"JSON Web Tokens" matching MCP servers:

Connect AI assistants to your Gramps Web family tree. Search and edit genealogy records, explore ancestors, descendants, relationships and timelines, and read document scans with vision-capable models. Includes guided research workflows, source citations, read-only mode, and privacy-aware media previews. Install with Docker or a Claude Desktop bundle.

Connects to SlimSnap to provide recent screen captures as structured JSON data (text and annotations) for AI to read, avoiding screenshot limitations.

AI agent knowledge marketplace where agents share solutions and earn tokens. Search, publish, and unlock previously solved problems to reduce token usage and computational costs.

Structural memory for coding agents — 60% fewer tokens, refactor-safe, runs entirely on your machine.

Local-only MCP server for saving and restoring conversation context across AI agent sessions using JSON files on disk.

An MCP server for Capacities API 2.0 that enables AI agents to discover, create, read, update, and delete objects, blocks, and daily notes with structured JSON or Markdown, using personal API tokens.

Shared research cache for AI agents. Caches web research across sessions and users - hit means instant answer from verified sources, miss means your research saves the next dev's tokens. Semantic search with freshness tracking, gap detection, and real-time token measurement via JSONL. Free, open source.

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.

Persistent memory server for MCP clients that stores structured facts as JSON across sessions, enabling atomic add, remove, replace, and view operations.

Salesforce AgentForce as a traversable MCP knowledge graph. 40 nodes covering Einstein Trust Layer, Agent Topics, Actions, Data Cloud, and Resolution Criteria. 11x fewer tokens than RAG. Free: uvx ckg-agentforce

Persistent memory MCP server that allows Claude to store, organize, and retrieve knowledge across sessions without consuming context window tokens.

Enables an AI assistant to load, query and edit a YAML or JSON graph file, with tools for adding, editing and removing nodes and edges, managing reusable styles and graph-level properties, and saving changes. Every change is written to the file immediately, so the same graph can be viewed and edited live in the companion web app.

Refines development prompts and stores semantic memory to save tokens in complex Antigravity tasks, enabling token savings and enriched context.

A design knowledge MCP server that Claude can query when generating UI, covering eight layers: principles, patterns, content design systems, research methods, service design, brand/visual, business strategy, and design tokens.

Compresses context for AI agents by storing memories in compact markdown files with FTS5 search, enabling fast retrieval of relevant information while saving tokens.

A Model Context Protocol server that enables Claude to persistently store, search, and manage text memories with tags in a local JSON file.

Enables AI tools to query context from a local JSON data source via stdio, demonstrating the Model Context Protocol.

Provides owner-bound secure storage and retrieval of tool outputs via MCP tools, enabling trusted persistence for agents like Claude Code, Codex CLI, and OpenCode.

Cross-tool AI memory MCP server for Claude Code, Cursor, Antigravity, Windsurf, and every MCP-compatible AI. 400 tokens not 4,000.

A Model Context Protocol server that provides persistent storage, categorization, and retrieval of bookmarks through AI clients like Claude. It allows users to manage web links using custom categories and includes options for local JSON storage or AWS S3 synchronization.