Skip to main content
Glama
atomtanstudio

chatgpt-image-bridge-mcp

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODEX_BINNoPath to the Codex executable. If not set, the server will attempt to auto-detect it (e.g., from the macOS ChatGPT bundle or via PATH).
CHATGPT_IMAGE_BRIDGE_MCP_MODELNoReserved text/image model choice. Defaults to the account default.
CHATGPT_IMAGE_BRIDGE_MCP_DATA_DIRNoDirectory for durable job records and canonical assets. Defaults to the host-provided PLUGIN_DATA directory, or a user data directory if unset.
CHATGPT_IMAGE_BRIDGE_MCP_WORK_DIRNoScratch directory for Codex turns. Defaults to '<data>/work'.
CHATGPT_IMAGE_BRIDGE_MCP_TOOL_WAITNoSeconds before returning a recoverable running job. Defaults to '240'.
CHATGPT_IMAGE_BRIDGE_MCP_VISION_MODELNoVision-capable Codex model. Defaults to the account default.
CHATGPT_IMAGE_BRIDGE_MCP_ALLOWED_ROOTSNoOptional OS-path-separator list restricting readable images and writable project roots.
CHATGPT_IMAGE_BRIDGE_MCP_IMAGE_TIMEOUTNoMaximum provider generation seconds. Defaults to '1800'.
CHATGPT_IMAGE_BRIDGE_MCP_VISION_TIMEOUTNoMaximum visual-analysis seconds. Defaults to '240'.
CHATGPT_IMAGE_BRIDGE_MCP_MAX_IMAGE_BYTESNoPer-image input/output limit in bytes. Defaults to '16777216'.
CHATGPT_IMAGE_BRIDGE_MCP_MAX_PENDING_JOBSNoMaximum number of queued plus running generation jobs. Defaults to '8'.
CHATGPT_IMAGE_BRIDGE_MCP_CODEX_ENV_ALLOWLISTNoOptional comma-separated exact environment names passed to Codex; values may reach model tools.
CHATGPT_IMAGE_BRIDGE_MCP_JOB_RETENTION_SECONDSNoNumber of seconds to retain private job metadata and canonical assets. Defaults to '2592000'.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/atomtanstudio/chatgpt-image-bridge-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server