"All items" matching MCP servers:

17 decision intelligence algorithms as MCP tools for AI agents. Bandits (UCB1, Thompson), LP/MIP solver (HiGHS), Monte Carlo simulation, Bayesian inference, graph analytics (PageRank, Louvain), genetic algorithms, CMA-ES, anomaly detection, time series forecasting, and more. All under 25ms, deterministic, zero LLM cost.

Stop hallucinating numbers. An MCP server that runs every math expression through four independent numeric engines in parallel and returns all four results side by side — so when they disagree, you know the answer is numerically unreliable.

Enables MCP clients like Claude Desktop to query DEXUN AdWhiz for ad account lists, AI recommendations, savings summaries, recent activity, and API quota, all read-only.

Hosted multi-model AI media + chat MCP server. Generates images, video, audio, face-swaps and talking-avatars, and chats across 300+ models (Claude, GPT, Gemini, DeepSeek…) - all from one balance and one API key.

Enables coding agents to submit their original request, proposed plan items, and observed repository conventions for per-item necessity scoring before making edits. It returns advisory keep, simplify, or review recommendations with reasons and evidence, without blocking or modifying the plan.

Agent-readable feed of AI and agent tech news (framework releases, security advisories, compliance deadlines, classified hourly) and upcoming live events. Read anonymously; post items with a free API key.

Enables Claude to drive Google Flow end-to-end: batch video generation on Veo 3 / Omni 1.1, scene chaining, keyframe transitions, video-to-video edits, and automatic downloads, all through a local bridge with the OmniFlow Chrome extension.

Enables validation of clinical notes in SOAP format, checking required fields and semantic coherence using a local LLM, all processed locally with no data leaving the machine.

MCP server for tinify.ai image optimization. AI-powered upscaling, resizing/cropping, compression, and SEO filename & alt text generation — all in one tool.

Lets MCP clients such as Claude Code, Codex, Cursor, and VS Code drive the Grok Bot desktop app on macOS by listing the user's bots, reading their chats, sending them messages, and answering their multiple-choice questions locally without API keys. All actions run live in the real app via the macOS Accessibility API, with no network calls, telemetry, or dependencies.

Enables AI agents to perform detailed local image analysis, including pixel-level queries, cropping, grid coordinates, comparisons, and zero-shot classification, all without cloud APIs, keys, or payments.

Enables AI-assisted aquaculture manuscript writing through six specialized agents for literature review, drafting, results, abstract, copyediting, and integrity checks, all accessible from MCP-compatible chat clients.

Enables agents to verify claims against cited evidence, screen content for prompt injection and relevance before reading it, and rank candidates by meaning, all with calibrated probability verdicts.

Enables agents to resolve ambiguous decisions by returning calibrated probabilities for each candidate action, along with a gate that signals whether to act on the top option or escalate, all via a cheap local or remote backend.

160 tools that do that heavy lifting - storage, agent-to-agent collaboration, document conversions, identity verification -- almost all priced under a tenth of a cent or less per call.

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.

Enables Codex and Claude Code to send a self-contained task to an existing Grok Bot, read incremental replies, and interrupt the bot’s current turn while preserving its existing conversation, memory, and connected tools.

Enables engineers to estimate LLM costs, check GPU VRAM fit, audit MCP configs for security risks, and analyze network device config changes and compliance—all locally, with no account or telemetry.

An MCP server that lets you schedule AI phone calls and manage Leximo assignments directly from Claude Desktop or Claude Code.

A lightweight, zero-dependency Python MCP server that exposes a single do_everything tool. Any AI agent that supports MCP can use it to offload all language-model work to a local OpenAI-compatible endpoint, reducing cost on the agent's primary LLM.

Give your AI agent PDF summarization, code review, translation, web extraction, document comparison, and persistent memory — all paid autonomously via Bitcoin Lightning.

Provides access to 227+ expert-crafted Fabric AI patterns for tasks like summarizing, analyzing, and extracting wisdom, all through Claude Desktop with no API keys needed.

MCP server that forges pixel art sprites & game assets using Google Gemini — generate, crop, split & process, all from your AI assistant.

It enables users to search public prompt libraries for complete prompts with example images and source links, list model names and official prices, and request text-model optimization when a search has no match or a rewrite is explicitly requested, all without an account or API key.

Runtime quality validation for AI agent outputs. Detect hallucinations, enforce scope compliance, and score output quality — all via MCP.

Enables local LLM chat sessions to continue indefinitely by automatically compacting context and storing permanent memory on disk, with recall across all past sessions.

MCP server + Claude Code plugin for ComfyUI — execute workflows, generate images, visualize pipelines, manage models, control VRAM, and explore custom nodes, all from your AI coding assistant.

A local, auditable multi-model workflow engine that lets you define YAML graphs for orchestrating LLM agents across vendors, with MCP tools for validation, dry-runs, execution, and human approval, all fully observable in a local web interface.

Reads the Claude Code, Codex and OpenCode usage logs already on your machine and reports token totals, per-day and per-hour activity, a per-agent and per-model breakdown, and a year-in-review recap. It makes no network request at all — a test fails if any source file in the package can open a socket.

Connects Speak AI transcription and insight data to Claude and ChatGPT, enabling natural language queries for summaries, action items, and quotes from recordings.