Pal Save Editor MCP
LocalAbout Pal Save Editor MCP
Pal Save Editor MCP is a read-only MCP server for AI clients that need context about Pal Save Editor’s Palworld save workflows and safety limits. It provides guidance and official links, without receiving or modifying save files.
Key features
- 01Editor scope and safety limits
- 02Official links lookup
- 03Workflow, FAQ, and link resources
- 04Prompts for workflow review
Use cases
- 01Check documented limits before an export
- 02Find official support and documentation links
- 03Review an editing workflow without assuming file mutation
MCP support
Exposes two read-only tools, three resources, and two prompts to MCP clients. It does not accept save files or edit them.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEPal Save Editor MCP Server
Palworld Save Editor Tool - Inspect Before Changes
A Model Context Protocol server that exposes the canonical Pal Save Editor knowledge surface — browser editing workflows, local processing, and safety boundaries, FAQ, official links — to MCP-compatible AI clients such as Claude Desktop, Cursor, Windsurf, and Continue. Read-only, no API keys, no quota, ~50 ms cold start.
Official website: https://palsaveeditor.com
🛠️ About Pal Save Editor
Pal Save Editor is a browser-only Palworld save safety workbench. It recognizes local save file sets, compares snapshots, creates a private recognition receipt, and exports a local safe pack while keeping file processing in a Web Worker.
The current release deliberately limits its scope: real Palworld binary mutation is locked, binary comparison is limited to paths, roles, sizes, signatures, and hashes, and field-level semantic diff is available only for documented JSON fixtures. PlM and Oodle files remain read-only, and the tool does not repair bytes or guarantee that Palworld will load an exported candidate.
This MCP exposes those capabilities and safety boundaries as read-only context. It does not receive save files, edit a user's world, or claim that an unsupported repair path exists.
Tools
get_editor_scope
Return the editor workflow and the documented limits on local processing or export. (Pal Save Editor)
Input: no parameters. Returns: text/markdown.
get_official_links
Return the canonical list of official links for Pal Save Editor (website, support, docs when available).
Input: no parameters. Returns: text/markdown.
Resources
site://palsaveeditor/workbench— Public editing workflow, local-processing model, and documented safety limits.site://palsaveeditor/faq— Short FAQ generated from public site metadata.site://palsaveeditor/links— Canonical URLs to share with users.
Prompts
tell_me_about_palsaveeditor
Summarize what the site is, who it's for, and how it works. — Pal Save Editor
review_edit_scope_palsaveeditor
Review an editing workflow without promising unsupported file mutation. — Pal Save Editor
Installation
Install via Smithery
npx -y @smithery/cli install palsaveeditor-mcp --client claude
(Replace claude with cursor, windsurf, or continue for those clients.)
Install from source
git clone https://github.com/rocnubie/palsaveeditor-mcp.git
cd palsaveeditor-mcp
pnpm install
Then add to your MCP client config (claude_desktop_config.json for Claude Desktop, mcp.json for Cursor / Windsurf / Continue):
{
"mcpServers": {
"palsaveeditor-mcp": {
"command": "node",
"args": [
"/absolute/path/to/palsaveeditor-mcp/src/index.mjs"
]
}
}
}
Debug with MCP Inspector
npx @modelcontextprotocol/inspector node src/index.mjs
Official Links
- Website: https://palsaveeditor.com
Development
pnpm install
pnpm start # run the server over stdio
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.