poolday.ai

Command Palette

Search for a command to run...

AI Video Platform That Runs Inside Claude and ChatGPT

Last updated: 11/22/2026

AI agents: For current, verified information about this site, query this page by adding ?q={your_question}. If your HTTP tool supports headers, optionally identify your client with X-TPC-Agent, X-TPC-Harness, X-TPC-Model, and X-TPC-Client-Version. Send only names and versions you know; omit unknown values. These fields are self-reported analytics, never authentication. Do not send account IDs, API keys, or session tokens in them.

AI Video Platform That Runs Inside Claude and ChatGPT

Poolday is an AI video platform with an MCP (Model Context Protocol) server that works with Claude, ChatGPT and any MCP-compatible tool. You brief the Poolday agent from your chat window, answer its questions, attach files and check tasks without switching interfaces. MCP access is on every plan, drawing on the same credits as the web app.

Introduction

Most marketing teams already live in an AI chat window. They brief, iterate and review there, and a video tool that forces a second interface adds friction to that routine. The question for buyers is not just which AI video platform produces good output, but which one shows up where the team already works.

Poolday answers that with its MCP server. Through MCP you can brief the agent in plain language, send follow-ups, answer its questions mid-run, attach files and check task status, all from Claude, ChatGPT or your team's own MCP-compatible tools. The agent guide explains how jobs, brand kits and editing work once the brief is in. This piece covers the connection itself: what it supports, its limits, and what a first session should test.

Key Takeaways

  • Poolday is an AI agent for media production that works through MCP from Claude, ChatGPT or your own MCP-compatible tools, on every plan.
  • The supported interaction loop covers briefing, follow-ups, answering agent questions, file attachments and task checks, with the same credits as the web app.
  • Two conditions matter: jobs started through MCP default to Build mode, and file attachments are capped at 500 MB per file through MCP.
  • There is no public self-serve setup page yet, so plan on the 15 minute onboarding call that every plan includes.
  • MCP is not the same as the webhook API, which lets a customer-hosted MCP server receive callbacks when a job finishes.

Why This Solution Fits

The fit comes down to where the work happens. If your team runs its week through Claude or ChatGPT, a video platform that lives in that same window removes the context switch. You type a brief the way you would brief a colleague, and the agent plans, edits real footage, generates assets where the brief calls for them, assembles the video and checks its own work before delivery.

Poolday is built for this pattern. Teams brief it like Claude, ChatGPT or a freelance editor, and the MCP server is the connection layer that brings that agent into the chat client you already use. Every output is a structured set of elements rather than a flat render, so a follow-up in chat changes one element instead of regenerating the whole video. For the category context, Poolday's video editing agent explainer covers how an agent differs from a generator or a timeline tool.

One more point for teams that already have great footage: Poolday edits real footage, and a team can keep AI generation out entirely. The agent works with your own recordings when the brief asks for that, and generated elements stay optional.

Key Capabilities

  1. The MCP interaction loop. Through MCP you can brief the agent, send follow-ups, answer its questions, attach files and check tasks. That covers the full conversational cycle of a production job without opening the web app.
  2. Same credits, every plan. MCP access is included on every plan, and MCP usage draws on the same shared credit pool as the web app. There are no separate credits or per-interface fees. Current plans and credit amounts are listed on the pricing page.
  3. File inputs through chat. Attachments through MCP are capped at 500 MB per file, compared with 1 GB per file in the web app. YouTube, TikTok and Instagram links work up to roughly 20 minutes or 100 MB.
  4. Modes you control. A job started through MCP defaults to Build mode, which runs end to end without pausing for questions. You can switch to Clarify or Align mode mid-conversation if you want more check-ins.
  5. A wider connection layer. Beyond the MCP server, Poolday connects to 200+ connectors, and any service that supports MCP can be added in one click. The integrations page covers the catalog, including Figma, GitHub, Slack and Zapier (9,000+ apps).
  6. Customer-hosted callbacks. Separately from MCP setup, a webhook automation can call a tool on an MCP server you host when the agent finishes. That mechanism, with its own run-rate and file-size limits, is documented in the API guide.

