Skip to main content
Glama
nekobato

ChatGPT WebSearch MCP

by nekobato
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

ChatGPT WebSearch MCP

A local MCP stdio server that provides access to the OpenAI (ChatGPT) API for Claude Code and other MCP clients. Supports models with web search capabilities.

Usage

Claude Code

$ claude mcp add chatgpt-websearch \
	-s user \  # If you omit this line, it will be installed in the project scope
	-e OPENAI_API_KEY=your-api-key \
	-- npx @nekobato/chatgpt-websearch-mcp

Or configure in settings

{
  "mcpServers": {
    "chatgpt-websearch": {
      "command": "npx",
      "args": ["@nekobato/chatgpt-websearch-mcp"],
      "env": {
        "OPENAI_API_KEY": "your-api-key",
        ...
      },
    },
  },
}

Environment Variables

The following environment variables can be used to set default values:

  • OPENAI_API_KEY (required): Your OpenAI API key

  • OPENAI_DEFAULT_MODEL (optional): Default model to use (default: gpt-5)

  • REASONING_EFFORT (optional): Default reasoning effort level for reasoning models (minimal|low|medium|high)

  • SEARCH_CONTEXT_SIZE (optional): Default verbosity level (low|medium|high)

  • OPENAI_MAX_RETRIES (optional): Default maximum retry attempts (default: 3)

  • OPENAI_API_TIMEOUT (optional): Default API timeout in milliseconds. If not set, auto-adjusts based on effort level:

    • minimal/low: 60000 (1 minute)

    • medium: 120000 (2 minutes)

    • high: 300000 (5 minutes)

Related MCP server: GPT-5 MCP Server

API

MCP Tools

  • ask_chatgpt: Send a prompt to ChatGPT and receive a response

    • prompt (required): The prompt to send

    • model (optional): The model to use (default: from OPENAI_DEFAULT_MODEL env var or gpt-5)

    • system (optional): System prompt to set context and behavior

    • temperature (optional): Temperature for response generation (0-2, default: 0.7) - Not available for reasoning models

    • effort (optional): Reasoning effort level (minimal|low|medium|high, default: from REASONING_EFFORT env var) - For reasoning models only

    • verbosity (optional): Output verbosity (low|medium|high, default: from SEARCH_CONTEXT_SIZE env var) - For reasoning models only

    • maxTokens (optional): Maximum output tokens

    • maxRetries (optional): Maximum API retry attempts (default: from OPENAI_MAX_RETRIES env var or 3)

    • timeoutMs (optional): Request timeout in milliseconds. Auto-adjusts based on effort level (high=300s, medium=120s, low/minimal=60s)

    • useStreaming (optional): Force streaming mode to prevent timeouts. Auto-enabled for medium/high effort reasoning models

Development

Requirements

  • Node.js 22+

  • An OpenAI API key in OPENAI_API_KEY

Commands

# Install dependencies
pnpm install

# Run in development mode
pnpm dev

# Build for production
pnpm build

# Run tests
pnpm test

# Lint code
pnpm lint

# Format code
pnpm format

License

MIT License

Available Tools

1 tool
ask_chatgptA

Ask ChatGPT a question and get a response. Supports both regular models (with temperature) and reasoning models (with effort/verbosity).

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesThe prompt to send to ChatGPT
modelNoThe model to use (default: from OPENAI_DEFAULT_MODEL env var or gpt-5). Unless specified by the user, you should not set this model parameter. Supported models: gpt-5, gpt-5-mini, gpt-5-nano, o3, o3-pro, o4-mini, gpt-4.1, gpt-4.1-minigpt-5
systemNoSystem prompt to set context and behavior for the AI
temperatureNoTemperature for response generation (0-2). Not available for reasoning models (gpt-5, o1, o3, etc.)
effortNoReasoning effort level: minimal, low, medium, high (default: from REASONING_EFFORT env var). For reasoning models only.
verbosityNoOutput verbosity level: low, medium, high (default: from VERBOSITY env var). For reasoning models only.
searchContextSizeNoSearch context size: low, medium, high (default: from SEARCH_CONTEXT_SIZE env var). For reasoning models only.
maxTokensNoMaximum number of output tokens
maxRetriesNoMaximum number of API retry attempts (default: from OPENAI_MAX_RETRIES env var or 3)
timeoutMsNoRequest timeout in milliseconds. Auto-adjusts based on effort level: high=300s, medium=120s, low/minimal=60s. Can be overridden with OPENAI_API_TIMEOUT env var.
useStreamingNoForce streaming mode to prevent timeouts during long reasoning tasks. Defaults to auto (true for medium/high effort reasoning models).

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description carries full burden. It mentions the core behavior (ask question, get response) and model types, but does not disclose potential side effects (e.g., cost, latency) or authentication requirements. The schema provides additional details like streaming and timeouts, but the description itself is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences that front-load the core purpose and then provide a succinct differentiation of model types. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential purpose and model distinction, but given 11 parameters and no output schema, it could mention the return format (text response) and streaming behavior. It is mostly complete, leaving some details to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the baseline is 3. The description adds value by grouping parameters: regular models use temperature, reasoning models use effort/verbosity. This contextual guidance helps the agent select appropriate parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool asks ChatGPT a question and gets a response. It distinguishes between regular and reasoning models, which aligns with the model parameter options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use regular models (with temperature) vs reasoning models (with effort/verbosity). However, it lacks explicit guidance on when not to use this tool, though no siblings exist to compare.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion between tools.

Naming Consistency5/5

A single tool means naming is trivially consistent.

Tool Count1/5

A single tool is far too few for a server named 'WebSearch MCP'; it suggests a mismatch between server purpose and tool surface.

Completeness1/5

The server only offers ask_chatgpt, lacking dedicated web search, scraping, or any other relevant operations, making it severely incomplete.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • OpenAI MCP Server

    thadius83
    A
    license
    C
    quality
    D
    maintenance
    Enables integration with OpenAI models through the MCP protocol, supporting concise and detailed responses for use with Claude Desktop.
    1
    3
    MIT

  • GPT-5 MCP Server

    nbrain-team
    F
    license
    C
    quality
    D
    maintenance
    Enables GPT-5 inference via OpenAI API with configurable reasoning effort, verbosity levels, and optional web search integration. Supports per-call parameter overrides for flexible AI model interactions through MCP.
    1

  • GPT-MCP Bridge

    bzzimmy
    F
    license
    Not graded
    quality
    Not graded
    maintenance
    Enables Claude and other MCP-compatible tools to communicate with OpenAI's GPT models (GPT-5, GPT-5-mini, o3) with conversation history and session management. Features advanced controls like reasoning effort settings, token tracking, and parallel conversation sessions for efficient AI workflows.
    10

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/nekobato/chatgpt-websearch-mcp'

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