Skip to content
Back to skills

Replit

ASecurity

Read, create, update, and publish apps through Replit's official MCP server.

  • 69,003 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 4, 2026
ai-agents

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned October 4, 2026

npx -y skills add asgeirtj/system_prompts_leaks --skill replit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Replit?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Replit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/asgeirtj-replit/badge)](https://www.skillsdirectory.com/skills/asgeirtj-replit)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "replit"
description: "Read, create, update, and publish apps through Replit's official MCP server."
icon: "replit"
metadata: { "includeInPrompt": false }
---

# Replit

Use the installed `replit` CLI. Start with `replit status`. If it reports
`not_connected`, run `replit authorize-url` and share only the returned
`connect_url` with the user.

OAuth uses Dynamic Client Registration and PKCE through authd. No shared client
secret enters Muse, and credentials must never be requested in chat.
The first connection requests read-only access. Before a write, or after one
fails for missing access, run `replit status --for-command <tool-name>`. If it
returns `scope_status: not_granted`, copy `scope_add_url` exactly and post it on
its own line as `[Additional Replit access](<scope_add_url>)` so the client
renders the native access button, then wait for consent to finish before
retrying once. OAuth access does not replace Hatch approval. Never construct a
scope URL or ask for tokens in chat.

Run `replit list-tools` to inspect the live provider catalogue and schemas,
then call an advertised tool with:

```text
replit call-tool --name <tool> --arguments-json '<json-object>'
```

`list-tools` exposes only reviewed Replit tools and includes each tool's
`hatch_permission`, `hatch_action`, and `hatch_permission_label`. Unknown or
new provider tools remain unavailable until reviewed. Read permissions follow
the user's connector settings; creating, editing, and publishing apps use
separate granular approvals. Do not retry a failed or timed-out write
automatically because its side effect may have completed.

Files in this skill

  • SKILL.md1.6 KB
  • connector_auth_config.yaml242 B
  • manifest.yaml2.2 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.