Skip to main content
Glama
andreahaku

GPT-5 MCP Server

by andreahaku

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_API_KEYYesYour OpenAI API key with GPT-5 access.
TASK_COST_LIMITNoPer-task spending limit in USD (default: 2.00).2.00
DAILY_COST_LIMITNoDaily spending limit in USD (default: 10.00).10.00
ALERT_WEBHOOK_URLNoOptional webhook URL for alerts.
OPENAI_TIMEOUT_MSNoTimeout in ms (default: 30000).30000
OPENAI_RETRY_COUNTNoNumber of retries (default: 3).3
RESOURCE_MAX_COUNTNoMax resources included per call (default: 5).5
DEFAULT_TEMPERATURENoDefault temperature for GPT-5 (default: 0.7).0.7
RESOURCE_MAX_TOKENSNoPer-resource token budget (default: 1500).1500
MAX_INSTRUCTION_TOKENSNoTruncate very long instructions (default: 1500).1500
OPENAI_FALLBACK_MODELSNoComma-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_MODELNoPrimary OpenAI model (default: gpt-5).gpt-5
DEFAULT_REASONING_EFFORTNoDefault reasoning effort: minimal, low, medium, or high (default: high).high
MAX_CONVERSATION_CONTEXTNoNumber of messages kept per call (default: 10).10
OPENAI_RETRY_BASE_DELAY_MSNoBase delay between retries in ms (default: 300).300
CONVERSATION_HARD_CAP_MULTIPLIERNoHard cap multiplier for conversation (default: 10).10

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

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/andreahaku/gpt5_mcp'

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