> ## Documentation Index
> Fetch the complete documentation index at: https://leadping.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP Server

> Connect Leadping documentation and API reference context to AI assistants through the Model Context Protocol.

*Revision Date: June 28, 2026*

Leadping provides a hosted Model Context Protocol (MCP) server for the documentation at:

```text theme={null}
https://leadping.ai/docs/mcp
```

Use it when you want an AI assistant to answer Leadping questions from the current docs and API reference instead of relying on stale model knowledge or pasted snippets. It is especially useful when you are building an integration, checking setup requirements, or asking an agent to explain the right Leadping endpoint, field, or compliance workflow.

## What the MCP server does

The Leadping MCP server gives compatible AI tools read-only access to the published documentation and API reference. Once connected, your assistant can:

* Search the Leadping docs for relevant guides, API details, and examples
* Read full documentation pages when it needs more context
* Inspect the OpenAPI reference through the documentation filesystem
* Link answers back to the relevant Leadping docs pages

Good use cases include:

* Asking an agent to find the right lead intake endpoint.
* Reviewing TrustedForm requirements while writing a posting integration.
* Checking carrier registration setup details before launch.
* Generating internal runbooks that cite the Leadping docs.
* Helping a developer use the SDKs without pasting reference pages into chat.

## What it does not do

The MCP server is documentation-only. It cannot:

* Sign in to your Leadping account
* Create, edit, or delete leads
* Send SMS or place calls
* Change sources, phone numbers, billing, users, or settings
* Read private account data
* Issue agent credentials, API keys, source keys, or user tokens

For authenticated account actions, use the Leadping application or API directly. For agent and service authentication, start with [API Authentication](/api-authentication) or the machine-readable guide at `https://leadping.ai/auth.md`.

## What is MCP?

MCP is an open protocol that lets AI applications connect to external tools and data sources in a standard way. Instead of pasting documentation into chat, you connect the assistant to the source.

For Leadping, that source is the published documentation.

## Available tools

The hosted server exposes documentation-focused tools:

| Tool                                           | Use it for                                                                                                                      |
| ---------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `search_leadping_documentation`                | Broad searches across Leadping guides, API reference content, and examples                                                      |
| `query_docs_filesystem_leadping_documentation` | Reading specific `.mdx` docs pages, listing the docs structure, or searching exact terms in a virtual read-only docs filesystem |

Start with search for general questions. Use the filesystem tool when the assistant needs exact page content or wants to inspect the docs tree.

## Quick start

Add the MCP server URL to an MCP-compatible client that supports remote HTTP servers:

```text theme={null}
https://leadping.ai/docs/mcp
```

After connecting, restart or refresh your client if required, then ask a Leadping-specific question.

Try prompts like:

* "Search the Leadping docs for TrustedForm requirements."
* "How do I prepare a business for 10DLC carrier registration in Leadping?"
* "Find the Leadping API endpoint for creating a lead and explain the required fields."
* "What message categories are prohibited on Leadping?"

## Codex

Add the Leadping MCP server to your Codex MCP configuration:

```toml theme={null}
[mcp_servers.leadping]
url = "https://leadping.ai/docs/mcp"
```

Restart Codex so the server is loaded.

## Cursor

Add the server to your Cursor MCP configuration:

```json theme={null}
{
  "mcpServers": {
    "leadping": {
      "url": "https://leadping.ai/docs/mcp"
    }
  }
}
```

Then enable the server in Cursor settings. Once connected, Cursor can use the Leadping docs while helping you write integration code.

## VS Code

For VS Code clients that support MCP over HTTP, add a server entry similar to:

```json theme={null}
{
  "servers": {
    "leadping": {
      "url": "https://leadping.ai/docs/mcp"
    }
  }
}
```

Open the MCP configuration in VS Code and start the server from the editor controls if your extension requires it.

## Claude Code

If your Claude Code version supports remote HTTP MCP servers, add Leadping with:

```bash theme={null}
claude mcp add --transport http Leadping https://leadping.ai/docs/mcp
```

Restart Claude Code, then run `/mcp` to confirm that the Leadping server is connected.

## How it works

1. Your AI assistant receives a Leadping-related question.
2. The assistant searches the Leadping MCP server for relevant docs.
3. If needed, it reads the full page content from the virtual docs filesystem.
4. The assistant answers using the retrieved documentation context.

Ask the assistant to cite the docs page it used when you need a supportable answer.

## Troubleshooting

If your assistant cannot use the Leadping MCP server:

* Confirm the server URL is exactly `https://leadping.ai/docs/mcp`
* Check that your client supports remote HTTP MCP servers
* Restart the MCP client after changing configuration
* Verify the server appears as connected in your client's MCP tools list
* Ask a direct docs question, such as "Search Leadping docs for carrier registration"
* If a client rejects one of the examples above, use that client's current MCP setup format and keep the Leadping server URL the same

If your client only supports local stdio MCP servers, use a supported remote-MCP bridge for that client, or check your client's current MCP documentation.