mcpField
F
Faxend

Faxend

Remote
faxend.comCommunication0Updated 2w ago

About Faxend

Faxend is a hosted remote MCP server for AI assistants to send PDF faxes, track delivery, and check plan pages. It is for Faxend users handling fax tasks from MCP clients, and requires no local server installation.

Key features

  1. 01Send PDFs to fax numbers
  2. 02Add an optional cover page
  3. 03Check delivery status and failure reasons
  4. 04List recent faxes
  5. 05View remaining plan pages

Use cases

  1. 01Fax a PDF form to a number
  2. 02Confirm whether a fax was delivered
  3. 03Review recent faxes on an account
  4. 04Check how many plan pages remain

MCP support

The hosted MCP server provides fax sending, status checks, recent-fax listings, and page-balance tools to MCP clients over Streamable HTTP. Access is authorized with a Faxend API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://faxend.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://faxend.com/mcpAuth required

Tools

Details

From the project README

Faxend logo

Faxend MCP server

Faxend sends real faxes from your phone, browser and now your AI assistant. This repository is the public documentation for Faxend's hosted remote MCP server, which lets Claude, ChatGPT, Cursor and other MCP clients send a PDF to any fax number, follow the delivery and check the pages left on your plan.

  • Server URL: https://faxend.com/mcp
  • Transport: Streamable HTTP (stateless, JSON responses)
  • Auth: your Faxend API key (Authorization: Bearer fxk_..., or ?key=fxk_... for connectors that only take a URL)
  • Full guide: https://faxend.com/mcp/
  • MCP Registry name: com.faxend/faxend

This repository holds documentation only. The server is hosted by Faxend; there is nothing to install or run locally.

Tools

ToolWhat it doesType
send_faxSends a PDF (public https URL or base64) to one fax number, with an optional cover note page. Returns a fax_idwrite
get_fax_statusDelivery status of one fax: sending, delivered or failed (with the reason and whether pages were refunded)read-only
list_recent_faxesUp to 20 recent faxes from your account (web, Chrome extension, AI assistants), recipients maskedread-only
get_remaining_pagesPages left on your Faxend plans, per plan and in totalread-only

Every tool has a title and readOnlyHint / destructiveHint annotations.

Connect

  1. Sign in at https://faxend.com and open API keys (https://faxend.com/api-keys/).
  2. Create a key. It is shown once; copy it.
  3. Add the server to your client.

Claude Code:

claude mcp add --transport http faxend https://faxend.com/mcp \
  --header "Authorization: Bearer YOUR_FAXEND_API_KEY"

Cursor and other clients:

{
  "mcpServers": {
    "faxend": {
      "type": "http",
      "url": "https://faxend.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_FAXEND_API_KEY" }
    }
  }
}

claude.ai and ChatGPT custom connectors take only a URL: use https://faxend.com/mcp?key=YOUR_FAXEND_API_KEY and keep that URL private. Step-by-step instructions for each client are on https://faxend.com/mcp/.

Keys can be revoked any time on the API keys page.

Pricing

Each faxed page (and a cover page) uses one page from your Faxend plan. Failed faxes are refunded automatically. Pages cannot be bought through the assistant; see https://faxend.com/pricing/.

Limits

  • PDF only, up to 20 MB and 100 pages per fax
  • 120 requests per minute and 20 faxes per hour per key
  • Delivery usually takes 1 to 5 minutes

Example prompts

Privacy and terms

License

Documentation in this repository is released under the MIT License. The Faxend service is proprietary.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.