LABSCO SUMMARY

Different tools for different applications, from one install.

Contexts are the reason to run a gateway instead of pointing every editor at every server: one application gets the documentation plugin, another gets something else, and neither carries the other's tool definitions in its context. Plugins declare their network and file permissions in the manifest, so what one can reach is readable before you install it.

What it is

A cross-platform Rust binary that acts as an MCP server for your AI applications and gets its capability from plugins. Each plugin declares its tools, resources and prompts in a TOML manifest and asks only for the permissions it needs.

What you get

One stdio endpoint that Claude Desktop, Claude Code, Cursor, VS Code, Zed, Codex CLI and Opencode all connect to
Plugins installed, created, configured and inspected — jilebi plugins add, create, setup and log
Application contexts that limit which tools each application sees, so one editor gets a documentation plugin and another does not
Plugin manifests in TOML declaring tools with input schemas, read-only resources with MIME types, and prompt templates with interpolated arguments
A permission model per plugin: allowed hosts, specific URLs, readable and writable files, readable and writable directories, with user_defined prompting at setup time
Environment variables and secrets declared separately, with secrets allowed no defaults
Persistent state for plugins across runs

Requirements

Windows, Linux or macOS. Install with the script from mcp.jilebi.ai, or download the platform archive. On macOS the binary needs its quarantine attribute removed and the xz dependency installed. Then add jilebi with the stdio argument to your client configuration.

Setup effort

One command — curl -fsSL https://mcp.jilebi.ai/install.sh | bash

See installation options

USE CASES

01

Keeping each editor's tool list short

Create a named context listing only the plugins that application should see, and point that application at it.

02

Adding a capability across every client at once

Install the plugin into the gateway and every connected application picks it up, rather than editing six configuration files.

03

Knowing what a plugin can touch

The manifest declares allowed hosts, URLs and file paths up front, and setup prompts for the values you have to supply yourself.

04

Turning an existing MCP server into a plugin

The create command scaffolds a project, and the docs include a conversion prompt for porting an existing server into the manifest format.

BEFORE YOU INSTALL

What to know first

Requires

jilebi on PATH

Where it runs

All 7 documented clients run the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

curl -fsSL https://mcp.jilebi.ai/install.sh | bash

MCP Clients

Claude Desktop, Claude Code, Cursor

JSON

{
  "mcpServers": {
    "jilebi": {
      "command": "jilebi",
      "args": [
        "stdio"
      ],
      "env": {}
    }
  }
}

VS Code

VS CODE · JSON

{
  "servers": {
    "jilebi": {
      "type": "stdio",
      "command": "jilebi",
      "args": [
        "stdio"
      ]
    }
  }
}

Zed

ZED · JSON

{
  "context_servers": {
    "jilebi": {
      "command": "jilebi",
      "args": [
        "stdio"
      ],
      "enabled": true,
      "source": "custom",
      "env": {}
    }
  }
}

Codex

CODEX · TOML

[mcp_servers.jilebi]
command = "jilebi"
args = ["stdio"]

OpenCode

OPENCODE · JSON

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jilebi": {
      "type": "local",
      "command": [
        "jilebi",
        "stdio"
      ],
      "enabled": true,
      "environment": {}
    }
  }
}

Jilebi