Nimesh 88cd0933bd
🐛 Raise and make configurable the MCP request body size limit (#12450)
The MCP endpoint parsed request bodies with express.json() and its
default 100kb limit, so large tool calls such as execute_code failed
with HTTP 413 (PayloadTooLargeError). Read the limit from the new
PENPOT_MCP_MAX_BODY_SIZE env var, defaulting to 10mb, and document it.

Closes #12080

Signed-off-by: Nimesh Kulkarni <167794819+GitNimay@users.noreply.github.com>
Co-authored-by: Andrey Antukh <niwi@niwi.nz>
2026-11-03 16:21:28 +01:00
..
2026-11-01 19:27:24 +01:00
…
2026-06-30 16:15:30 +02:00

Penpot MCP Server

A Model Context Protocol (MCP) server that provides Penpot integration capabilities for AI clients supporting the model context protocol (MCP).

Setup

  1. Install Dependencies

     pnpm install
    
  2. Build the Project

     pnpm run build
    
  3. Run the Server

     pnpm run start
    

Penpot Plugin API REPL

The MCP server includes a REPL interface for testing Penpot Plugin API calls. To use it, connect to the URL reported at startup.