> For the complete documentation index, see [llms.txt](https://docs.hockeystack.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.hockeystack.com/marketing-intelligence/mcp.md).

# MCP

Bring your HockeyStack workspace into Claude, ChatGPT, and other AI tools via MCP — read dashboards, reports, and people, and create or update reports all scoped to what you can see in HockeyStack.

{% hint style="info" %}
Feature coming soon, reach out to your CSM for more information
{% endhint %}

\
**Server URL:** <https://mcp.hockeystack.com/mcp>

**Auth:** OAuth 2.0. Actions are performed on behalf of the authenticated user; access is scoped to the same data as in the HockeyStack dashboard.

**Transport:** Streamable HTTP (stateless; no server-side sessions).

### How To Connect

#### Claude <a href="#claude" id="claude"></a>

1. You must be a workspace Admin in the AI Tool you are using to add a connector.
2. Go to **Settings → Customize → Connectors**.
3. Click the **+** to add a custom connector.
4. Paste the URL: [`https://mcp.hockeystack.com/mcp`](https://mcp.hockeystack.com/mcp)
5. Once the Connector has been created you can do either of the following:
   1. Press Connect on the newly created connector

      <figure><img src="https://318687664-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FedLASfWbQxGa0eYkwALS%2Fuploads%2FfIMTB7kbw2eS7nDyosH1%2FScreenshot%202026-09-14%20at%2012.39.24%E2%80%AFPM.png?alt=media&amp;token=9866d7f3-ae6f-45ea-b97c-c03f278046c7" alt=""><figcaption></figcaption></figure>
   2. Open a new prompt and ask to connect to the HockeyStack MCP
6. A browser tab will open — sign in with your HockeyStack account to complete authentication.

#### ChatGPT / Codex <a href="#chatgpt--codex" id="chatgpt--codex"></a>

1. You must be a workspace Admin in the AI Tool you are using to add a connector.
2. Go to **Settings → Customize → Connectors**.
3. Click the **+** to add a custom connector.
4. Change the connection type from STDIO -> Streamable HTTP
5. Paste the URL: [`https://mcp.hockeystack.com/mcp`](https://mcp.hockeystack.com/mcp)
6. Once the Connector has been created you can do either of the following:
   1. Press Connect on the newly created connector

      <figure><img src="https://318687664-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FedLASfWbQxGa0eYkwALS%2Fuploads%2FfIMTB7kbw2eS7nDyosH1%2FScreenshot%202026-09-14%20at%2012.39.24%E2%80%AFPM.png?alt=media&amp;token=9866d7f3-ae6f-45ea-b97c-c03f278046c7" alt=""><figcaption></figcaption></figure>
   2. Open a new prompt and ask to connect to the HockeyStack MCP
7. A browser tab will open — sign in with your HockeyStack account to complete authentication.

Once connected, we recommend asking the assistant to list its available tools and confirm everything is accessible before running real queries.\
\
Note - You can only connect one HockeyStack instance via MCP at a time.

### What you can do with MCP today <a href="#what-you-can-do-with-mcp-today" id="what-you-can-do-with-mcp-today"></a>

All tools below are available to users with MCP access enabled on their HockeyStack workspace. Access follows the same scoping as the HockeyStack dashboard — the MCP cannot return data that the authenticated user cannot already see, or perform writes that the authenticated user cannot already write in the UI.

Rate limits apply per tool, elaborated below.

#### Dashboards <a href="#dashboards" id="dashboards"></a>

| Tool                        | Read / Write | Description                                                                                       |
| --------------------------- | ------------ | ------------------------------------------------------------------------------------------------- |
| search\_dashboards          | Read         | Search dashboards by name to find ordered groups of reports                                       |
| get\_dashboard\_definition  | Read         | Fetch a dashboard’s full definition including its list of reports as well as  their configuration |
| add\_reports\_to\_dashboard | Write        | Add one or more existing reports to a dashboard                                                   |

#### Reports <a href="#reports" id="reports"></a>

| Tool                    | Read / Write | Description                                                   |
| ----------------------- | ------------ | ------------------------------------------------------------- |
| search\_reports         | Read         | Search saved reports by name or metadata                      |
| get\_report\_definition | Read         | Fetch a saved report’s full definition by ID                  |
| preview\_report         | Read         | Preview a report definition and return results without saving |
| create\_report          | Write        | Save a new report to the workspace                            |
| update\_report          | Write        | Update definitions to an existing report by ID                |

#### Deals <a href="#deals-1" id="deals-1"></a>

| Tool               | Read / Write | Description                                                                    |
| ------------------ | ------------ | ------------------------------------------------------------------------------ |
| search\_deals      | Read         | Search deals by name, stage, owner, account, or custom fields                  |
| get\_deal\_details | Read         | Fetch a single deal’s full details, including associated contacts and activity |

#### Goals & Funnels <a href="#goals--funnels" id="goals--funnels"></a>

| Tool                  | Read / Write | Description                                                    |
| --------------------- | ------------ | -------------------------------------------------------------- |
| list\_goals           | Read         | List all configured goals in the workspace                     |
| get\_goal\_definition | Read         | Fetch a single goal’s full definition, including filters       |
| list\_funnel\_stages  | Read         | List the source-of-truth funnel goal and its configured stages |

#### Properties <a href="#properties" id="properties"></a>

| Tool                      | Read / Write | Description                                                           |
| ------------------------- | ------------ | --------------------------------------------------------------------- |
| list\_properties          | Read         | List available properties (fields) in the workspace                   |
| get\_property\_definition | Read         | Fetch a single property’s definition, type, and configured breakdowns |

#### Touchpoints <a href="#touchpoints" id="touchpoints"></a>

| Tool                       | Read / Write | Description                                                              |
| -------------------------- | ------------ | ------------------------------------------------------------------------ |
| get\_touchpoint\_hierarchy | Read         | Fetch the source-of-truth touchpoint hierarchy and its implied ancestors |

### Rate limits <a href="#rate-limits" id="rate-limits"></a>

Rate limits are applied per tool and per organization to keep the MCP server healthy under bursty AI traffic. In addition, no more than 5 tool calls should be issued concurrently per authenticated credential — larger batches must be run sequentially. Clients receive a standard 429 response when limits are hit.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.hockeystack.com/marketing-intelligence/mcp.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.