"A browser" matching MCP servers:

Enables browser automation (navigation, screenshots, clicking, typing) and AI image generation using Puppeteer and Google Gemini.

Enables coding agents to add a bounded semantic-judgment layer for routing, ranking, extraction, verification, and escalation, returning typed signals and review recommendations.

MCP server for hybrid medical consultation integrating Western and Traditional Chinese Medicine, enabling symptom analysis, diagnosis, and treatment suggestions through two specialized models.

Lets an MCP client drive a real Playwright browser by describing desired outcomes one step at a time, while a Typesafe System One model picks elements, actions, and values and flags done, blocked, error, or irreversible states. It also exposes snapshotting, reading, checking, screenshots, direct acting, and page-registered WebMCP tools for taking manual control.

A browser-automation MCP server that lets a calling LLM state one desired outcome at a time while a separate model decides the element, action, value, and completion status per round, enabling navigation, form filling, verification questions, page reading, and invocation of WebMCP tools a site registers.

A local, fully vectorized computational engine for stock market analysis that enables AI to perform factor calculation, strategy backtesting, IC analysis, and GPU-based multi-dimensional visualization using local DuckDB data.

Dynamic multi-agent debate MCP server for structured argumentation and reasoning among AI agents.

Five-layer agent memory over MCP. zenbrain_store routes each memory: steps to a procedure, emotional weight to an episode, high confidence to a pinned core memory, the rest to a semantic fact. zenbrain_recall returns results with id and layer; zenbrain_forget deletes one plus what consolidation linked to it; zenbrain_consolidate runs one sleep-like pass. Local SQLite, no account, no network call.

Provides AI assistants with real-time web search, reasoning, and research capabilities through Perplexity's Agent API and Search API, enabling tools for search, conversational Q&A, deep research, and advanced reasoning.

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.

Enables AI agents to access Cloudflare Workers AI for serverless LLM chat completions, text embeddings, and image generation via MCP tools.

Enables Claude Code to delegate web research and image generation to ChatGPT via Playwright browser automation, allowing token-efficient search and visual design iteration without manual screenshots.

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.

Bazi (Four Pillars) charting MCP server with true solar time correction and multilingual output in Chinese, English, Japanese, and Korean.

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.

Exposes OpenAI's gpt-image-2 (image generation and editing) as an MCP server for tools like generate_image, edit_image, and iterative edit sessions.

Cybersecurity AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

Connect AI agents to Jev AI (jev-ai.pro) for classification, scoring, yes/no checks, advisory action assessment, batched typed decisions and saved judges. Returns structured answers and probabilities using your Jev AI API key.

Furl folds repeated tool output into a hash-addressed marker, keeps the line that matters, and returns any original byte-exact the moment the agent asks for it. No summary. No guessing. Nothing thrown away.

Two self-hosted MCP servers: manage a local model machine (Ollama pull/switch, LoRA training) and bridge to local Ollama/vLLM for pure language processing tasks (writing, summarizing, classifying, extraction) without giving the calling agent tools or file access.