pepita
FreeNot checkedRead, edit, publish, and preview your pepita websites from Claude.
About
Read, edit, publish, and preview your pepita websites from Claude.
README
Snapshot. Factored out of the private pepita monorepo, built and released from there, and not standalone-buildable. PRs are applied in the monorepo. https://pepita.dev
@pepitahq/mcp
Local MCP server (stdio) for pepita sites. Lets a local Claude (Claude Code / Desktop / the MCP Inspector) read and edit your sites, publish them, and manage shareable preview links — the same things you can do in the editor. Edits show up live in the pepita editor too, so you can move between the chat and the visual editor mid-task.
Prefer the hosted connector? There's a remote, OAuth-authenticated connector at
https://mcp.pepita.dev/mcp— nothing to install, just sign in with your pepita account:claude mcp add --transport http pepita https://mcp.pepita.dev/mcp(or add it as a custom connector in Claude Desktop / claude.ai). This package is the local alternative — it runs on your machine and works with any MCP client.
Authentication reuses the pepita CLI: run pepita login first (writes
~/.pepita/config.json), or set PEPITA_TOKEN. No separate OAuth.
Use
# one-off, no install:
npx @pepitahq/mcp
# register the local server in Claude Code:
claude mcp add pepita-local -- npx -y @pepitahq/mcp
Also listed in the MCP Registry as
dev.pepita.mcp/mcp. If your MCP client can browse the registry, find pepita
there and add it in one step; otherwise use the npx / claude mcp add setup above
(the registry entry points at the same @pepitahq/mcp package).
Tools
Fourteen tools — six that read your sites, five that write, publish, or manage previews, and three that manage assets:
- Read —
list_sites,get_status,list_site_files,read_site_file,list_previews,list_video_assets - Write —
write_site_file(into the working copy),publish(→ live), and preview links:create_preview,update_preview(push the current site onto an existing link),delete_preview - Assets —
rename_asset(display label only — the id and URLs never change, so pages referencing the asset keep working),get_video_asset_original_url(an expiring download link for the uploaded original),delete_video_asset(removes the asset and stops its streams)
list_site_files / read_site_file read the working copy by default, the live
site (state: "live"), or a specific preview link (preview: "<name>").
Destructive / account-level actions (custom domains, team, billing, deleting a site) are deliberately not exposed — those stay in the editor UI, where their confirmations live. (Deleting a preview link is exposed: it only stops serving, and the version stays restorable from History.)
Env
PEPITA_TOKEN— bearer token (overrides the config file).PEPITA_API_BASE— API host (defaulthttps://app.pepita.dev).PEPITA_CONFIG_DIR— config dir (default~/.pepita).
Install pepita in Claude Desktop, Claude Code & Cursor
unyly install pepitaInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add pepita -- npx -y @pepitahq/mcpFAQ
Is pepita MCP free?
Yes, pepita MCP is free — one-click install via Unyly at no cost.
Does pepita need an API key?
No, pepita runs without API keys or environment variables.
Is pepita hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install pepita in Claude Desktop, Claude Code or Cursor?
Open pepita on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare pepita with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
