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

# MCP for AI assistants

> Each market runs a Model Context Protocol server, so an assistant can query company data in plain language.

Every market runs a [Model Context Protocol](https://modelcontextprotocol.io) server. Point an MCP
client at it and an assistant can query company data directly, without you writing request code.

## Endpoints

| Market        | URL                                            |
| ------------- | ---------------------------------------------- |
| United States | `https://global-api.thedatacity.com/v1/us/mcp` |
| France        | `https://global-api.thedatacity.com/v1/fr/mcp` |
| Germany       | `https://global-api.thedatacity.com/v1/de/mcp` |
| Ireland       | `https://global-api.thedatacity.com/v1/ie/mcp` |

One server per market, each authenticated with the same API key you use for the REST endpoints. See
[Authentication](/global-api/guides/authentication).

<Note>
  Connect more than one server when you want an assistant to compare markets. Each server only knows
  about its own country, so comparing the US with Germany means connecting both.
</Note>

## Connecting a client

Most clients take a URL and a header. For Claude Code:

```bash theme={null}
claude mcp add --transport http tdc-us \
  https://global-api.thedatacity.com/v1/us/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"
```

Clients that use a JSON configuration file usually take this shape:

```json theme={null}
{
  "mcpServers": {
    "tdc-us": {
      "type": "http",
      "url": "https://global-api.thedatacity.com/v1/us/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" }
    }
  }
}
```

Name each server after its market. An assistant with `tdc-us` and `tdc-de` connected can tell them
apart; two servers both called `tdc` cannot be reasoned about.

## Tools

Each server exposes six tools. They are a deliberate subset of the REST API, not a mechanical
translation of all eleven endpoints — batch and classification endpoints are left out because they
serve bulk pipelines rather than conversational use.

| Tool                    | What it does                                                                |
| ----------------------- | --------------------------------------------------------------------------- |
| `list_filters`          | Lists every filter the market supports, with valid values and match counts. |
| `list_dimension_values` | Lists valid values for one location dimension.                              |
| `search_companies`      | Finds companies by name or free text, using semantic search.                |
| `filter_companies`      | Finds companies matching structured criteria.                               |
| `get_company`           | Retrieves the full record for one company by registration number.           |
| `get_company_group`     | Retrieves the corporate group around one company.                           |

`list_filters` is described to the assistant as the tool to call first. The same rule that governs
the REST API applies here: valid values cannot be guessed, and an unrecognised one returns an empty
result rather than an error. See [Errors](/global-api/guides/errors).

## What you can ask

The tools are designed to be composed, so useful questions are the ones that need several steps:

* "How many industrial biotech companies are there in the US compared with Germany?"
* "Find companies in Bavaria with a website and turnover above €10m, then show me the group
  structure of the largest three."
* "What filters can I use for France, and which of them do not exist for the US?"

The assistant calls `list_filters` to discover the right codes, then `filter_companies` to run the
query. You do not need to know the classification scheme before asking.

## Rate limits

MCP traffic is limited to **300 requests per minute per key**, higher than the 60 per minute that
applies to the REST endpoints, because a single question can trigger several tool calls.

<Warning>
  A throttled tool call comes back as a *successful* MCP result whose content is a `429` document.
  The assistant may read that as data and answer from it rather than reporting a failure. If answers
  suddenly become vague or contradict earlier ones, check whether you are hitting the limit.
</Warning>

## Limits worth knowing

* The server is read-only. No tool writes, updates or deletes anything.
* A key reaches all four markets, so connecting a market server is a choice about what the assistant
  should see, not a permission boundary.
* Tool results count against your quota the same way REST calls do. An assistant exploring a broad
  question can spend a lot of calls quickly.

<Note>
  Tell us which questions your assistant handles badly at
  [support@thedatacity.com](mailto:support@thedatacity.com). The tool set is curated by hand, so
  what agents actually struggle with is what we change next.
</Note>