Install
$ agentstack add mcp-agentpub-io-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Agent skills for agentpub — instant, reviewable web publishing for AI agents.
Your agent publishes a page in three HTTP calls; you review it on the live page, your agent revises, and you keep it permanently. These skills teach any agent to drive that loop.
Docs (for agents): https://agentpub.io/llms.txt
Install
# install a specific skill globally
npx skills add agentpub-io/skill --skill agentpub-publish -g
# or add the whole repo
npx skills add agentpub-io/skill
Skills
| Skill | What it does | | --- | --- | | agentpub-publish | Publish files to the web in three calls (create → upload → finalize). Anonymous 24h previews, or permanent owned sites with a Bearer key. | | agentpub-blueprints | Produce consistent, on-brand deliverables from locked design templates — same look every run, no drift. | | agentpub-onboarding | Give a new user a ~2-minute personalized demo: build them a real, reviewable artifact and walk them through the publish → review → revise → approve → keep loop. | | client-status-report | A ready blueprint for clean, print-friendly weekly client status reports. |
How it fits together
agentpub-publish is the base. agentpub-blueprints + client-status-report produce consistent artifacts on top of it. agentpub-onboarding choreographs the whole loop to show a new user the value fast. It all composes the public agentpub API — no account required to start.
License
MIT — see [LICENSE](./LICENSE).
Cursor Plugin / Marketplace
This repo is the Cursor plugin source for agentpub: skills plus the hosted MCP that drives the full publish → review → revise → approve loop.
- What it enables: agents publish a live page, reviewers comment right on that page, the agent revises in place (versioned), and you approve when it is done — not just a one-shot host URL.
- MCP endpoint:
https://agentpub.io/mcp(seemcp.json) - Local test: symlink or copy this repo to
~/.cursor/plugins/local/agentpub, then reload Cursor - Submit / update listing: https://cursor.com/marketplace/publish with this repository URL
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: agentpub-io
- Source: agentpub-io/skill
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.