Pylon MCP

Expose Pylon data to AI tools and assistants via Model Context Protocol.

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.

What you can do with MCP today

All tools below are available to any Member or Admin user with the MCP Access role 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