"The most widely used models" matching MCP servers:

Enables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.

Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.

Enables agents to trace any Hugging Face model's ancestry and descendants, find the most finetuned base models, and explore whole model families. It exposes tools for lineage, children, leaderboards, family views, and model search, answering from nightly-rebuilt index data.

MCP server that lists available GitHub Models and compares responses from multiple models for the same prompt.

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.

Enables AI agents to list, compare, and estimate exact costs for image, video, audio, and 3D generation models, including per-image, per-second, and per-run pricing with recoverable errors.

Enables exact Claude API cost estimation from token counts with correct prompt-cache economics, plus cache break-even analysis showing whether and at which TTL reusing a prefix pays off. It also scans source code for tiktoken-based token counting used alongside Claude models and points to the correct fix.

Enables text-only language models to understand images by forwarding image and prompt requests to vision model backends via MCP, returning descriptive text. Supports multiple OpenAI-compatible providers with task routing and safety checks.

Nectar is a stdio MCP server for Pollinations image and video generation. It gives MCP clients a small, focused toolset for generating images, editing images, generating videos, listing available image/video models, and checking pollen balance.

Enables MCP clients to run 600+ generative AI models from fal.ai, including image, video, audio, and text, with tools for synchronous and asynchronous execution, model catalog browsing, and schema inspection.

Hardened MCP bridge to the full Ollama ecosystem — local and cloud models. 6 tools covering health, model management, chat, and generation with SSRF mitigation, singleton HTTP client, and structured error handling. Two deps, one file.

OrcaRouter MCP — browse 160+ LLM models with live pricing (no API key needed for catalog) and route chat completions through the OrcaRouter gateway with automatic fallback.

An MCP server that gives text-only models image generation and understanding capabilities, with tools like generate_image, describe_image, and set_api_key. It enables any MCP client to create and analyze images using a single API key.

Provides local, deterministic scoring and detailed auditing of text for AI-writing patterns via two read-only tools, with no network calls or language models.

Lets Claude Code delegate coding tasks to external models running on a local opencode serve, preserving main agent tokens for planning and review.

An MCP server that turns the Hugging Face Hub into a conversational model picker with a tool-use eval harness to prove the agent actually uses it correctly.

An MCP server providing access to 554+ generative AI models with spend safety guardrails, enabling text-to-image, image-to-video, and more through a simple 4-call workflow.

Official MCP server for the Perplexity API Platform, enabling AI assistants to perform real-time web search, reasoning, and deep research using Sonar models.

Official MCP server for Perplexity API Platform, enabling AI assistants with real-time web search, reasoning, and research capabilities through Sonar models and the Search API.

MCP server that converts file contents into compact, line-numbered PNG images for vision models to read, reducing token usage by roughly 7x for large files.

Enables Claude to generate and edit images using OpenAI's GPT Image models, with automatic model selection and local file saving.

Tells an agent what went wrong with its own Ollama calls, in sentences with the fix: lost prompt cache and where the prompt stopped matching, context overflow, a model running partly on CPU, tool schemas crowding the prompt. Also the last turn in numbers and which local models fit in video memory. Local, read-only, nothing leaves the machine.

Enables using DeepSeek models as a small, cheap supervised worker from any MCP-compatible client, providing fast flash and deep reasoning tools for bounded tasks.

Christian Bible Scripture MCP: BSB verse lookup, Christian encouragement, the Doxa Way journey map. Three tools: doxa_encourage, doxa_scripture, doxa_way_movement. Hosted at https://doxa.app/mcp/v1, free per-individual quota, BYOL for unlimited. Scripture, summoned.

Enables MCP clients to generate images and iteratively edit them using OpenAI's gpt-image-2 models, with session management, background job polling, and local file saving.

Enables LLMs to see clipboard screenshots without saving files, using free Grok visual models, and integrates seamlessly with Command Code, Cursor, Claude, and other coding agents.

An MCP server that seats multiple LLMs as a council, letting your assistant query them in parallel or in sequence, relay answers for cross-critique, and merge conclusions within one conversation.

Adds a deep_reasoning tool that consults stronger reasoning models (e.g., DeepSeek R1) to produce full reasoning traces for complex problems, helping the agent shape and cross-check its answers.

Enables users to perform deterministic time series forecasting through Claude by running reproducible Python statistical and foundation models, providing tools for loading data, cross-validation, forecasting, anomaly detection, and exporting re-runnable manifests without any LLM involvement.

Real human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.