"Using npx to run tools directly without requiring an API" matching MCP servers:

Enables agents to discover, evaluate, and serve task-specialist models (embeddings, reranking, classification, extraction) with OpenAI-compatible endpoints and MCP tools for routing, embedding, reranking, and extraction.

An MCP server that connects AI assistants to YNAB budgets, enabling natural language queries about finances backed by full API coverage and built-in YNAB methodology knowledge.

Provides five safe tools (calc, search, model_drift, compare_runs, grade_answer) for arithmetic, keyword search, model drift monitoring, eval comparison, and answer grading against sources, all implemented directly from the MCP spec with zero dependencies.

AI-powered MCP server for file renaming, organization, and PDF splitting using natural language prompts and content analysis.

Routes one brief to the right image model across 60+ (gpt-image-1.5, Ideogram 3, Recraft V4, Flux), validates the output, and fans out to iOS/Android/PWA/favicon/visionOS/Flutter bundles. Works without an API key via Pollinations, HF Inference, Stable Horde, or host-LLM inline SVG.

Full-stack utility API with 337+ tools including AI chat, web scraping, weather, finance, SEO, crypto, colors, readability, DNS, and more — all through a single MCP server. Pay-as-you-go credits, no API keys needed.

An MCP server that translates natural-language queries into structured catalog searches using Amazon Bedrock, enabling MCP clients to query existing in-house APIs.

MCP server for personal knowledge management providing AI-powered tools for semantic search, audio transcription, image generation, and PPT creation.

Enables natural-language interaction with Ladybug Tools for building performance simulation, 3D modeling, and data visualization, allowing agents to perform complex environmental analysis tasks without CAD software.

Enables document Q&A with grounded citations using the official Gemini File Search API. Upload documents, create stores, and ask questions that return exact passage citations.

Enables coding agents to access Alibaba Cloud Model Studio's built-in web search, web extraction, Python code interpretation, reverse image search, and text-to-image search through the Responses API using Token Plan or pay-as-you-go keys.

Wraps a set of cloud OpenAPI capabilities — text-to-image generation, streaming speech synthesis, audio file transcription with timestamps and speaker labels, object-storage upload with presigned download URLs, and web/image search — as standardized MCP tools. This lets MCP-capable AI clients such as Claude Code, Cursor, and Cline invoke these services directly through natural language, with per-tool credential configuration.

Enables automatic collection and AI analysis of Slack messages to create organized Notion pages, supporting custom analysis directions like meeting minutes, issue extraction, and topic classification.

Turns an OpenAPI spec into a ready-to-run test harness with local LLM agents: WireMock stubs, contract tests, robustness probes, and chaos scenarios you can switch on and off in a running WireMock.

Enables AI coding clients to generate and save project-aware images and videos using existing paid AI subscriptions, without API keys or passwords, and to optimize media for the web.

Enables agents to call paid utilities for DNS/SSL checks, site status, summarization, keyphrase extraction, decision advice, data cleanup, claim verification, and grounding via per-call USDC payments over x402, with free discovery tools and no signup or API key.

A lightweight MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI - saving context window and tokens for what matters.

Enables interaction with the Move AI UGC GraphQL API for markerless motion capture, allowing users to upload footage, create takes, run single- and multi-camera processing jobs, monitor progress, and download output files.

Local MCP server that connects VS Code agents like Cline to OpenAI and provides workspace file tools (read, write, list) with restricted file access.

一个MCP视觉分析工具，将本地图片交给豆包视觉模型分析，帮助Claude Code和DeepSeek理解截图内容。

Provides deployable, stateless MCP services for rigorous inference evaluation and benchmarking, including a profiled lm-evaluation-harness controller/worker and a bounded vLLM forward-pass benchmark adapter.

Offers 29 free tools for text processing, AI-powered generation, SEO optimization, utilities, cron tasks, file processing, and ideas management, all without requiring an API key.

Turn any API into an MCP server. Query in English. Get results—even when the API can't.

Enables image and video generation using Luma's API, supporting multiple models, aspect ratios, and advanced features like keyframes and style references.

Enables clients to generate images, videos, music, and voiceovers across supported models by API ID, monitor long-running tasks, and install agent skills over one hosted connection, with USD quotes and approval before paid calls.

Enables MCP clients to count tokens and estimate costs, run BM25 search, compare model evaluations with paired bootstrap and McNemar tests, validate JSON Schema output, and scan for prompt injection and PII.

Local MCP servers that give Claude Code access to other tools mid-session.

MCP server that translates natural-language questions into SQL, validates every query structurally, and executes approved read-only queries against a SQLite database, returning results and rejections.

Enables forwarding Douyin or Bilibili video shares to Kimi for AI analysis and automatically writing the resulting Chinese notes into an Obsidian vault.

Enables coding agents to generate AI images directly through MCP tools, handling payment via the x402 protocol with USDC on Base and no API keys.

A collection of miscellaneous tools for Claude, Cursor, and MCP-compatible clients. Includes OCR (Optical Character Recognition) capabilities leveraging the Google Gemini API.

MCP server that provides file operations and Moonshot API-powered tools (reasoning, code review, testing, research, web search, agent) for Kimi K2.5, requiring only a Moonshot API key.

Enables image recognition using vision models via OpenAI-compatible APIs, supporting multiple platforms like OpenAI, DeepSeek, and Ollama.

Provides a collection of MCP servers for computational chemistry tasks including molecular generation and retrosynthesis. Also offers property prediction and molecule pricing capabilities.

Turns a single image of an object into a textured 3D model (GLB with web-ready copy and six-view previews) on your own NVIDIA GPU, returning the written files and a preview. Runs locally as an MCP tool or, optionally, offloads the job to hosted GPUs with an API key.

An MCP server that lets Claude query Google's Gemini CLI as a sub-agent. Get second opinions, verify information, and cross-reference answers between AI models.

An MCP server for generating and editing images using Google Gemini Imagen via Vertex AI. Supports multiple resolutions and aspect ratios.

Enables room agents to generate or edit images (published directly into the room's Docs rather than passed through the model's context) and transcribe audio attachments, using the deployment's media providers with the room itself acting as the credential.

Provides 63 production-ready API tools for AI agents, including web scraping, AI generation, crypto data, OCR, image generation, audio transcription, text-to-speech, email, and domain lookup.

Free Industry 4.0 / IIoT tools, no API key or account: lint MQTT Sparkplug B topics, check a Unified Namespace (UNS) for naming and hierarchy problems, and run an industrial AI-readiness diagnostic for manufacturing digital transformation and smart-factory projects. Works in Claude Code, Codex and any MCP client.