Derive MCP server
Commit Nov 15, 2026Publish AI-generated artifacts to permanent versioned URLs, manage reviews, and allow agents to act on feedback.
Also known as derive-to/derive
- Stars
- 33
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Nov 15, 2026
- License
- —
What is Derive MCP?
Derive publishes AI-generated artifacts to permanent versioned URLs, manage reviews, and allow agents to act on feedback.
Summary generated from the project's README
About Derive MCP server
Derive provides a workspace for managing AI-generated content by turning files into permanent, versioned artifacts. It allows developers and teams to publish HTML, Markdown, LaTeX, or entire websites to durable URLs that maintain a complete history of revisions and decisions. Users can host the service via a hosted app or by running a single self-hosted container on their own infrastructure.
This server functions as a remote MCP server via HTTP or can be run locally using stdio. It enables coding agents to publish work, find existing artifacts, and respond to human feedback left in comments. Developers can connect clients like Claude Code or Codex using specific commands to grant agents roles such as publishing directly or suggesting changes through comments. The system supports various storage backends including SQLite, Postgres, S3, and R2 to accommodate different scaling needs.
What you can do with it
- 1Publish versioned web artifactsAn AI agent can take a directory of files and turn them into a live, versioned website with a single command.
- 2Collaborate with human feedbackA developer can instruct an agent to read comments on a published document and apply the requested revisions.
- 3Automate agentic workflowsYou can set up named workers with standing instructions to perform scheduled jobs and publish results to your library.
- 4Maintain a project libraryUsers can organize their AI-generated research, reports, or designs into collections with live previews.
Written from the project's README. Every use case is checked against a quote from it.
How to install Derive MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Derive MCP in Claude Code
$ claude mcp add --transport http derive https://derive.to/mcpInstall Derive MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"derive": {
"url": "https://derive.to/mcp"
}
}
}Install Derive MCP in VS Code
.vscode/mcp.json
{
"servers": {
"derive": {
"type": "http",
"url": "https://derive.to/mcp"
}
}
}Install Derive MCP in VS Code CLI
$ code --add-mcp '{"name":"derive","type":"http","url":"https://derive.to/mcp"}'Install Derive MCP in Codex
$ codex mcp add derive --url https://derive.to/mcpInstall Derive MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.derive] url = "https://derive.to/mcp"
Install Derive MCP in Gemini CLI
$ gemini mcp add -s user --transport http derive https://derive.to/mcpInstall Derive MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"derive": {
"url": "https://derive.to/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 14, 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 reachablederive-to/derive is public and reachablegithub.com/derive-to/derive ↗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 2026-11-09github.com/derive-to/derive ↗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 GitHubTry it now
No account or install is needed. One request publishes a live page:
curl -F file=@page.html https://derive.to/v1/drafts # or a .zip of a whole site
# → a live URL, plus a claim link that turns the draft into a
# permanent, versioned artifact in your workspace
Give your agent a durable place to publish, find, and improve work:
npx skills add derive-to/derive --skill derive # any agent that reads skills
claude mcp add --transport http derive https://derive.to/mcp # or connect over MCP
Or paste this into a compatible coding agent and let it set itself up:
I'd like you to set up Derive: where the work we make gets published, reviewed, and kept.
Install the skill if I have npm: npx skills add derive-to/derive --skill derive
Otherwise, read https://derive.to/skill.md and follow it (MCP server: https://derive.to/mcp).
Then pick a plan, report, or designed page we've worked on recently and publish it. If I'm not connected to Derive, use the anonymous draft flow. It needs no account and returns a live URL with a claim link. Send me both links.
What is Derive
Derive is a workspace for work made with agents. Give an HTML page, Markdown document, LaTeX paper, deck, or built site a lasting URL and version history. Publish from the browser, CLI, HTTP API, or a compatible agent over MCP. Keep the work private or share it, leave comments, edit it directly, and publish the next version at the same URL.
The content, version history, and comments stay with each artifact. A teammate or another agent can open the same URL and see what changed without reconstructing the work from a chat.
A workspace can also keep agents: named workers with standing instructions, the sources they may use, and a model account. You ask one for work, or give it a schedule, and each piece of work is a job you can follow. A job runs on its owner's own computer, or on a Derive machine where the workspace has them, and publishes its results to the same artifact library. When a job needs a person, it waits in their Inbox.
Derive is Fair Source and self-hostable. Run it as one container on your own infrastructure or use the hosted app.
Features
Publish anything, get a permanent URL
HTML, Markdown, a LaTeX paper, or a whole built site. Every revision is a new version at the same URL, so a link you shared last week still resolves, and still shows its history.
