gpt-codex-handoff
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | OpenAI API key for live reviewer mode. | |
| OPENAI_REVIEWER_MODEL | No | Model name for OpenAI reviewer (e.g., gpt-4.1-mini). | |
| GPT_HANDOFF_REVIEWER_MODE | No | Set to 'fake' to use fake reviewer mode without API key, or 'real' for live mode. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ask_gpt_next_stepC | Ask the GPT reviewer for a strict JSON next-step recommendation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion with other tools. The tool's purpose is distinct by default.
The single tool name is clear and uses a verb_noun pattern, but with no other tools to establish a pattern, consistency cannot be fully assessed.
A single tool is insufficient for a handoff workflow; it suggests a trivial surface that is likely to cause agent dead ends.
The server provides only a next-step recommendation tool, missing obvious related operations like context retrieval, output handling, or workflow control.