"Files formatted in JSON" matching MCP servers:

Create, validate, read, edit, export, and search JSON Canvas files with an interactive inline viewer, stored privately per user.

A personal memory engine and MCP server that stores durable facts in markdown files managed via git, enabling hybrid search (lexical + semantic) through an MCP interface for persistent context across LLM sessions.

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

MCP server for parsing, searching, and extracting branches from XMind mind map files, supporting Markdown/JSON output, token-aware formatting, and Claude Desktop integration.

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

A local-first MCP server that gives AI coding assistants persistent, structured, human-readable memory for a software project by storing project knowledge as Markdown files in the project's .dev-context-memory/ folder.

A lightweight Notion MCP server that minimizes token usage by returning Markdown instead of raw JSON, enabling efficient read/write operations on Notion pages.

Shared, code-grounded memory for developers and their coding agents. Capture a learning once and the whole team plus every agent recalls it; memory is grounded in your code and stored as git-tracked JSON reviewed in PRs, with citations validated on write and stale memory withheld from recall. Works with any MCP client.

An MCP server that reads all your Claude Code project memory files and exposes them as tools. Lets any Claude instance — in any project, or via Claude.ai — query your full project history and preferences.

Enables searching Google Scholar with Scholar operators, year ranges, cited-by and all-versions lookups, and retrieving citations in five styles with BibTeX and EndNote export links as structured JSON.

Give your AI persistent, structured memory and let humans see it too. It stores project knowledge as Markdown files in a hierarchical tree, accessible via MCP tools and a built-in Web UI.

Repository-native protocol and MCP server for coordinating work items, documentation, changelogs, and project memory between humans and AI agents, using Markdown files in a Git repository as the canonical data source.

Local-first structured project memory for AI coding agents. Keeps decisions, constraints, intent, and human reasoning in readable sidecars beside project files; requires the free Wuniq desktop app.

Provides shared real-time context for Claude Code agents, including scope awareness, prior decisions, and anti-overlap, using only files in the repo.

Provides AI coding assistants persistent engineering memory stored as Markdown files in an Obsidian vault, enabling project context retrieval, session capture, decision recording, and memory search without requiring Obsidian to be running.

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

Enables AI agents to store and retrieve project context, bugs, decisions, and session logs by reading and appending markdown files in a local Obsidian vault, without requiring any cloud services.

A local memory layer for AI coding tools that stores user preferences, lessons, and project context as local files, exposed via MCP so different AI tools can share the same understanding of you.

Provides AI agents with persistent, long-term memory via OKF-formatted markdown and SQLite indexing, enabling stateful storage, retrieval, and search across sessions.

Persistent memory for AI agents through the Model Context Protocol. MemStack provides tools to store, retrieve, summarize, prune, export, and manage memories using local files, SQLite, Postgres, Redis, or in-memory storage.