Browser Use
OFFICIAL SERVERLocal MCP server that drives a Chrome or Chromium browser step by step, with an agent fallback
MCP servers that reach other models and ML platforms: generate images or audio, run embeddings, call another agent.
81 servers, page 1 of 3.
Search capabilities in this directory
Local MCP server that drives a Chrome or Chromium browser step by step, with an agent fallback
Lets an assistant run an OmniRoute model gateway: routing combos, quotas, costs, cache, compression, memory
Lets an assistant search the web, read pages as markdown and run Exa research agents.
Lets an assistant list, run and trace the flows in a Genkit project and look up Genkit docs
Web search, quick answers, reasoning and long research runs from Perplexity's API
Read traces, sessions, datasets and experiments in Arize Phoenix and manage its prompts
Lets an assistant turn a goal into a fixed spec, run coding agents against it and verify the result
Agent swarms with shared vector memory and task routing for Claude Code and other MCP clients
Agent runner, ReasoningBank pattern memory, local code edits and graph solvers for coding assistants over MCP.
macOS screen capture, UI inspection and native click-and-type automation exposed over MCP
Task board, chat and approvals between people and coding agents, served to them over MCP
MCP interface to the Loki Mode coding agent: start runs, read their state and check signed receipts
Exposes the PraisonAI agent framework's agents, memory, knowledge and model tools over MCP
Builds a cited, interlinked wiki from your documents and serves evidence from it over local MCP
Gives an agent self-learning vector memory: store and search patterns, episodes, skills and causal links.
Control a ComfyUI install: build and run workflows, fetch models, manage nodes and VRAM
Turns paper text and data into academic methodology diagrams and statistical plots via image models
Self-hostable MCP gateway that puts agents, tool connections and model routing behind one endpoint
Image and video generation, visual edit workflows and prompt-gallery search on MeiGen
Generate, rig, texture and prepare 3D models for printing through the Meshy AI API
Read, write and vector-search data in a Redis database from an MCP client
Hardware-aware local model picks plus Ollama model management over MCP
Exposes a Bike4Mind account's notebooks, files, chat and audio generation to MCP clients
Runs multi-role AI workflows written in YAML and returns their combined deliverable
Hands prompts and large files from an MCP client to Google's Gemini CLI or Antigravity CLI
Self-hosted multi-agent orchestration API whose MCP endpoint hands tasks, memory and schedules to agents
Two-way spoken conversation with a coding agent through speech-to-text and text-to-speech
Twelve quick scoring tools backed by TypeSafe's Jev model, each returning typed probabilities
Lets an assistant build, validate, run and monitor RocketRide AI data pipelines and manage their deployments.
Compresses large tool outputs, logs and files for an assistant on request, keeping the originals retrievable