MCP SERVERSend a question to OpenAI's web search with the reasoning model, effort level and search depth chosen per call — quick lookup or deep research from the same tool.
LABSCO SUMMARY
Most search tools give you a query box and one behaviour; here the model, the reasoning effort and how much context is read are arguments, so the same server serves a five-second fact check and a long comparative piece without reconfiguration. Since all three settings move both latency and cost, the useful habit is the one the tool itself recommends: gpt-5-mini at low effort for iterating, and the larger model with higher effort reserved for the questions that earn it.
A single-tool server over OpenAI's web search. One call carries the query plus the knobs that decide how hard the model works on it: which model, how much reasoning effort, how much search context, and where the searcher is.
An OpenAI API key from the OpenAI platform, in OPENAI_API_KEY — searches are billed against it, and effort and context size are what move that cost. It is a Python package run with uvx openai-websearch-mcp, so uv is the only local dependency. The project's installer, uvx --from openai-websearch-mcp openai-websearch-mcp-install, writes the Claude Desktop configuration for you. MIT.
One command plus a key — OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> uvx --from openai-websearch-mcp openai-websearch-mcp-install
USE CASES
Ask with the small model at low effort — fast enough to run several times while narrowing the question.
Raise the model and the reasoning effort and let it read more before answering, rather than stitching together snippets yourself.
Pass the location with the query, so local events, services and availability come back for the right place.
Set a default model, then only raise effort and context size on the questions that need it.
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
openai_web_searchOpenAI Web Search with reasoning models.
For quick multi-round searches: Use 'gpt-5-mini' with reasoning_effort='low' for fast iterations.
For deep research: Use 'gpt-5' with reasoning_effort='medium' or 'high'. The result is already multi-round reasoned, so agents don't need continuous iterations.
Supports: gpt-4o (no reasoning), gpt-5/gpt-5-mini/gpt-5-nano, o3/o4-mini (with reasoning).
BEFORE YOU INSTALL
1 tool when we connected. The model parameter accepts gpt-4o, gpt-4o-mini, gpt-5, gpt-5-mini, gpt-5-nano, o3 and o4-mini; reasoning_effort applies only to the reasoning models.
All 3 documented clients run the server on your machine.
CONTEXT COST
Rated by the size of the one tool definition that rides along on every turn
INSTALLATION
OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> uvx --from openai-websearch-mcp openai-websearch-mcp-install{
"mcpServers": {
"openai-websearch-mcp": {
"command": "uvx",
"args": [
"openai-websearch-mcp"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"OPENAI_DEFAULT_MODEL": "gpt-5-mini"
}
}
}
}MCP servers
arben-adm
assafelovic
Sacode
mzxrai