writ-mcp
OfficialRelated Servers
Alternatives to writ-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to run complete browser workflows through a single run_workflow tool, with anti-detection backends, intelligent element location, automatic retries, and session persistence.MIT
- AlicenseNot gradedqualityBmaintenanceExposes web search, site mapping, scraping, crawling, schema-validated structured extraction, and stateful Playwright browser interaction as MCP tools, routing every call through the same authenticated REST gateway used by the platform's HTTP clients.1MIT
- AlicenseNot gradedqualityAmaintenanceConnects MCP-compatible AI agents to an anti-detection browser server, exposing dozens of tools for navigation, page interaction, search, content extraction, downloads, multi-tab handling, and persistent sessions. It lets agents automate and scrape the web at scale using accessibility snapshots, CSS-selector fallbacks, saved profiles, and batch workflows over stdio or authenticated HTTP transport.971 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents and MCP clients to interact with Webflow's Data API and Designer, allowing them to manage sites, CMS content, pages, and design elements through natural language. Supports OAuth-based remote connections or local runs with a Webflow API token.402 npmMIT
- AlicenseNot gradedqualityAmaintenanceConnects MCP-compatible AI agents to an anti-detection browser server so they can navigate sites, interact with pages, run searches, extract content, download files, and reuse sessions across multi-tab workflows. It exposes 47 tools over stdio or HTTP transport, letting agents automate the web without getting blocked.971 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP server for automating Weavy.ai creative workflows. It provides tools to manage projects, add nodes, configure parameters, run generative nodes, and publish workflows via browser automation.5ISC
TDQS
Scored across 39 tools
The core domains (scrape, crawl, browser task, API build, workflows, data, monitors, automation) are mostly distinct and the descriptions use explicit NOT FOR cues. However, several authoring/build/debug tools overlap in practice: writ_website_to_api vs writ_record_website, writ_browser_compose vs writ_browser_act define_function/compose, and writ_create_http_extraction vs writ_update_workflow can be confused, forcing careful reading.
All tools use the writ_ snake_case prefix, and most follow a predictable verb_noun pattern (list_workflows, run_workflow, create_monitor, crawl_site). Minor deviations are noun-phrase resources (writ_personas, writ_payment, writ_devices, writ_saved_crawls) and the prepositional writ_website_to_api.
39 tools is very large for an MCP surface; many are sub-actions of longer browser/crawl/workflow workflows that could be grouped. While the platform is broad, the count far exceeds the typical 3-15 well-scoped range and increases selection and context burden.
Coverage is strong across scraping, crawling, browser automation, API building, saved workflows, data access, scheduling, monitors, automations, personas and payments. Some lifecycle gaps remain, such as no obvious delete/unwire paths for several resources and monitor listing only indirectly via writ_devices action='monitors', but most gaps are workaroundable.