Local Grounding MCP
Related Servers
Alternatives to Local Grounding MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to inspect images and screenshots locally over MCP, returning measured OCR text with pixel coordinates, geometry, per-element colours and contrast, spatial relationships, and version diffs without sending images off the machine.433 PyPIApache 2.0
- AlicenseNot gradedqualityCmaintenanceLocal vision-capable MCP server that lets AI agents describe screenshots, UI, charts, and photos via vision and OCR tools, with support for multiple providers and automatic fallback.5MIT
- AlicenseAqualityDmaintenanceAn MCP server providing AI agents with a stealth Chromium browser that uses hybrid accessibility-object-model and set-of-mark vision for token-lean snapshots and reliable action via ref ids.1373 npm2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceMCP server that gives Claude and other clients vision capabilities including screenshot-to-code, OCR, error diagnosis, diagram analysis, data-viz insights, UI diff checks, and video analysis via any OpenAI-compatible vision endpoint.Apache 2.0
- AlicenseAqualityCmaintenanceMCP server that provides vision capabilities to coding agents, enabling them to analyze screenshots, UI mockups, terminal errors, documents, tables, and charts through OpenAI-compatible vision models. Supports local stdio and remote HTTP deployments with structured JSON output and binary upload side channels.845 npmMIT
- AlicenseBqualityCmaintenanceZero-dependency MCP server that lets an AI agent drive the system's own Chrome or Edge over the DevTools Protocol — auto-detecting and sandboxing the browser, then taking full-viewport or pixel-perfect CSS-selector-clipped screenshots, filling React/Vue controlled form fields, clicking, and inspecting element bounds. It also reports on-page geometry and visibility so agents can verify visual layout and catch UI regressions.3Apache 2.0
TDQS
Scored across 4 tools
Each tool targets a clearly distinct operation: status inspection, model lifecycle, the core visual localization action, and screenshot housekeeping. There is no meaningful overlap between any pair of tools.
Three tools follow a verb_noun pattern (load_grounding_model, locate_target, cleanup_grounding_screenshots), while grounding_health is resource-first. The deviation is minor and all names remain readable and predictable.
Four tools is well-scoped for a narrow visual-grounding fallback service: one core action plus supporting health, loading, and cleanup operations. Each tool earns its place without redundancy.
The surface covers the core locate operation plus model loading, health, and screenshot cleanup. Minor gaps exist around unloading/reloading the model and listing screenshots, but these are workable omissions for a fallback utility.