"Ajv" matching MCP servers:

Enables validating JSON/JSONC, getting/setting values with jq-like paths, pretty-printing or minifying, validating against Ajv JSON Schema, and diffing local files or inline strings without network calls.

Enables agents that cannot accept image input to read a running Android app's UI as text — dumping the accessibility/semantics tree, auditing tap targets and overlaps, and rendering pixels as glyphs — and to drive it by tapping elements resolved from their labels. Works without a hosted vision API, using adb against a connected device.

Enables offline King James Version Bible lookup, passage retrieval, word and phrase search, deterministic verse-of-the-day access, and book/chapter listing for AI assistants. All tools are read-only and return citable references with structured JSON.

Enables a Chief of Staff client to find Codex tasks, create and submit project work with exact prompts, track progress via durable receipts, and continue or manage the same conversation locally.

Enables MCP clients to read WhatsApp chats and send, reply, react to, and schedule messages on the WhatsApp Desktop already logged in locally. All traffic stays on 127.0.0.1, with human-like pacing and verified delivery rather than cloud APIs or QR logins.

Enables any MCP-capable AI client to drive the user's own Chrome or Edge browser through a set of browse_* tools — navigating, clicking, typing, extracting, and managing tabs with their existing logins on their own machine. Runs locally and self-hosted with a live viewport and pause/approve controls so every verified step stays under user watch.

Provides AI agents with production-ready integrations for GitHub repository management, sandboxed code execution, SFTP file operations, web search and scraping, YouTube, Google Workspace, Notion, and more.