Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
npx -y @orboto/[email protected]Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
claude mcp add orboto-mcp -- npx -y @orboto/mcp@0.240.0รันในเทอร์มินัล
{ "mcpServers": { "orboto-mcp": { "command": "npx", "args": [ "-y", "@orboto/[email protected]" ] } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Model Context Protocol server for orboto - a self-hosted ticket and project management platform. Connect Claude Desktop, Cursor, GitHub Copilot Chat, or any MCP-aware AI client and operate orboto as a structured set of tools.
131 tools cover tickets, projects, milestones, time tracking, documents, primer facts, alerts and absences. Every call respects the caller's permission set - what the API key behind the MCP session cannot do in the web UI, the MCP session cannot do either.
Model Context Protocol server for orboto - exposes tickets, projects, milestones, time, docs, primer-facts, alerts and absences as MCP tools for Claude Desktop / Cursor / Copilot Chat / any MCP-aware AI client.
The shortest path is the orboto CLI:
npm i -g orboto
orboto login
orboto mcp install # writes the "orboto" server entry into ./.mcp.json
orboto mcp install --scope user # or into the Claude Code user config
The entry it writes runs orboto mcp serve, which installs and starts
@orboto/mcp at the version of the instance it connects to, so the tool
schemas always match that API. The proxy versions are cached under
~/.orboto/mcp/<version>/, the entry carries no credential, and
orboto mcp status prints the instance version, the cached proxies and the
entry of the current directory. In Claude Code, orboto claude then starts a
session with the wake channel loaded.
Everything below configures the proxy by hand, for clients the CLI does not write. There are two ways to authenticate the stdio proxy:
ORBOTO_API_KEY. On first use the proxy opens your browser to the orboto login (which is your SSO login when SSO is configured), you approve once, and it keeps a short-lived, self-refreshing session cached on disk. Nothing to paste, nothing long-lived.ORBOTO_API_KEY to an orb_… key from Profile → API keys → Generate. Best for headless machines with no browser.The proxy reads ORBOTO_API_URL (the workspace URL including /api) and ORBOTO_API_KEY. The orboto CLI uses different names for the same two values (ORBOTO_BASE_URL, ORBOTO_TOKEN); a box that only sets the CLI's variables leaves the proxy without a URL, which it reports as a missing ORBOTO_API_URL at start.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows):
{
"mcpServers": {
"orboto": {
"command": "npx",
"args": ["-y", "@orboto/mcp"],
"env": {
"ORBOTO_API_URL": "https://orboto.example.com/api"
}
}
}
}
The first launch opens your browser to authorize. The refresh token is cached at ~/.config/orboto/mcp-oauth.json (mode 0600), so subsequent launches reconnect silently. On a headless host with no browser, the proxy prints the authorization URL to stderr for manual paste, or fall back to the API-key form below.
{
"mcpServers": {
"orboto": {
"command": "npx",
"args": ["-y", "@orboto/mcp"],
"env": {
"ORBOTO_API_URL": "https://orboto.example.com/api",
"ORBOTO_API_KEY": "orb_…"
}
}
}
}
Same shape under .cursor/mcp.json or .vscode/mcp.json in your workspace root (or the user-level equivalent).
Ask the AI: "List my orboto projects." The model picks orboto_list_projects, the call goes through MCP → REST API → back, and your projects come back as a list. If you see "no projects matched" but you know you're a member of some, the auth is working - re-check who the API key belongs to in Profile → API keys.
If your orboto host runs the bundled MCP container (default on the official docker-compose.yml), every client on your network can use it directly via Streamable HTTP - no npx and no per-laptop install:
{
"mcpServers": {
"orboto": {
"type": "streamable-http",
"url": "https://orboto.example.com/mcp",
"headers": {
"Authorization": "Bearer orb_…"
}
}
}
}
The /mcp path on the main host is proxied to the bundled MCP container - no separate subdomain or cert needed. Both modes (stdio via npm, HTTP via host) hit the same tool surface.
stdio-first CLIs (e.g. Codex): prefer the stdio proxy (
npx @orboto/mcp) over an HTTP+OAuth URL. Some CLIs handle the OAuth session refresh and session-expiry re-init poorly and can lose their tools after a while or after a server deploy; the stdio proxy avoids that churn. Claude Desktop, Cursor, and VS Code Copilot are known-good over HTTP+OAuth.
Codex CLI reads TOML from ~/.codex/config.toml - add an [mcp_servers.orboto] table pointing at the stdio proxy:
[mcp_servers.orboto]
command = "npx"
args = ["-y", "@orboto/mcp"]
env = { ORBOTO_API_URL = "https://orboto.example.com/api", ORBOTO_API_KEY = "orb_…", ORBOTO_MCP_CLIENT = "codex" }
Omit ORBOTO_API_KEY to use OAuth login instead. codex mcp add writes the same block from the CLI.
Each @orboto/mcp release matches a specific orboto API version - the tag on this package is the same as the v* tag on the source orboto repository. Tool schemas evolve with the API, so:
npx @orboto/[email protected] (or whichever your server is on).@latest if you always run your orboto host on the most recent release. On a mismatch (package newer than server), some newer tools may 404 at call time - but the older tools keep working.The MCP server logs the server version it talks to on startup, so you'll see the alignment in your client's MCP logs.
MIT. See LICENSE.md.
This repository (orboto/orboto-mcp) is a public subtree-mirror of the apps/mcp/ directory from the main orboto monorepo (private). Code changes land in the parent repo and are mirrored here on every tag push.
File issues here: https://github.com/orboto/orboto-mcp/issues. Bug reports, feature requests, and questions about @orboto/mcp belong on this repo - that's where triage happens. Pull requests against the mirror are closed since the code is read-only; please open a discussion on the issue instead and the fix lands in the parent repo.
Model Context Protocol server for orboto - exposes tickets, projects, milestones, time, docs, primer-facts, alerts and absences as MCP tools for Claude Desktop / Cursor / Copilot Chat / any MCP-aware
{ "mcpServers": { "orboto-mcp": { "command": "npx", "args": [ "-y", "@orboto/[email protected]" ] } }}ภาพรวม
Model Context Protocol server for orboto - exposes tickets, projects, milestones, time, docs, primer-facts, alerts and absences as MCP tools for Claude Desktop / Cursor / Copilot Chat / any MCP-aware AI client.
เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ระเบียนนี้ไม่ได้ระบุตัวแปรสภาพแวดล้อมที่จำเป็น
@orboto/mcp ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-14 Model Context Protocol server for orboto - exposes tickets, projects, milestones, time, docs, primer-facts, alerts and absences as MCP tools for Claude Desktop / Cursor / Copilot Chat / any MCP-aware AI client.