ChalkTalk MCP server
Commit Oct 25, 2026Converts AI conversations into narrated tutorial videos featuring code scenes, diagrams, charts, and CLI sessions.
Also known as chalktalkhq/plugins, plugins
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.7.0
- Last commit
- Oct 25, 2026
- License
- —
What is ChalkTalk MCP?
ChalkTalk converts AI conversations into narrated tutorial videos featuring code scenes, diagrams, charts, and CLI sessions.
Summary generated from the project's README
About ChalkTalk MCP server
ChalkTalk transforms AI chat sessions into structured tutorial videos containing code scenes, diagrams, charts, CLI sessions, and mathematical content. It works by drafting scenes and generating narration for each segment. The server allows an AI agent to inspect preview frames to ensure the visual content matches the intended walkthrough before you finalize the project.
Developers can integrate this server into various environments including Claude Code, Codex, Cursor, VS Code, Windsurf, and ChatGPT. Installation varies by client, ranging from CLI commands to adding a custom server URL. The service does not require an API key, as you sign in through your browser during the first tool call. Rendering happens within the ChalkTalk application rather than through the connector, allowing you to review the video before committing render time.
What you can do with it
- 1Generate pull request walkthroughsAsk the AI to create a short video explaining the changes in a specific pull request.
- 2Create narrated code tutorialsConvert a specific function into a complete walkthrough with voiceover and visual scenes.
- 3Audit video pacing and structureUse the agent to identify writing problems or pacing issues within a video project.
- 4Preview visual scenesRequest the agent to render and inspect specific frames to verify the visual layout.
Written from the project's README. Every use case is checked against a quote from it.
How to install ChalkTalk MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall ChalkTalk MCP in Claude Code
$ claude mcp add --transport http plugins https://chalktalk.dev/api/mcpInstall ChalkTalk MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"plugins": {
"url": "https://chalktalk.dev/api/mcp"
}
}
}Install ChalkTalk MCP in VS Code
.vscode/mcp.json
{
"servers": {
"plugins": {
"type": "http",
"url": "https://chalktalk.dev/api/mcp"
}
}
}Install ChalkTalk MCP in VS Code CLI
$ code --add-mcp '{"name":"plugins","type":"http","url":"https://chalktalk.dev/api/mcp"}'Install ChalkTalk MCP in Codex
$ codex mcp add plugins --url https://chalktalk.dev/api/mcpInstall ChalkTalk MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.plugins] url = "https://chalktalk.dev/api/mcp"
Install ChalkTalk MCP in Gemini CLI
$ gemini mcp add -s user --transport http plugins https://chalktalk.dev/api/mcpInstall ChalkTalk MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"plugins": {
"url": "https://chalktalk.dev/api/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablechalktalkhq/plugins is public and reachablegithub.com/chalktalkhq/plugins ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-10-25github.com/chalktalkhq/plugins ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubChalkTalk
Turn a conversation into a narrated tutorial video - without leaving your editor.
ChalkTalk writes the video as a structured document: scenes for code, diagrams, charts, CLI sessions, and maths, each with its own narration. Ask for a walkthrough of the function you just wrote and it drafts the scenes, checks them, and renders preview frames it can actually look at. You review and export in ChalkTalk.
Install
| Client | How |
|---|---|
| Claude Code | Plugin - two commands below |
| Codex | Two CLI commands below |
| Cursor, VS Code | One click from the install page |
| Claude Desktop, claude.ai, mobile | Settings → Connectors → Add custom connector → server URL |
| ChatGPT | Settings → Security and login → Developer mode, then Plugins → + → Public endpoint → server URL |
| Windsurf, Antigravity | Config snippet below |
| Anything else | The install page has a prompt you can paste into your own agent |
Claude Code
/plugin marketplace add chalktalkhq/plugins
/plugin install chalktalk@chalktalk-plugins
Then run /mcp to sign in.
Codex
codex mcp add chalktalk --url https://chalktalk.dev/api/mcp
codex mcp login chalktalk
Windsurf, Antigravity - merge into your MCP config. Windsurf keeps it at
~/.codeium/windsurf/mcp_config.json; Antigravity exposes it under
MCP Servers → Manage MCP Servers → View raw config.
{
"mcpServers": {
"chalktalk": {
"serverUrl": "https://chalktalk.dev/api/mcp"
}
}
}
Server URL, for anything that just asks for one:
https://chalktalk.dev/api/mcp
No API key. You sign in once in the browser on the first tool call.
Try it
- "Make a 90-second video explaining this pull request."
- "Turn this function into a code walkthrough with narration."
- "Start from the binary search template and show me the first scene."
- "Check my project for pacing problems and show me frame 3."
What it can do
| Author | Create, update, duplicate, and delete video projects |
| Explore | Search and fetch your projects and the template catalogue |
| Check | Validate structure, report pacing and writing problems |
| See | Render preview frames the agent can inspect before you commit |
| Narrate | Generate voiceover from narration you have approved |
Rendering runs in ChalkTalk rather than over the connector, so you review the video before spending render time on it.
Links
- ChalkTalk
- Connect your AI tools
- Privacy policy
- Terms of service
- Issues
- Support: support@chalktalk.dev
This repo is generated from the ChalkTalk app repo - open an issue rather than a pull request against these files.
ChalkTalk MCP questions
How do I add ChalkTalk MCP to Claude Code?
Run claude mcp add --transport http plugins https://chalktalk.dev/api/mcp in your terminal. Add --scope user to make it available in every project.
How do I add ChalkTalk MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Do I need an API key to use ChalkTalk?
No API key is required; you sign in via your browser during the first tool call.
Can the AI see what the video looks like?
Yes, the server can render preview frames that the AI agent can inspect before you commit to the final video.
Where does the video rendering take place?
Rendering is performed within the ChalkTalk application rather than over the MCP connector.