"JSR" matching MCP servers:

Lets AI agents scaffold modern npm packages, CLIs, HTTP services, and apps as a native tool. Three tools: inspect the full option/preset schema, preview the generated file tree for a config, and write the project to disk.

MCP server for jar.tools' JAR security scanner. Enables AI agents to scan local .jar, .zip, or .class files for supply-chain risk without opening a browser.

MCP server for Tersign, the evidence layer for agent commerce, enabling agents to issue, verify, and manage signed receipts, compliance records, refunds, and disputes on a counter-signed hash-chained ledger.

MCP server for local speech-to-text using Whisper Large V3 (MLX), enabling audio transcription with text/timestamps/SRT output and LLM-based correction, all running offline on Apple Silicon.

Google Trends data: interest over time, by region, related queries, and trending now.

Send email through your own Amazon SES account, and check domain verification, the suppression list and sandbox status. Works with any SES account; Wraps adds send history and delivery events.

Code-mode MCP server (docs_search + execute_code two-tool surface) backed by a unified capability manifest across three sandbox kernels (in-process node:vm, WASM via QuickJS / Pyodide / Wasmtime, and remote microVM via E2B / Cloudflare Sandbox). At N=30 tools the bootstrap-context cost drops to 13.6% of direct tool-use. Apache-2.0.

MCP server that allows reading inside Java archives (classes, APIs, sources, resources, bytecode) without extraction, with focused tools to minimize context window noise.

Enables AI assistants to read-only explore OpenObserve: list streams, inspect schemas, and run bounded SQL searches over logs, metrics, and traces without write access.

Enables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials.

High-quality speech-to-text transcription using Zhipu AutoGLM ASR, supporting long audio chunking, context-aware modes, and timestamp segmentation.

Enables AI coding assistants to debug and analyze JavaScript code in web pages through breakpoint debugging, function hooking, network analysis, and runtime inspection of scripts including minified code.

This server enables agents to author fancy-flow workflows headlessly on a TypeScript host, with the same tools as the PHP version.

Queries Aurum design system components, tokens, icons, Figma node IDs, and changelog via LLM clients.

Enables MCP clients to securely access Jisr's documented HR Open API read-only operations, including employees, attendance, leave, payroll, finance, and discovery tools, with role-based field policies and dual protocol support.

An MCP server providing access to Sveriges Radio's P3 channel music playlists, including real-time tracks and historical data. It enables AI assistants to fetch current songs and search the last 90 days of playlist history by date or artist.

Generate and render PlantUML diagrams from natural language. A pure Node.js MCP server that creates, validates and explains UML diagrams (sequence, class, activity, state, component and more) as SVG — with zero Java and zero external server. Tools: render_diagram, check_syntax, explain_diagram. Just run npx @plantuml/mcp-js.

Analyzes JSX prop usage in React/TypeScript codebases using AST parsing, enabling prop usage tracking, component analysis, and TypeScript support.

Local speech-to-text transcription using Microsoft's VibeVoice-ASR model with speaker diarization, enabling audio transcription directly in AI tools like Claude Code, Cursor, and OpenCode.

Enables AI agents to manage inventory conversationally: list and look up products, check current stock levels, record inbound and outbound movements idempotently, review movement history, and surface items below their minimum threshold. Every figure is grounded in tool calls rather than model estimation, and invalid operations return explicit error codes the agent can reason about.