"Accessing the OpenAI API" matching MCP servers:

A tiny MCP server that wraps Perseus Vault to provide persistent, encrypted, local-first memory for OpenAI Codex agents, enabling them to remember project conventions, decisions, and context across sessions.

Connects AI assistants to Tacit building digital twins to query buildings, equipment, sensors, and zones using natural language. It provides tools for exploring Brick-compliant knowledge graphs, fetching historical sensor data, and accessing site documents.

Universal Git-powered persistent memory, context rules & native MCP server for AI coding agents. Prevents context amnesia with stateful workflows, Git Notes, and cross-model review gates across Claude, OpenAI, Gemini & DeepSeek in Cursor, Claude Code & VS Code.

MemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, updating, and scheduling these memories.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Provides a local-first, provenance-aware memory layer that enables MCP-capable AIs to store, recall, validate, and reason over facts with contradiction detection, trust weighting, deduplication, and encryption, supporting offline private operation without GPUs or API keys.

An MCP server that provides long-term memory and semantic search using Qdrant and OpenAI embeddings, with tools for storing, searching, and managing knowledge.

Provides AI-driven project memory management through structured prompts that help Claude parse tasks from specs, review code changes, sync with commit history, and maintain project documentation without directly accessing files.

Connects AI assistants to IT Glue, the MSP documentation platform. Browse organizations, read and write documents and flexible assets, and answer natural-language questions via semantic vector search (OpenAI/Azure embeddings). Viewer/editor/admin roles gate tool access; bring-your-own-key applies IT Glue's native permissions. Runs over stdio or HTTP; Docker image available.

Provides a compressed knowledge graph of the NVIDIA AI developer stack for deterministic traversal, enabling agents to answer questions about dependencies and prerequisites with minimal tokens.

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

Enables searching and accessing Readwise highlights and documents through HTTP endpoints using the Model Context Protocol. Provides vector and full-text search capabilities with streaming responses for retrieving reading highlights and notes.

Intelligent knowledge base system that enables users to process documents in 25+ formats, perform semantic search and Q\&A through vector retrieval. Supports multiple AI models including OpenAI and DouBao with local processing capabilities.

Provides persistent session memory for AI assistants, enabling them to store, search, and retrieve conversation summaries across sessions via the Model Context Protocol.

A research assistant server that enables saving, organizing, and retrieving research content with semantic search using ChromaDB and OpenAI embeddings.

A personal digital twin MCP server that manages professional context, including skills, experience, and project learnings. It allows AI assistants to retrieve and update user preferences and career interests across different development environments.

An MCP server implementation that enables interaction with the Letta API for managing agents, memory blocks, and tools in the Letta system.

A server that enables AI agents to perform sophisticated knowledge discovery and analysis across Obsidian vaults through the Local REST API plugin, supporting complex multi-step workflows with advanced filtering and full content retrieval.

Enables AI agents to use Obsidian vaults as persistent, bidirectional knowledge workspaces with wikilink/backlink resolution, structured frontmatter/tag indexing, task aggregation, and Obsidian Headless Sync.

Provides OpenCode with adaptive long-term memory by storing preferences, lessons, and usage history locally in SQLite, enabling AI to remember and adapt to users through context-based learning.

Enables querying a compressed knowledge graph of the NVIDIA AI developer stack, allowing users to traverse declared dependencies, prerequisites, and relationships across 20 domains via read-only MCP tools like query_ckg, get_prerequisites, and search_concepts.

A stateless MCP server that gives AI agents team-shared lore including area context documents, session captures, and structured docs (ADRs, logs, TODOs, plans) via the lore-api GraphQL endpoint.

An MCP server for managing work logs, research results, and task checkpoints to enable seamless collaboration and state recovery between AI agents. It provides a persistent memory layer for tracking project history and resuming workflows across different sessions or tools.

MCP server that enables AI assistants to interact with the MemOS API, providing memory search, feedback management, and knowledge base operations via MCP-compliant tools.

Unofficial Notion MCP server built on Notion's private API (token_v2 cookie). Gives LLM agents full read/write access to the entire workspace — no integration token and no per-page sharing.

Enables AI agents, including Claude, to interact with the AETERNA persistent world, leaving traces, sharing knowledge, and accessing world state and token economy.

Enables AI agents to query and interact with Google NotebookLM notebooks to retrieve citation-backed information. It provides tools for listing notebooks, accessing source data, and asking natural language questions.

Provides a centralized MCP-based system for managing and accessing multi-project memory banks remotely, with features like project isolation, file structure validation, and type-safe operations.

Transforms YouTube into a queryable knowledge source with search, video details, transcript analysis, and AI-powered tools for summaries, learning paths, and knowledge graphs. Features quota-aware API access with caching and optional OpenAI/Anthropic integration for advanced content analysis.

Enables MCP-compatible AI clients to connect to a self-hosted DeepTutor instance for accessing learning data, study tools, practice workflows, knowledge retrieval, and learning-state management.