> For the complete documentation index, see [llms.txt](https://docs.uptiq.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.uptiq.ai/ai-workbench-qore/control-center/govern/connectors.md).
# Connectors
Review which outside systems and platform skills agents can use, and their standing.
Connectors is the account-wide register of what an agent is allowed to reach outside itself — third-party integrations, MCP servers, and the platform's own built-in skills. Open **Control Center → Govern → Connectors**. The page describes itself as showing *"Which outside systems the institution has made available, on what terms — and the outer limit every agent inherits."*
Every agent inherits this as its outer limit: an agent can't use a connector this account hasn't made available, regardless of what its own configuration requests.
Connectors, on the Integrations tab.
Each tab has its own **Search connectors** box, which filters that tab by name. The lists are paged, with the total shown at the bottom, for example `1-10 of 228`.
## Integrations
Third-party systems available to the account, such as core banking platforms, CRMs, and document-processing services. Each row shows:
| Field | What it shows |
| --------------- | -------------------------------------------------------------------------------- |
| **Connector** | The integration's name and icon. |
| **Description** | What it connects to and what it's for. |
| **Standing** | Whether agents may use it — currently **Allowed**. |
| **Tags** | Its category, such as **Banking**, **Compliance**, **CRM**, or **Productivity**. |
This is the same catalog behind [Integrations Hub](/ai-workbench-qore/console/integrations-hub.md) — Connectors is where you review standing across the whole account; Integrations Hub is where you connect one for a project.
## MCP servers
Model Context Protocol servers connected by agents in the account. There is one row for each connection an agent has made, so the same server appears once per agent that uses it. Each row shows:
| Field | What it shows |
| ------------- | --------------------------------------------------------------------------- |
| **Connector** | The connection's name, with **MCP server** and the server's URL beneath it. |
| **Standing** | Whether agents may use it — currently **Allowed**. |
| **Project** | The project the connection belongs to. |
| **Used by** | The agent that uses the connection. |
Use it to see which agents reach which servers. For example, several agents connecting to the same public server each appear as their own row, with their own project.
{% hint style="warning" %}
**The URL is shown in full.** If a server's URL carries a key as a query parameter, anyone who can open Connectors can read it. Prefer servers that take credentials in a header or through OAuth.
{% endhint %}
## Platform skills
Qore's own built-in skills — reasoning, web search and crawl, code execution, document and knowledge operations, and UI-rendering skills like Display Code Block and Display Document. Each row shows:
| Field | What it shows |
| ------------- | -------------------------------------------------- |
| **Connector** | The skill's name, tagged **Platform skill**. |
| **Standing** | Whether agents may use it — currently **Allowed**. |
| **Project** | The project it was used from. |
| **Used by** | The agent that used it. |
Platform skills are listed once per skill per agent that used it, so this tab runs to thousands of rows in a busy account. Search by the skill's name to find it.
Connectors, on the Platform skills tab.
{% hint style="info" %}
Platform skills and MCP servers list **Project** and **Used by** per row because they're attributed to the agent that invoked them. Integrations list **Tags** instead, since a third-party connector is a standing account capability rather than a per-use record.
{% endhint %}
## Related
{% endcolumn %}
{% endcolumns %}
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.uptiq.ai/ai-workbench-qore/control-center/govern/connectors.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
