Body-MCP
Related Servers
Alternatives to Body-MCP
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceA local-first MCP server that enables AI-assisted coding through workspace-scoped tools for file reading/editing, command execution, jobs, Git, LSP, media, browser, and desktop workflows. It enforces OAuth, workspace ACL, trust policies, and file/secret guards so owners can safely grant inspect, edit, or trusted capabilities.559 npmMIT
- FlicenseBqualityBmaintenanceMCP server that enables AI agents to drive your real, logged-in browser via accessibility snapshots, with hardened credential brokering and local workflow memory.5355 npm-
- AlicenseNot gradedqualityAmaintenanceTurns web-based AI clients such as Claude, ChatGPT, and Grok into secure operators of a local machine by exposing an OAuth-gated MCP endpoint with 38 governed tools for file editing, whitelisted shell commands, search, Git, SQLite, browser automation, DevTools, background tasks, localhost fetches, ports, clipboard, notifications, and Postman control. Read-only and destructive operations are annotated, optional app providers can be toggled, and access is confined to permitted folders for safe, local-first desktop automation from the browser.MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first MCP server that provides project context, verification gates, and structured tools for coding agents to discover knowledge, run diagnostics, and execute allowlisted commands within a repository.40 npmMIT
- AlicenseBqualityDmaintenanceProduction-grade MCP server that gives AI agents safe access to your local dev environment: filesystem, databases, processes, and OpenAPI specs.1540 npm4MIT
- AlicenseAqualityAmaintenanceAn open-source MCP server that lets any coding agent operate your computer like a person does—reading the UI through accessibility trees, clicking and typing in the background, showing an agent pointer, zooming into regions, and driving your signed-in Chrome on macOS, Windows, and Linux.4141Apache 2.0
TDQS
Scored across 78 tools
Many tools have distinct targets, but the set has several overlapping control paths: hands_type vs desktop_type, hands_click vs desktop_click, eyes_see_browser vs browser_bridge vs privacy_session_snapshot, and multiple cancel/stop tools. The detailed descriptions help, but an agent still has to choose carefully between browser modes (own Chromium, CDP attach, extension bridge, user browser) and desktop observation modes.
All names are snake_case, and domain prefixes like hands_, eyes_, desktop_, memory_, privacy_, research_, body_, and reflex_ provide readable grouping. However, verb order and prefixing are mixed: hands_type is prefix_verb, memory_search is resource_verb, attach_browser/list_tabs/select_tab are bare verb_noun, and body_console_stop uses prefix_resource_verb.
78 tools is far too many for a single server, regardless of how broad the 'body' domain is. The surface includes many subdomains — browser control, desktop automation, memory, research, privacy, workflows, roles, tasks, skills, events, console — which should be split or scoped down.
The surface covers an unusually broad lifecycle: browser/desktop perception and action, memory CRUD/search/export, privacy sessions, research collection, background tasks, workflows, skills, roles, approvals, and undo. Minor gaps exist, such as no task listing and no skill deletion/update, but most workflows have enough coverage to avoid hard dead ends.