Comments and changes stay with the work
Share an artifact and @mention the people or agents who should weigh in. Comments pin to the exact text, direct edits create new versions, and connected agents can read feedback and publish focused revisions. When a decision truly needs sign-off, request a formal review of that version.
A library for published work
Every artifact lands in a library with a live preview. Pin the work you use often, find work shared with you, and organize related artifacts in collections.
Also included:
- Portable work. Content, versions, and comments stay with the artifact so another person or agent can continue the work.
- Agents and jobs. Make an agent from Claude Code or Codex, ask it for work, put it on a
schedule, or chain several into a workflow. Run it on your own machine with
derive runner serve, or on a Derive machine. See Run agents. - Checkpoints. Save the state of ongoing work in a page that a later session can open.
- Sandboxed viewer. Artifacts run on an opaque origin, isolated from cookies and other artifacts.
- Flexible storage. Use SQLite and local disk, or Postgres and S3/R2 at scale.
- Live collaboration. Comments, optional approvals, and presence update over Server-Sent Events.
- Share previews. Links show an artifact preview in Slack, Discord, X, and Notion.
- CLI and MCP. Publish from the terminal or connect a compatible agent.
- Access controls. Make work private, visible to the workspace, or public. Public links can also use a password.
Roadmap
The current roadmap lives at derive.to/roadmap and keeps its history at the same URL.
Get started
Hosted
The fastest path. No install.
- Go to derive.to
- Create an account
- Publish your first artifact
You get a library, in-browser publishing, version history, and comments.
Self-host
One container is the whole product: API, web, sign-in, publishing, comments, and the sandboxed viewer, with SQLite and blobs in one volume.
Follow the self-hosting quick start to install a digest-pinned release or build the current checkout. It includes secure first-user bootstrap, readiness checks, and a verified first backup. See the deployment guide for Postgres, S3/R2, and cloud hosts.
Want a complete artifact rather than a blank starter? Open or publish one of the official examples: a designed launch page, a research brief, or a living status report. Each shows a different starting point.
From the terminal
npm i -g @derive-to/cli
derive init my-doc --template slides # templates: md · html · slides
cd my-doc
derive publish # versioned URL; the id is saved to derive.json
Connect your coding agent (MCP)
or one line for Claude Code: claude mcp add --transport http derive https://derive.to/mcp
# Derive is a remote MCP server (OAuth). Connect either client:
claude mcp add --transport http --scope project derive https://derive.to/mcp
codex mcp add derive --url https://derive.to/mcp
# or run a local stdio server (set DERIVE_SERVER; DERIVE_TOKEN for a static bearer):
npx -y @derive-to/mcp
The agent acts at the role you grant. Publish access publishes directly, as a kept and restorable version with the workspace notified; a lower scope suggests changes in comments for a person to apply. Full setup and tool guidance is in packages/mcp/SKILL.md.
How it works
One Node container is the whole product; storage is pluggable behind interfaces. The same image self-hosts on SQLite and local disk, scales on Postgres and S3/R2, or runs on Cloudflare Workers.
apps/api HTTP API, sandboxed artifact serving, viewer
apps/web web UI (TanStack Start, SPA mode, static bundle)
packages/core domain: ports, publish, markdown render, viewer shell
packages/db MetaStore: sqlite (default) · postgres · d1
packages/storage BlobStore: fs (default) · s3/r2
packages/cli derive init (md/html/slides) · derive publish <file|dir> · derive runner serve --agent <id> (work an agent's jobs)
packages/mcp Local compatibility MCP: eight tools + derive://guide (the remote /mcp has seventeen)
Every artifact ships OG and Twitter meta plus an oEmbed document, serves a live Server-Sent Events stream, and renders under a strict sandbox CSP on an opaque origin. See the artifact authoring standard for authoring and embed details.
License
Functional Source License (FSL-1.1-ALv2), fair source. Run, modify, and self-host Derive freely for any purpose except offering it as a competing commercial product or service. Each release automatically converts to Apache-2.0 two years after it ships. See the plain-English licensing guide.
Derive MCP questions
How do I add Derive MCP to Claude Code?
Run claude mcp add --transport http derive https://derive.to/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Derive MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Can I self-host Derive?
Yes, Derive is self-hostable as a single container on your own infrastructure.
What kind of files can I publish?
You can publish HTML pages, Markdown documents, LaTeX papers, decks, or entire built websites.
How do agents interact with the work?
Agents can read review comments and publish focused revisions or act as named workers with standing instructions.
Does it support different storage backends?
Yes, it supports SQLite and local disk for simple setups, or Postgres and S3/R2 for scaling.