Zight MCP Server
Give your agents visual context with Zight MCP
Create a Request Link for a video, screenshot, or file, then let compatible agents work from the recording, transcript, on-screen text, and available logs behind a Zight link.
Connect to
Connection options vary. Claude links to Zight’s official connector listing. Muse and Grok are shown via MCP, not as direct Zight integrations; setup and availability depend on each client.
https://mcp.zight.com/mcp
Add it as a remote MCP server or custom connector
Trusted by 5m+ people who would rather show than tell
What is the Zight MCP server?
The Zight MCP server is a remote MCP server that lets AI assistants create Request Links and read the context behind Zight video links. Connect it at mcp.zight.com/mcp.
Create Request Links
Ask for the context you need
Tell your assistant what someone should send and it creates the Request Link in your current Zight workspace. Share the link anywhere. The other person can respond without needing a Zight account or installation.
See how Zight Request Links workRead video content
Give your assistant the video, not your recap
Paste a Zight video link into your AI tool. It can work from the recording and the context Zight captured with it instead of relying on the part you remembered to type.
Transcripts and on-screen text come from Zight AI. Logs are available when they were collected with the video.
Screen recordings
The walkthrough, the bug report, or the customer’s own recording — as the source, not as a summary of it.
Transcripts and OCR
What was said, and the text that was visible on screen. No copying error messages out of a video by hand.
Console and network logs
The technical evidence that came with the recording, so debugging starts from what actually happened.
Request Link responses
The video someone submitted through your Request Link, with the available context attached.
What people do with it
Three jobs that stop needing a copy-paste step
Debug from the evidence, not the retelling
Give your assistant the link to a customer’s request video and it works from the recording, the transcript and the console logs together — instead of from your paraphrase of what they said went wrong.
Turn a walkthrough into the follow-up
Point it at a recording and ask for the summary, the action items, or the handoff note. The assistant reads what was said and what was on screen, so the output is about the actual work.
Stop pasting context into chat
The copy-the-transcript-into-a-chatbot step disappears. The assistant fetches what it needs from the link, which means it is working from the whole recording rather than the part you remembered to paste.
FAQ
Questions people ask first
A remote MCP server that lets an AI assistant create Zight Request Links and read the context behind Zight video links, including the recording, transcript, text visible on screen, and available console and network logs.
Yes. It can create a request for a video, screenshot, or file in your current workspace. You can add a title and instructions, set a future expiry, and use workspace-supported options such as video log collection or premium integration record linking.
Any app that supports remote MCP servers or custom connectors, which includes Claude. What a given app can do with the context depends on its own MCP implementation and the permissions you grant it.
Use https://mcp.zight.com/mcp as the remote MCP server URL. Add it as a remote MCP server or a custom connector, depending on what your tool calls it — the Help Center has the step-by-step for each.
No. The assistant reads the context behind the Zight links you give it, and it inherits the permissions of the account that connected the server. Zight is SOC 2 Type II certified and your content is not used to train models.
No. Browser log collection is for video requests and requires the workspace log collection feature. Linking a request to a Zendesk, Salesforce, or Intercom record requires a custom ID and premium integrations; without that entitlement, the record link is ignored.
Ask for the context. Then let your assistant read it.
Create a Request Link or paste a Zight video link into your AI tool. The same connection handles both sides of the handoff.