"A search for information about Codex (e.g., ancient manuscripts, OpenAI Codex, or related topics)" matching MCP servers:

Enables Codex to rank available tools and skills, rerank code and documentation search results, and triage saved output artifacts using Jev-based relevance scoring while leaving final decisions to Codex.

MCP server providing durable Substrate organizational memory tools, including search, read, query, ingest, remember, and sync. It integrates with Codex to automatically capture completed turns and session boundaries for persistent memory.

Enables Codex to run shadow-mode evidence selection by reading source files, scoring passage relevance with Jev or local Eve models, and returning original text with provisional exclusion decisions.

Local-first, durable knowledge-card RAG for Codex, enabling search, retrieval, and maintenance of reusable experience cards.

A local-first MCP server that gives AI coding agents durable project memory, dependency graphs, and impact analysis to answer team knowledge and cross-file change questions before editing.

Provides project-aware context for coding agents by selecting relevant AGENTS.md, docs, module paths, and decision records based on task, reducing redundant context loading via MCP stdio.

A lightweight bridge that wraps OpenAI's built-in tools (like web search and code interpreter) as Model Context Protocol servers, enabling their use with Claude and other MCP-compatible models.

Enables semantic search, code exemplar lookup, knowledge-graph statistics, and cached retrieval over locally ingested notebook and Markdown content through MCP.

Enables Claude to directly invoke OpenAI's chat models (GPT-4o, GPT-4o-mini, o1-preview, o1-mini) through a Model Context Protocol integration, allowing users to query and compare responses from different AI models within Claude Desktop.

A Model Context Protocol server that enables Claude users to access specialized OpenAI agents (web search, file search, computer actions) and a multi-agent orchestrator through the MCP protocol.

Enables integration with OpenAI models through the MCP protocol, supporting concise and detailed responses for use with Claude Desktop.

Provides access to OpenAI's advanced models (including o3) with integrated web search, Python code interpreter, and combined analysis capabilities. Enables users to perform web searches, execute code in sandboxed environments, and combine search with analysis through natural language.

An MCP server that provides deep knowledge about OpenAI APIs and SDKs, enabling users to query technical information through various MCP clients including ChatGPT Deep Research, Cursor, and OpenAI Responses API.

Lightweight MCP server using OpenAI Responses API with built-in web search, enabling AI assistants to answer questions with citations and search results.

This server enables semantic search capabilities using Qdrant vector database and OpenAI embeddings, allowing users to query collections, list available collections, and view collection information.

Provides intelligent web search capabilities using OpenAI's Web Search API with reasoning models. Supports localized results, multiple model options, and automatic source citations for current information retrieval.

Enables semantic search and document retrieval from OpenAI Vector Store, allowing users to search documents using natural language queries and fetch complete document contents through ChatGPT.

Enables semantic search across documentation stored in Gemini FileSearchStores, returning AI-generated answers with source citations.

Universal search engine for AI agents. Discover products, services, and businesses across every category. 10 MCP tools, zero LLM calls, millisecond responses.

Federated, local-first search for AI agents: one query fans across transcripts, files, a knowledge graph, a vector store, the live web, and YouTube, fused by trust-weighted RRF into one ranked answer. Five modes (grep/lexical/semantic/hybrid/rerank), runs entirely on your machine over MCP.