"The most widely used models" matching MCP servers:

Manages and dispatches multiple MCP servers from a cloud dashboard, reducing tool-context bloat by loading only the most relevant servers for a given task.

Enables AI assistants to search read-only used-car listings from Encar, Che168, Copart, and IAAI across South Korea, China, and US auctions, returning structured JSON for queries, vehicle details, price changes, brands, models, and market metadata. It runs locally over stdio and calls the apiauto.space API with quota-aware, security-filtered results.

Enables AI assistants to manage events, venues, organizers, and tickets on WordPress sites via CRUD operations.

Crash-test AI agents on real professional decisions. Agents take real tariff classification and patent examination cases, search reference libraries and rulebooks, submit a decision, and get an exact score with a receipt against what the professional actually decided. Most cases were decided after current models were trained.

Waterfall lead enrichment for AI agents. Cascades through Apollo, Clearbit, and Hunter to build the most complete lead profile in a single call.

Just to be clear about the final JSON: the MCP server is named herdr-inbox, and it enables Claude Code agents in herdr to ask questions asynchronously without stalling, with all open questions answered from one popup and answers routed back to the asking agent.

An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Connects MCP clients to a local social engine that reads bounded posts, comments, replies, and feeds into local inboxes, turns source material into drafts and briefs, and publishes exact frozen jobs with recorded provider IDs and receipts across Instagram, Threads, and Substack.

Enables AI assistants to check daily-verified AI model and agent prices, estimate monthly costs for preset or custom workloads, compare models side by side, and find the cheapest options.

Enterprise-grade code intelligence server for AI assistants that analyzes codebases for due diligence, tech debt, security vulnerabilities, and code quality.

Provides AI agents with a toolset to query model inventories, trace dependencies, and analyze the impact of changes across machine learning models and data pipelines.

A proxy MCP server that aggregates tools from multiple MCP servers and forwards calls to the appropriate server, used with the Metatool App for GUI tool management.

A local stdio MCP server that enables researchers to practice explaining their work outside a conference setting through a guided, one-question-at-a-time interview about their research, its audience, its consequences, and a concrete next step. It stores the saved answers in a local SQLite draft and returns an approximate rubric-based grade, without calling any model or requiring an API key.

Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.

Enables language models to receive external randomness so the same prompt can produce different answers while still following the user's request.

Enables processing PDFs via Aryn's API, typically used with a filesystem MCP server for file management.

Enables MCP-compatible assistants to connect to a user's workspace, read across boards, notes, checklists, habits, money, meals, chores, and chat, and make scoped additions, changes, or removals with attribution.

Enables AI agents and MCP clients to dispatch queries to the most suitable model among 70+ LLMs by scoring intent, budget, cost, and latency, returning structured routing decisions with execution telemetry. It runs as a zero-dependency Python MCP server that plugs into Claude Desktop, Cursor, and other MCP-compatible clients.

A read-only MCP server providing curated Qdrant documentation for LLMs, enabling retrieval of the latest and most accurate documentation.

Enables AI agents and MCP clients to estimate VRAM footprint and tensor parallelization requirements for quantized llama.cpp models, returning structured outputs without external dependencies.

World Weather Online MCP Server gives AI agents direct access to one of the world's most comprehensive weather APIs — trusted by 300,000+ developers and used by major airlines and airports worldwide. Tools available: * get_weather — current conditions and up to 14-day hourly forecasts for any city, postcode, or lat/lon * get_historical_weather — past weather data from July 2008 onwards, up to 30-

Enables dynamic, intent- and budget-aware routing of queries across 70+ LLMs by balancing cost and latency through Pareto-optimal model selection. Integrates with MCP clients like Claude Desktop and Cursor for automated multi-model execution.

Enables autonomous agents and MCP-compatible clients to enforce policy-approved actions using risk tiers, reversible checkpoints, and token approval bounds.

A locally runnable stdio MCP server for Fortrip hotel search, live room rates, hotel details, trip planning and booking payment links. Uses a Fortrip CLI token or saved CLI login; payments are completed by the user on Fortrip and Stripe.

Plori runs AI agents in Workspaces. A Workspace is a project folder in the cloud. Several agents can work in it at the same time, each on its own copy of the files, and Plori merges their work back into the folder. Every version of the files is kept.

Enables AI clients to transcribe YouTube links and uploaded audio or video files, then retrieve the resulting transcripts as text, SRT, VTT, or JSON with timestamps and optional speaker labels. Also supports paging through long transcripts, checking upload progress, listing or deleting jobs, and viewing remaining account minutes.

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.

Checks live x402 routes across Base, Solana, and Algorand before agents spend. $0.003 USDC settles only for a valid live eligible route; normal typed misses are not settled. Free preview and validate tools. Seller payment is separate; the agent keeps its wallet. Optional signed route-binding receipts support buyer-side checks.

Enables agents to fuzzy-screen person and company names against the OFAC SDN/Consolidated, EU, UK and UN sanctions lists downloaded fresh from official sources, returning potential-match statuses, 0–100 scores and listing details via a billed screening tool, plus a free local tool that lists covered sources, score scale and disclaimer.