# Pylon MCP

## Pylon MCP Server

The Pylon MCP Server exposes Pylon data to AI tools that support the Model Context Protocol (e.g. Claude, ChatGPT, Cursor). AI tools authenticate with your Pylon account via OAuth and can read and update issues, accounts, and contacts within the data you can see in Pylon.

* **Server URL:** `https://mcp.usepylon.com`
* **Auth:** OAuth 2.0 (AuthKit). Actions are performed on behalf of the authenticated user; access is scoped to the same data as in the Pylon dashboard.
* **Transport:** Streamable HTTP (stateless; no server-side sessions).

### Setup in Pylon

Configure and enable the MCP Server from the Pylon dashboard: Settings → AI Controls → MCP Server. Use the MCP URL above in your AI tool. For more detailed instructions, see [here](https://support.usepylon.com/articles/2407390554-connecting-to-the-pylon-mcp-server?lang=en).

### What you can do with MCP today

All tools below are available to any Member or Admin user with the  `MCP Access` [role](https://docs.usepylon.com/pylon-docs/platform/roles-and-user-management#member-permissions-2) enabled. Access follows the same scoping as the Pylon 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.

#### **Issues**

| **Tool**                 | **Read / Write** | **Description**                                                             |
| ------------------------ | ---------------- | --------------------------------------------------------------------------- |
| **`search_issues`**      | Read             | Search issues by title, state, account, assignee, tags, custom fields, etc. |
| **`get_issue`**          | Read             | Fetch a single issue by ID or number                                        |
| **`get_issue_messages`** | Read             | Full message history for an issue                                           |
| **`create_issue`**       | Write            | Create a new issue                                                          |
| **`update_issue`**       | Write            | Update issue fields (status, assignee, custom fields, …)                    |

#### **Accounts**

| **Tool**              | **Read / Write** | **Description**                                            |
| --------------------- | ---------------- | ---------------------------------------------------------- |
| **`search_accounts`** | Read             | Search accounts by name, domain, tags, custom fields, etc. |
| **`get_account`**     | Read             | Fetch a single account, including custom field values      |
| **`update_account`**  | Write            | Update account fields                                      |

#### **Contacts & Users**

| **Tool**          | **Read / Write** | **Description**                 |
| ----------------- | ---------------- | ------------------------------- |
| **`get_contact`** | Read             | Fetch a contact by ID           |
| **`get_user`**    | Read             | Fetch a Pylon team member by ID |
| **`get_me`**      | Read             | Return the authenticated user   |

### **Rate limits**

Rate limits are applied per tool and per organization to keep the MCP server healthy under bursty AI traffic. Clients receive a standard **`429`** response when limits are hit.

### Use Case Examples

* **Debug an issue end to end:** Solve an issue with Claude Code with a prompt like "debug this \<pylon link>" and put up a PR for a bug fix
* **Write a product spec notion doc:** Feed it a bunch of issues and use a Claude Code skill to generate a product spec doc based on evidence
* **Ad hoc analysis:** Ask a question about a customer in ChatGPT and leverage data from Pylon in addition to other tools like Notion or Linear


---

# Agent Instructions: 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:

```
GET https://docs.usepylon.com/pylon-docs/integrations/pylon-mcp.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.