AI & ML MCP Servers

Live odds from 24 Kambi-powered sportsbooks in one call, with the best price per outcome.

AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.

OP tasks, your presets and the public workflow gallery, billed to your API key.

Calibrated probabilistic foresight for AI agents, powered by live prediction-market signal.

FAF Source of Truth for Gemini. Read project DNA from .faf files. Ecosystem: #2759

AI agent knowledge library — earn credits, query lessons, unlock books, and train for certs.

MCP Server that transforms ComfyUI workflows into AI-callable tools for MCP Host

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

24 keyless tools for AI agents on Vector, the Apex Fusion eUTXO L2: wallets, contracts, registry.

Validate GPTBot and OAI-SearchBot IP addresses. Remote MCP validate_ip tool.

Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data

OpenAI Ads MCP for ChatGPT Ads campaigns, creatives, audiences, insights, and conversions.

AI image, video and audio generation for agents: banners, reveal videos, avatars, voice cloning.

Structured, cited, real-world data from 300+ sources and the open web for your AI agents.

Learn a designer's repetitive command patterns and surface the next likely action, cutting the...

Dynamic RAG Engine preventing AI hallucinations in Korean Finance and Crypto markets.

AI inference pricing for agents: live and historical model prices, provider comparison.

The internet's infrastructure graph for AI agents - 46B nodes and edges, free trial via 2 HTTP calls

HAL (HTTP API Layer) - An MCP server that provides HTTP API capabilities to Large Language Models

Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.

Semantic code & doc search with keyword boost. AST code nav, auto HF mirror, local, privacy-first.

Free GeoNames MCP: countries, cities, POIs, distance & nearby. Remote HTTP + agent token signup.

AI-powered application security testing — scan APIs, discover endpoints, and find vulnerabilities.

Reads text aloud locally on Windows, macOS, and Linux. No API key, account, or cloud service.

Search and download academic papers from arXiv, PubMed, bioRxiv, medRxiv, Google Scholar, Semantic…

Codebase Q&A for Claude Code through Gemini's 1M-token window, with workspace scans and caching.

MCP server wrapping Gemini CLI: query, review, search, structured output, and diff assessment.

AI translation with multi-model consensus

Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.

Google Gemini Notebook (NotebookLM): notebooks, sources, cited chat, podcasts, video, slides

Neural Draft MCP — CMS, blog, bookings, galleries, commerce. 38 tools.

Premium agentic endpoint for carbon-aware-inference-router-mcp.

Clone any web page from a URL into a verified offline HTML copy, embed, or rebuild.

Ask Neural Partners' Chief of Staff about services, published pricing and booking a conversation.

IBM watsonx.ai MCP by three.ws: chat, text generation, embeddings, and tokenization.

Fetch current stock prices and key data for symbols across global markets. Look up companies like…

Google leads the Arena again; Anthropic trails by 22 points and OpenAI by 62. Query full.

Call your local Ollama or vLLM model over MCP with schema-validated JSON output

LangChain's share of weekly npm framework downloads fell from 32% to 19% in 46 weeks, while.

Anthropic's SDK went from 34% to 97% of the OpenAI SDK's weekly npm downloads in 46 weeks. It.

ChatGPT reports 900M weekly users (Feb 2026). Gemini reports 950M monthly (Jul 2026), 2.4× its.

OpenAI was the #1 lab on Arena for 95% of 2024. On 25 Sept 2026 it ranks 8th among labs, and.

Anthropic holds 8 of the Arena top 20, Google 7 and OpenAI 0. In Apr 2025 OpenAI held 9 and.

Since Jan 2024, Google's models have been #1 on Arena for 227 of 1003 days, third among labs.

Free experimental GPU tools: text generation, images and audio transcription. Shared quotas; no SLA.

On npm, Ollama's client fell from 27 to 6.6 downloads per 1,000 cloud lab SDK downloads in 46.

Qwen3.8-Max rates within 30 Arena points of Claude Opus 5.5 for 3.3× less per output token..