only once. Store it securely (password manager/secret store). (huggingface.co)
- In the FastMCP connection interface (use the "Install Now" / add connector flow), add an HTTP header with:
- Header name: Authorization
- Header value: Bearer YOUR_HF_TOKEN
Example value: Bearer hf_XXXXXXXXXXXXXXXXXXXX (include the "Bearer " prefix exactly).
Enter this in the Headers section of the FastMCP connection dialog when installing the Hugging Face MCP connector.
ENVIRONMENT VARIABLES (if you prefer env vars or for server/docker deploys)
- Decide which env var to set:
- DEFAULT_HF_TOKEN — used by the MCP server when no Authorization header is provided (useful for local/dev or STDIO deployments).
- HF_TOKEN — used by some local clients/SDKs and when running stdio transport.
(Set the one appropriate to your deployment; the README shows DEFAULT_HF_TOKEN for docker examples and HF_TOKEN for stdio.) (huggingface.co)
- Example — Docker run (from the README) to set a default token:
- docker run --rm -p 3000:3000 -e DEFAULT_HF_TOKEN=hf_XXXXXXXXXXXXXXXX hf-mcp-server
Replace hf_XXXXXXXXXXXXXXXX with the token you copied. (Do not expose this token in public images or logs.)
- docker run --rm -p 3000:3000 -e DEFAULT_HF_TOKEN=hf_XXXXXXXXXXXXXXXX hf-mcp-server
- Example — shell export for local runs:
- export HF_TOKEN=hf_XXXXXXXXXXXXXXXX
Then start the MCP server (or your local client) so the process inherits the environment variable. (huggingface.co)
- export HF_TOKEN=hf_XXXXXXXXXXXXXXXX
- If you use both a header and an env var: the server prefers an Authorization: Bearer header for each incoming request; DEFAULT_HF_TOKEN / HF_TOKEN serve as fallbacks for local/dev usage. (Use env vars only for secure server-side deployments — avoid setting defaults in production images.) (huggingface.co)
Important notes and best practices
- The Authorization header must include the "Bearer " prefix exactly: e.g., Authorization: Bearer hf_XXXXXXXX. Do not omit "Bearer ".
- Tokens are displayed only once when created — copy and store them securely. If a token is exposed, immediately revoke/rotate it. (huggingface.co)
- For production use prefer fine‑grained tokens with the minimal scopes required. This limits blast radius if a token is leaked. (huggingface.co)
Where to put the values in FastMCP
- Click the "Install Now" / add-connector button in FastMCP.
- In the connection form that appears, enter:
- Headers → Authorization : Bearer YOUR_HF_TOKEN
- (Optional) Environment variables → add DEFAULT_HF_TOKEN or HF_TOKEN with the token value if you want the MCP server to use it as a fallback.
- Save/install the connector. The MCP server will use the provided header for incoming requests; env vars are used by the server/process if no header is sent or for local deployments.
If you want, tell me whether you need the exact click-path for the FastMCP UI you’re using (Claude/Gemini/VSCode/other) and I’ll give the precise UI steps for that client.
Quick Start
Choose Connection Type for
Authentication Required
Please sign in to use FastMCP hosted connections
Run MCP servers without
local setup or downtime
Access to 1,000+ ready-to-use MCP servers
Skip installation, maintenance, and trial-and-error.
No local setup or infra
Run MCP servers without Docker, ports, or tunnels.
Always online
Your MCP keeps working even when your laptop is off.
One secure URL
Use the same MCP from any agent, anywhere.
Secure by default
Encrypted connections. Secrets never stored locally.
Configuration for
Environment Variables
Please provide values for the following environment variables:
HTTP Headers
Please provide values for the following HTTP headers:
started!
The MCP server should open in . If it doesn't open automatically, please check that you have the application installed.
Copy and run this command in your terminal:
Make sure Gemini CLI is installed:
Visit Gemini CLI documentation for installation instructions.
Make sure Claude Code is installed:
Visit Claude Code documentation for installation instructions.
Installation Steps:
Configuration
Installation Failed
More for API Development
View All →Sentry
Streamline Sentry API integration with this remote MCP server middleware prototype. sentry-mcp acts as a bridge between clients and Sentry, supporting flexible transport methods and offering tools like the MCP Inspector for easy service testing. Inspired by Cloudflare’s remote MCP initiative, it helps developers adapt and debug workflows, making Sentry interaction smoother for both cloud and self-hosted environments.
More for Developer Tools
View All →
GitHub
Extend your developer tools with the GitHub MCP Server—a powerful Model Context Protocol server enhancing automation and AI interactions with GitHub APIs. It supports diverse functionalities like managing workflows, issues, pull requests, repositories, and security alerts. Customize available toolsets to fit your needs, enable dynamic tool discovery to streamline tool usage, and run the server locally or remotely. With read-only mode and support for GitHub Enterprise, this server integrates deeply into your GitHub ecosystem, empowering data extraction and intelligent operations for developers and AI applications. Licensed under MIT, it fosters flexible and advanced GitHub automation.
Desktop Commander
Desktop Commander MCP transforms Claude Desktop into a powerful AI assistant for managing files, running terminal commands, and editing code with precision across your entire system. It supports in-memory code execution, interactive process control, advanced search and replace, plus comprehensive filesystem operations including reading from URLs and negative offset file reads. With detailed audit and fuzzy search logging, it enables efficient automation, data analysis, and multi-project workflows—all without extra API costs. Designed for developers seeking smarter automation, it enhances productivity by integrating all essential development tools into a single, intelligent chat interface.
Chrome DevTools
Provides direct Chrome browser control through DevTools for web automation, debugging, and performance analysis using accessibility tree snapshots for reliable element targeting, automatic page event handling, and integrated performance tracing with actionable insights.
FreeCAD
Enables AI-driven CAD modeling by providing a remote procedure call (RPC) server that allows programmatic control of FreeCAD, supporting operations like creating documents, inserting parts, editing objects, and executing Python code for generative design workflows.