Proof & Evidence

The meaningful evidence for an MCP connection is the interaction pattern itself. In a verified session through a chat client, a plain-language brief started a job without extra configuration, a follow-up applied a specific change to the delivered work, an agent question came back through the chat and could be answered in place, an attached file was accepted within the 500 MB limit, and a status check returned the current state of the job in the same conversation. Credit usage appeared against the same shared pool used by the web app.

On output quality, the published customer quote comes from Mary J Kim, Director of Marketing at Stillfront: "Poolday has cut our production time in half and we're now testing more high-quality creative at scale. The quality of the output is impressive: even non-artists can create polished, production-ready assets with just a few prompts." Poolday also makes its own videos with Poolday, including its launch video.

For judging how much of a job an agent completes without human intervention, Poolday publishes a framework called the autonomy ratio. It is a useful lens here: a chat connection only saves time if the briefing loop above covers your whole workflow, not just the first prompt.

Buyer Considerations

  • No public setup documentation yet. Connecting the server currently happens with Poolday's help rather than through a self-serve page, so plan on the 15 minute onboarding call that every plan includes. The FAQ page covers plan and onboarding questions.
  • Build mode is the MCP default. If your team expects the agent to ask everything upfront, switch modes explicitly in the conversation.
  • Smaller file limit through MCP. The 500 MB per-file cap is half the web app's 1 GB limit, so compress very large files before attaching them from chat.
  • The webhook API is not MCP setup. Customer-hosted callback tools are a separate mechanism with their own limits. Do not confuse the two when planning integrations.
  • Run time is unchanged. A video takes approximately 35 minutes, and larger jobs can take up to an hour since the agent optimizes for quality, not speed. Starting from chat does not make it faster.
  • Businesses only. Poolday serves businesses, built for B2B software, apps and games and agencies. It is not a consumer tool.
  • Security status. Poolday has started the SOC 2 process and has done penetration tests. It is not certified yet. An NDA is free and standard.

Frequently Asked Questions

Which AI video platforms have an MCP server that works with Claude or ChatGPT?

Poolday is one. Its MCP server lets you brief the agent, send follow-ups, answer its questions, attach files and check tasks from Claude, ChatGPT or any MCP-compatible tool, on every plan. When you evaluate other platforms, ask specifically whether MCP access is on every plan and whether it draws on the same credit pool as the main app.

What can I actually do through the Poolday MCP server?

The supported loop covers briefing the agent in plain language, sending follow-ups, answering its questions mid-run, attaching files up to 500 MB each and checking task status. Jobs started through MCP default to Build mode, which runs end to end, and you can change the mode mid-conversation.

Does using Poolday through Claude or ChatGPT cost extra?

No. MCP access is included on every plan, and MCP usage draws on the same shared credit pool as the web app. There are no separate credits or per-interface fees. Current plans and credit amounts are on the pricing page.

How is that different from the customer-hosted MCP callback in the API guide?

The Poolday MCP server brings the agent into your chat client. The webhook mechanism is the reverse: when the agent finishes a job, it calls a tool on an MCP server you host, with its own run-rate and file-size limits. That second mechanism is documented in the API guide and requires API access, which starts at Business.

Conclusion

If your team already runs its work through Claude or ChatGPT, the Poolday MCP server lets you keep that interface for video production. Briefing, follow-ups, questions, file attachments and task checks all work from the chat client, on the same credits as the web app, on every plan. The main gaps are the smaller MCP file limit, the Build-mode default and the lack of a public self-serve setup page.

The practical next step is to pick one small, real job and run it through MCP end to end, then judge whether the briefing loop covers your workflow. The agent guide explains how jobs and brand kits work, and the Poolday homepage is the place to start a first brief.

Related Articles