"OpenAI's Web Retrieval Infrastructure" matching MCP servers:

Enables AI agents to search and retrieve over 89K skills on-demand at runtime, eliminating the need to manually install skills upfront.

An MCP server that retrieves relevant PDF chunks via local embeddings and returns them to IDE agents (Cursor, Kiro, Claude Code) for answer generation.

A version-aware cache for web research that stores and serves documentation references, preventing models from re-researching the same topics across sessions.

Bridges AI agents with watsonx.data document libraries, enabling natural language queries and intelligent retrieval from document libraries.

MCP server for Gramps Web. Gives AI agents structured, tool-based access to family trees through the Model Context Protocol. Built with .NET 8.

Remote MCP server (HTTP/OAuth) exposing a self-hosted Honcho instance to claude.ai custom connectors and other MCP clients.

Enables AI agents to persist, retrieve, and share source-linked memory across sessions via MCP tools, backed by PostgreSQL with project/session management, decision tracking, keyword search, and cross-host context handoff.

Enables proof-carrying project execution through a read-only remote MCP endpoint and WebMCP tools for managing Project Passports, task graphs, evidence-backed provider comparisons, route approvals, artifacts, verification records, and checkpoints without executing external providers.

MCP server giving AI agents real-time web search, page scraping, company intelligence, email discovery, local lead generation, and a persistent knowledge graph. Pay only for what you use, no subscriptions.

Enables AI applications to submit claims, decisions, and evidence so it maintains a typed state model of beliefs, conflicts, changes, and next actions, preserving claim lineage and semantic evidence across versioned persistence.

MCP server for persistent project knowledge management, enabling AI assistants to store, search, and reuse project analysis insights with freshness checking and impact analysis.

Self-hostable MCP server for WhisperGraph — a graph of 7.39B nodes / 39B edges mapping DNS, BGP, GeoIP, WHOIS, and threat intelligence. Six read-only tools (Cypher query + schema introspection + threat assessment), six resources, eight investigation prompts. stdio and Streamable HTTP transports.

Ratary is an AI Brain Platform — infrastructure that gives AI: Persistent memory — durable, owner-scoped, versioned Structured knowledge — metadata, relations, graph traversal Intelligent retrieval — hybrid search + bounded context assembly Protocol access — Ratary MCP, REST, optional gRPC It sits between AI clients and storage. One brain, many surfaces — Cursor, Claude Code, custom agents, enter

AutoMem MCP provides persistent memory for AI assistants, enabling them to recall information across conversations and platforms with graph-vector retrieval.

A self-improving knowledge agent that provides local retrieval, web research, and structured answer synthesis for Claude Code and VS Code Copilot via MCP. It enables AI tools to manage a project-specific knowledge lifecycle through automated research and indexing.

Enables deterministic, token-minimal multi-hop retrieval from a vault of [[wikilink]] notes via the Model Context Protocol, allowing LLMs to answer questions by following authored links without vector databases or LLM calls during retrieval.

Local-first memory for AI agents. On-device hybrid retrieval over a single SQLite file.

Governed memory for coding agents with trust lifecycle, conflict detection, staleness tracking, and health scoring. SQLite + FTS5, zero infrastructure. Works with Claude Code, Cursor, Codex, Windsurf.

MCP server that exposes Tencent IMA knowledge base capabilities, enabling RAG-based Q&A, file retrieval, note management, and web import through natural language.

Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP