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

# Connectors

{% hint style="info" %}
This feature is currently in beta, with access limited to those participating in the beta.
{% endhint %}

<figure><img src="/files/amIXumOLOJhv0esllzcX" alt=""><figcaption></figcaption></figure>

Connectors give Pylon agents access to external tools so they can search for context, retrieve information, and take action outside Pylon.

Connectors can expose tools through the Model Context Protocol (MCP) or a custom API. Administrators decide which connectors are available and which tools each agent can use.

### Connection types

| Connection   | Best for                                                         | Identity used                                        |
| ------------ | ---------------------------------------------------------------- | ---------------------------------------------------- |
| **Personal** | Assist Agent, Slack Agent, and other human-in-the-loop workflows | The individual teammate's external account           |
| **Shared**   | Team-wide or fallback access for human-in-the-loop workflows     | An organization-level shared account or access token |
| **Agent**    | Background Agent and approved autonomous workflows               | A dedicated agent or service account                 |

### Custom MCP server

Administrators add custom MCP connectors from the [Connectors](https://app.usepylon.com/settings/ai-controls/connectors) page. Once connected, MCP tools can be invoked from an agent, used by [Skills](/pylon-docs/agents/skills.md), or restricted to specific agents and roles.

If a system does not provide an MCP server, an administrator can define a [Custom API tool](https://app.usepylon.com/settings/ai-controls/connectors) that agents can use to hit internal or third party API endpoints.

<figure><img src="/files/022voSi2rIlHabD2r0Uz" alt=""><figcaption></figcaption></figure>

### Permissions and data access

Connecting a tool does not automatically ingest all of that system's data into Pylon. It makes specific tools available for an agent to call when needed.

Pylon controls which tools agents can call. The connected system remains responsible for enforcing its own permissions and tenant boundaries.

{% hint style="info" %}
Admins can disable and enable tools globally directly on the connector level and each agent has it's own tool configuration under&#x20;
{% endhint %}


---

# 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.usepylon.com/pylon-docs/agents/connectors.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.