GPT-5 MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | Yes | Your OpenAI API key with GPT-5 access. | |
| TASK_COST_LIMIT | No | Per-task spending limit in USD (default: 2.00). | 2.00 |
| DAILY_COST_LIMIT | No | Daily spending limit in USD (default: 10.00). | 10.00 |
| ALERT_WEBHOOK_URL | No | Optional webhook URL for alerts. | |
| OPENAI_TIMEOUT_MS | No | Timeout in ms (default: 30000). | 30000 |
| OPENAI_RETRY_COUNT | No | Number of retries (default: 3). | 3 |
| RESOURCE_MAX_COUNT | No | Max resources included per call (default: 5). | 5 |
| DEFAULT_TEMPERATURE | No | Default temperature for GPT-5 (default: 0.7). | 0.7 |
| RESOURCE_MAX_TOKENS | No | Per-resource token budget (default: 1500). | 1500 |
| MAX_INSTRUCTION_TOKENS | No | Truncate very long instructions (default: 1500). | 1500 |
| OPENAI_FALLBACK_MODELS | No | Comma-separated fallback models (default: gpt-4o,gpt-4o-mini,gpt-4-turbo-preview,gpt-4-turbo,gpt-4,gpt-3.5-turbo). | gpt-4o,gpt-4o-mini,gpt-4-turbo-preview,gpt-4-turbo,gpt-4,gpt-3.5-turbo |
| OPENAI_RESPONSES_MODEL | No | Primary OpenAI model (default: gpt-5). | gpt-5 |
| DEFAULT_REASONING_EFFORT | No | Default reasoning effort: minimal, low, medium, or high (default: high). | high |
| MAX_CONVERSATION_CONTEXT | No | Number of messages kept per call (default: 10). | 10 |
| OPENAI_RETRY_BASE_DELAY_MS | No | Base delay between retries in ms (default: 300). | 300 |
| CONVERSATION_HARD_CAP_MULTIPLIER | No | Hard cap multiplier for conversation (default: 10). | 10 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| consult_gpt5C | Consult GPT-5 for planning or coding assistance |
| start_conversationB | Start a new conversation with GPT-5 |
| continue_conversationB | Continue an existing conversation with GPT-5 |
| get_cost_reportB | Get a report of current costs and usage |
| set_cost_limitsB | Configure spending limits for GPT-5 usage |
| set_conversation_optionsC | Adjust conversation budget/context options |
| get_conversation_metadataC | Return conversation metadata and messages |
| summarize_conversationB | Summarize a conversation to reduce context size |
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 8 tools
The purposes of consult_gpt5, start_conversation, and continue_conversation overlap somewhat, as all involve interacting with GPT-5. However, get_cost_* and set_cost_* are clearly distinct, and get_conversation_metadata vs summarize_conversation serve different needs.
Most tools follow a verb_noun pattern (e.g., start_conversation, get_cost_report, set_cost_limits). The exception is consult_gpt5, which embeds the object directly rather than using a generic noun, but the naming style is otherwise consistent.
With 8 tools, the server is well-scoped for managing GPT-5 conversations and costs. Each tool covers a distinct aspect of the workflow without unnecessary bloat, and the count is appropriate for the domain.
The core lifecycle of conversation management and cost control is covered, including starting, continuing, summarizing, and monitoring usage. Minor gaps include the lack of an explicit 'end_conversation' or 'delete_conversation' tool, but agents can likely work around these.