AI Assistants & MCP

Connect Claude, Cursor, VS Code, Codex or any MCP client to the TSG Global documentation so your AI assistant answers from the real docs.

TSG Global's documentation is available to AI coding assistants through the Model Context Protocol (MCP), an open standard that lets an assistant call outside tools. Connect the server below and your assistant can search these docs, read any page, and report documentation problems back to us, instead of guessing from stale training data.

The documentation MCP server

Setting	Value
Server URL	https://docs.tsgglobal.com/~gitbook/mcp
Transport	Streamable HTTP
Authentication	None. The server only reads public documentation.
Cost	Free

The server exposes three tools:

Tool	What it does
searchDocumentation	Full-text search across every page. Returns matching excerpts with titles and links.
getPage	Fetches the complete Markdown of one page by its URL, for example https://docs.tsgglobal.com/api-reference/programmable-sms/send-an-sms-message.
sendFeedback	Lets the assistant report outdated, contradictory or missing content on a page. Reports go to the TSG documentation team.

This server covers documentation only. It cannot send messages, order numbers, read your account or call any TSG Global API. Your API keys never pass through it. To act on the platform, your code still calls the APIs described in this documentation.

Connect your assistant

Claude Code

Run once in your terminal:

claude mcp add --transport http tsg-docs https://docs.tsgglobal.com/~gitbook/mcp

Then ask, for example, "Using the TSG docs, write a function that sends an SMS and handles the delivery receipt webhook."

Claude.ai / Desktop

Open Settings → Connectors → Add custom connector, name it "TSG Global docs", and paste https://docs.tsgglobal.com/~gitbook/mcp as the URL. No authentication is needed. Enable it in a chat from the tools menu.

Cursor

Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json for all projects):

{
  "mcpServers": {
    "tsg-docs": {
      "url": "https://docs.tsgglobal.com/~gitbook/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json in your workspace, then start the server from the MCP view:

{
  "servers": {
    "tsg-docs": {
      "type": "http",
      "url": "https://docs.tsgglobal.com/~gitbook/mcp"
    }
  }
}

Codex

codex mcp add tsg-docs --url https://docs.tsgglobal.com/~gitbook/mcp

Other clients

Any MCP client that supports streamable HTTP can connect. Point it at https://docs.tsgglobal.com/~gitbook/mcp with no bearer token. stdio and SSE transports are not offered.

Other machine-readable formats

If your tool does not speak MCP, the same content is available as plain Markdown:

Resource	URL	Use it for
Index of all pages with summaries	https://docs.tsgglobal.com/llms.txt	Give an assistant a map of the docs
Every page in one file	https://docs.tsgglobal.com/llms-full.txt	Load the whole documentation into context (about 150 KB)
Any single page	Append .md to its URL, e.g. https://docs.tsgglobal.com/get-started.md	Fetch one page without HTML
One-page API summary	API Quick Reference	Hosts, authentication, endpoints, webhooks and limits in a single read

What to expect

• Answers are grounded in the published documentation. If the docs are wrong, the assistant will be wrong too; the sendFeedback tool exists so it can tell us.

• The assistant still needs your credentials to run code against the API. Keep API keys in environment variables, never in prompts or chat history.

• Prompts that work well: "Search the TSG docs for how DLRs are delivered and write the webhook handler", "Which authentication does the phone-number search API use?", "Compare the SMS and MMS webhook retry policies."

Questions or ideas for the MCP server, including an MCP server for the API itself? Email [e-mail].