"MCP servers that work without API keys" matching MCP servers:

Manages persistent work memories and context across AI tools, enabling structured storage, search, and retrieval of work content, tasks, and knowledge with session-based project organization.

A local-first MCP server that lets AI assistants search and retrieve context from indexed projects, Git state, decisions, and tasks without sending data to the cloud.

Enables evidence-first, tenant-isolated knowledge management and business-scenario execution for Accio Work foreign trade, with honest unavailable responses when connectors or approvals are missing.

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.

MCP server exposing eight esoteric calculation systems (Western/Vedic astrology, Human Design, Gene Keys, and more) through 14 tools, with deterministic profiles, partial success, and OAuth integration.

Enables managing Zotero reference libraries with full CRUD operations, collections, notes, annotations, and attachments via the Zotero API.

Built-in MCP server that gives AI agents direct access to an Obsidian vault for reading, writing, searching notes, and executing commands.

AI assistant integration with Logseq knowledge graph: 21 tools to read, write, query, and search notes, enabling seamless interaction with your notes.

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.

Gives Claude persistent, local context about how you work, your weekly agenda, and shipped work, with automatic work logging and git integration—all stored privately on your machine.

Enables AI agents to read, create, update and delete any file in a mounted folder of markdown notes, patch individual headings, blocks or frontmatter keys, search by text or JsonLogic queries over frontmatter, tags and links, and stream note changes as events. Runs as a standalone container requiring no Obsidian installation and binds only to private networks such as Tailscale or WireGuard.

Enables LLM agents to query a bi-temporal property graph using verified temporal operators via MCP, with auditable claims and correction-aware time travel.

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.

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.

Japan Operations OS for AI agents — 14 knowledge domains covering regulations, protocols, calendar, travel, food culture, language, disaster safety, daily life, and persistent memory. 31 MCP tools via REST + Streamable HTTP.

Integrates with Red Hat APIs to enable searching Knowledge Centered Support (KCS) solutions, retrieving solution details, searching support cases, and obtaining case details through LLM applications.

Free, open MCP server for The Urantia Papers — full-text and semantic search across 197 papers, 14,500+ paragraphs, and 4,400+ named entities.

Self-hosted MCP gateway that connects productivity tools like Jira, Confluence, and Obsidian to AI assistants via a single endpoint.

Engram is a local-first memory server that lets AI agents remember things across sessions with zero cloud dependencies.

Provides a local, adaptive memory layer that lets AI agents persist and retrieve decisions, constraints, and lessons across sessions without requiring an LLM API key.