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

# MCP server

> Connect TechnologyChecker documentation and API reference to AI tools like Claude, Cursor, VS Code, and ChatGPT via the Model Context Protocol (MCP).

TechnologyChecker provides a hosted MCP server that lets AI tools search this documentation directly. Instead of relying on web search, your AI assistant queries our docs in real time for more accurate answers about the API, features, and integration patterns.

```
https://technologychecker.io/docs/mcp
```

## What is MCP

The [Model Context Protocol](https://modelcontextprotocol.io) (MCP) is an open protocol that creates standardized connections between AI applications and external services. When connected, AI tools can search TechnologyChecker documentation during response generation, not just when you explicitly ask.

<CardGroup cols={2}>
  <Card title="Direct source access" icon="bullseye">
    Searches indexed documentation directly instead of relying on web search results that might be stale or incomplete.
  </Card>

  <Card title="No search noise" icon="filter">
    Bypasses SEO and ranking algorithms. Goes straight to documentation content.
  </Card>
</CardGroup>

## Connect to your AI tool

<Tabs>
  <Tab title="Claude">
    <Steps>
      <Step title="Open Claude settings">
        Navigate to the [Connectors](https://claude.ai/settings/connectors) page in your Claude settings.
      </Step>

      <Step title="Add the MCP server">
        Select **Add custom connector** and enter:

        * **Name:** `TechnologyChecker`
        * **URL:** `https://technologychecker.io/docs/mcp`
      </Step>

      <Step title="Use in conversations">
        When using Claude, select the attachments button (the plus icon) and select **TechnologyChecker**. Claude can now search the documentation while answering your questions.
      </Step>
    </Steps>
  </Tab>

  <Tab title="Claude Code">
    Run the following command to add the TechnologyChecker MCP server:

    ```bash theme={null}
    claude mcp add --transport http TechnologyChecker https://technologychecker.io/docs/mcp
    ```

    Verify the connection:

    ```bash theme={null}
    claude mcp list
    ```
  </Tab>

  <Tab title="Cursor">
    <Steps>
      <Step title="Open MCP settings">
        Press <kbd>Cmd</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> (or <kbd>Ctrl</kbd> + <kbd>Shift</kbd> + <kbd>P</kbd> on Windows) to open the command palette and search for **Open MCP settings**.
      </Step>

      <Step title="Add the server">
        In `mcp.json`, add:

        ```json theme={null}
        {
          "mcpServers": {
            "TechnologyChecker": {
              "url": "https://technologychecker.io/docs/mcp"
            }
          }
        }
        ```
      </Step>
    </Steps>
  </Tab>

  <Tab title="VS Code">
    Create a `.vscode/mcp.json` file in your project and add:

    ```json theme={null}
    {
      "servers": {
        "TechnologyChecker": {
          "type": "http",
          "url": "https://technologychecker.io/docs/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="ChatGPT">
    ChatGPT supports MCP connections for Plus, Pro, and Team users. Add the TechnologyChecker MCP server URL in your ChatGPT settings under **Connectors**.

    ```
    https://technologychecker.io/docs/mcp
    ```
  </Tab>
</Tabs>

<Tip>
  You can also connect from any page on this site. Select the contextual menu (top of the page) and choose **Copy MCP server URL** or connect directly to Cursor or VS Code.
</Tip>

## What content is available

The MCP server searches all indexed content on this documentation site, including:

* API reference pages with endpoint details, parameters, and response schemas
* Feature documentation (domain lookup, lead lists, market research, signals)
* Getting started guides, authentication, rate limits, and credit costs
* Code examples in cURL, Python, and JavaScript

<Note>
  The MCP server is read-only. It searches documentation content but doesn't make API calls or access your TechnologyChecker account data.
</Note>

## Rate limits

| Scope                  | Limit                   | Description                                                       |
| :--------------------- | :---------------------- | :---------------------------------------------------------------- |
| Per user (IP address)  | 200 requests per hour   | Limits how frequently a single user can search the documentation. |
| Per documentation site | 1,000 requests per hour | Limits total searches across all users of the MCP server.         |

## Frequently asked questions

<AccordionGroup>
  <Accordion title="Does the MCP server replace the REST API?">
    No. The MCP server provides AI tools with access to documentation content. The [REST API](/api-reference/introduction) provides programmatic access to technology detection, company data, and market intelligence. They serve different purposes and complement each other.
  </Accordion>

  <Accordion title="Is the MCP server free to use?">
    Yes. The MCP server is included with your documentation and doesn't consume API credits. Rate limits apply to prevent abuse.
  </Accordion>

  <Accordion title="Can I use multiple MCP servers alongside TechnologyChecker?">
    Yes. AI tools support multiple MCP servers simultaneously. Connected servers only consume context when the AI actually searches them, so you can keep several connected without overhead. Be specific in your prompts so the AI searches the most relevant server.
  </Accordion>

  <Accordion title="What AI tools support MCP?">
    MCP is supported by Claude, Claude Code, Cursor, VS Code (Copilot), ChatGPT, Goose, and other MCP-compatible clients. Any tool that implements the Model Context Protocol can connect to the TechnologyChecker MCP server.
  </Accordion>
</AccordionGroup>