Who it is for
Design and engineering teams tracking and fixing accessibility compliance.
Accessibility scanning and remediation across design, code and live
Overview
Stark handles accessibility across the whole pipeline rather than at one stage, and the asset types it accepts show that: Figma files, code, automated test scans and live URLs all go into the same project for monitoring.
Scan results come back with full issue context, which is the difference between a list of violations and something a developer can act on. Progress is tracked across projects so a team can see whether it is improving, and compliance is reported against framework controls rather than as a raw count. Community tier, documentation published.
Design and engineering teams tracking and fixing accessibility compliance.
The endpoint asks for credentials before naming anything, so thirteen is the publisher's figure. Project creation, asset addition, scan result retrieval and compliance tracking are the groupings described.
Availability
Stark is listed in the Claude connectors directory only. Stark Lab, Inc. has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.
The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.
Claude listing
Stark publishes 13 tools to Claude. That is a mid-sized surface: 54.3% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Productivity publishes 12, so this one runs one tool above its bucket's median and ranks 224th of 462 by tool count.
It falls in the 11-20 tools band, which holds 22.5% of the Claude directory.
Stark publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://mcp.getstark.ai/mcp Stark is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.
In the publisher's words
Make Stark a native part of your AI workflow. Use it to create projects, scan assets, and quickly remediate accessibility issues across your entire workflow including design, code, and production. Key features: - Track your team's accessibility progress across all of your projects so you can determine what progress you're making. - Easily add new assets (Figma, code, automated test scans, URL, etc.) within projects to set them up for automatic monitoring. - Pull down asset scan results with full issue context to make quick and confident fixes - View your compliance journey and see which framework controls need attention Pair with our SKILLs or plugin for a complete accessibility AI workflow.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Issue and project management inside Linear
Claude · ChatGPT
Project and task tracking through chat commands
ChatGPT
Time cards, punches, schedules and PTO from a Buddy Punch account
Claude
Construction project data queried from chat
Claude · ChatGPT
Outbound campaign, lead and performance data from lemlist
Claude
Independent sourced fact-checking for AI-generated claims
Claude
This is an independent catalogue entry compiled by Node8 from Stark's public marketplace listing as it stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with Stark Lab, Inc., and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.