Skip to main content
Glama
Mieruko

MCP Plugins With ChatGPT Web

by Mieruko

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPreferred port for the MCP server. If in use, the launcher automatically selects a nearby free port.3000
ADMIN_PORTNoPreferred port for the local Workbench/admin server. If in use, the launcher automatically selects a nearby free port.3001
WORKSPACE_PATHNoOptional local project directory to use as the initial workspace. Additional projects can be registered from the Workbench with Add workspace.
MCP_UPSTREAM_CONFIGNoPath to the upstream MCP server configuration file.profiles/mcp-upstream.json
CHATGPT_TOOL_PROFILENoTool profile optimized for ChatGPT Web. Supported profiles include slim and full.slim
MCP_SESSION_RECOVERYNoOptional setting to enable MCP session recovery. Example: true.
WORKBENCH_DEFAULT_MODENoDefault Workbench permission mode. Supported modes include ask, auto/approve, and full.ask
WORKBENCH_SANDBOX_IMAGENoDocker image used when WORKBENCH_SANDBOX_PROVIDER=docker. Example: node:22-bookworm. The image must be pulled manually before enabling the sandbox.
WORKBENCH_SANDBOX_PROVIDERNoOptional sandbox provider. Set to docker to enable the opt-in Docker workspace sandbox.
CONTROL_PLANE_ORGANIZATION_IDNoOptional OpenAI organization ID owning the Secure MCP Tunnel. Set in .env when OpenAI reports tunnel_active_organization_required. Example: org_...

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources