
Syncro MCP
io.github.Servosity由 GitHub 账号 Servosity 发布v0.1.7更新于 Oct 24, 2026
Every Syncro PSA and RMM workflow in your terminal, plus a local database, offline search, and
概览
社区构建的 MCP 服务器与 CLI,把 Syncro PSA/RMM 数据同步到本地 SQLite 镜像,让助手跨客户生成账单、工单、资产与告警报表。
- 可以做什么
- 查询账单:已记录但未开票的工时、已关闭工单的计费偏差、未付应收账龄、按客户计算的每工时收入
- 查看工单与客户:长期无活动的未结工单、单个客户的跨实体档案、客户毛利
- 检查 RMM 与资产:缺少关键补丁的资产、各客户的告警噪音、从未转为工单的告警
- 执行常规写入:创建或评论工单、创建发票、更新客户、创建预约
- 执行删除类操作:删除工单、发票、客户与合同
- 在本地镜像中搜索与导出记录,支持全文检索与离线查询
- 适用场景
- 适合 MSP 负责人和运营人员一次性跨所有客户提问,例如未开票工时、应收账龄、停滞工单、补丁缺口、告警噪音,而不必在 Syncro 门户中逐页翻查。主要用于本地桌面端助手,不能替代在 Syncro 中的日常工作。
- 运行要求
- 以本地进程(stdio)方式运行于 macOS、Windows 或 Linux;通过 .mcpb 包或安装脚本部署 syncro-mcp 服务器及其配套的 syncro-cli。需要 Syncro 账户及从自有门户获取的 API 令牌,通过 SYNCRO_API_KEY 和 SYNCRO_SUBDOMAIN 环境变量提供,SYNCRO_BASE_URL 为可选项。跨代理的 npx 安装方式需要 Node.js。仅支持桌面端助手,不支持网页版 ChatGPT 与 Microsoft 365 Copilot。
安装
在 SourceWeft 中
- 打开 控制台中的 Syncro MCP,将其添加到工作区。
- 为需要使用其工具的对话启用该服务。
Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。
其他 MCP 客户端
参照 仓库 中的启动说明。
README
Syncro + AI - for Claude, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, and any agent that speaks MCP
Unofficial. Community-built Claude Code Skill and MCP server for the Syncro API. Not affiliated with, endorsed by, or sponsored by Servably, Inc..
[Syncro demo - animated preview]
▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.
Every Syncro PSA and RMM workflow in your terminal, plus a local database, offline search, and cross-entity reports no other Syncro tool has. Works with the AI you already use - ChatGPT (desktop app), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Gemini CLI. Free, open source, runs on your laptop. Built for MSP owners. No code required.
Works with your agent
Security note (until this connector is reprinted). Do not run HTTP mode (
--transport http), not even on localhost. This build has no password, listens on every network interface, and predates the browser-rebinding guard, so a web page you open can reach it. The MCP tools can also make changes with your credentials. Use the default stdio transport. If you set up a tunnel for a remote agent, shut it down. A fix is on the way.
The six agents MSP owners actually use (self-serve, works today):
The ChatGPT desktop app runs syncro-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote (HTTP) server, and this connector's HTTP mode is paused until it is reprinted (see the security note in mcp-install.md), so msp-skills does not support it yet. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list.
Also for the Microsoft and Google stacks
Big install base, but an honest heads-up: Gemini CLI runs the local binary you just installed, while Microsoft 365 Copilot and the Gemini app need a remote server, which msp-skills does not support yet.
Skill-native agents (also covered): Hermes and OpenClaw read this skill's
SKILL.mddirectly and speak MCP - see their install sections below. Also works with Cursor, Windsurf, Cline, Continue.dev, and Zed via MCP. Full per-tool wire-up: docs/which-agent.md.
Run more than one agent? Install across all 51+ supported agents in one command:
npx skills add Servosity/msp-skills@latest(requires Node.js, then run the per-skill installer for the CLI/MCP binaries). See docs/which-agent.md.
Install in 60 seconds
Fastest for Claude Desktop - one-click .mcpb
Claude Desktop bundle: the
.mcpblaunches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companionsyncro-cli. Releases cut from 2026-09-18 on ship that CLI inside the bundle; older bundles contain only the MCP server, so if yours lacks the companion, run the Path A or Path B installer below first (or setSYNCRO_CLI_PATHto an existing binary). Details: #331.
Download Syncro MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every Syncro release on the releases page.)
Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:
Path A - paste one prompt into your AI agent (recommended)
Copy this into Claude Code, Codex CLI, or Claude Cowork:
Install the Syncro Skill and MCP server from Servosity/msp-skills in this agent workspace. If this workspace uses a POSIX shell (macOS, Linux, WSL, or Bash), run
bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/syncro/install.sh). If it uses Windows PowerShell, runiwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/syncro/install.ps1 | iex. Then authenticate per the README and runsyncro-cli --helpto explore.
The same prompt works in any agent that can run shell.
Path B - run the installer yourself
Windows (PowerShell):
macOS / Linux:
The installer drops both syncro-cli (the CLI) and syncro-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.
Verify:
Upgrade to the latest version
The installer always fetches the current release - re-run it to upgrade:
macOS / Linux:
Windows (PowerShell):
Claude Desktop .mcpb users: download the latest .mcpb (top of this section) and re-select it in Settings > Extensions. Claude Code plugin users: /plugin update syncro@msp-skills.
Add to Claude Desktop, the ChatGPT desktop app, GitHub Copilot, Gemini CLI, or another MCP client
After the installer runs, see mcp-install.md and docs/which-agent.md for the per-agent wire-up - one section per agent, including the GitHub Copilot servers key and the ChatGPT desktop app. Claude Desktop's Settings > Extensions panel is the simplest path; the MCP config block (for users who prefer editing JSON) is documented in mcp-install.md.
Install for Hermes
From the Hermes CLI:
Inside a Hermes chat session:
Hermes speaks MCP natively, so it can also use the syncro-mcp server directly - same install path, same env vars.
Install for OpenClaw
Tell your OpenClaw agent (copy this):
Install the syncro skill from https://github.com/servosity/msp-skills/tree/main/skills/syncro. The skill defines how its required CLI (
syncro-cli) can be installed via theopenclaw:frontmatter block.
OpenClaw isn't generally available yet; the frontmatter wiring is pre-shipped and will activate the moment OpenClaw launches.
Authenticate
Set the credentials the CLI needs (from your Syncro portal):
doctor confirms the credentials work before you run anything that touches data. It exits 0 even when the credential is rejected, so scripts should add --fail-on error.
What this skill does
Ask in plain language; your agent runs the command. Every row below reads from a local mirror of your Syncro data, so the answer spans every customer at once and comes back in seconds.
Full command reference: guide.md. For the AI-agent operating contract (--agent, --dry-run, when to confirm before mutating), see AGENTS.md.
What makes this different
Most Syncro integrations and MCP servers proxy each question into a live API call. That's fine for one record. It dies at scale, when you're asking "how many billable hours did we log but never invoice across all 47 clients last quarter".
This skill syncs Syncro into a local SQLite mirror with full-text search. Aggregate questions become one local SQL join: instant, offline, and the AI sees the answer, not the raw data. Compound commands like billing uninvoiced, customers margin, and customers profile join timer entries, tickets, invoices, assets, and RMM alerts across every customer - work a stateless API wrapper can't do.
The pain this closes
MSPs leak roughly 10% of revenue to billing errors, and industry analyses name time-tracking inaccuracy the single biggest source - labor logged on a ticket that quietly never makes it onto an invoice (DeskDay, Revenue Leakage in Mid-Market MSPs; rev.io, Where MSPs Are Losing Money on Billing). Syncro has the time entries and the invoices, but the portal never ranks logged-but-unbilled hours by customer, so the leak stays invisible until a quarter later.
This skill turns that leak - and the other questions an owner keeps re-asking - into one command each:
syncro-cli billing uninvoiced- logged-but-unbilled labor ranked by customersyncro-cli billing drift- closed tickets that had billable time and never got invoicedsyncro-cli billing ar-aging- unpaid invoices bucketed by age, worst firstsyncro-cli tickets aging- open tickets with no recent activity, going stalesyncro-cli assets patch-gaps- assets missing critical patches, ranked across every customer
See pain-point.md for the longer narrative.
Frequently asked questions
Does this work with ChatGPT?
Yes, in the ChatGPT desktop app. It runs MCP servers locally (STDIO), the way syncro-mcp runs, and shares MCP configuration with Codex (OpenAI): add syncro-mcp under Settings > MCP servers as a STDIO server, or add it once to Codex's ~/.codex/config.toml. ChatGPT on the web is not supported by msp-skills yet: it needs a remote (HTTP) server, and this connector's HTTP mode is paused until it is reprinted; the security note in mcp-install.md explains why. If your team works there, a hosted gateway is the better pick; check that your AI app is on the gateway's setup list.
Does this work with Codex, Cursor, Windsurf, Cline, Copilot, or Gemini?
Yes - all of them speak MCP. Cross-tool install commands are in the matrix above and the deep-dive in docs/which-agent.md.
Do I need to know how to code?
No. The recommended install is to paste one sentence into Claude Code or Codex - your agent reads SKILL.md and does the install. The fallback is a one-line installer per OS (bash or PowerShell). Neither path requires writing code. You'll enter your Syncro credentials once.
Is my Syncro data safe?
Your data stays on your machine. The CLI and MCP server are local binaries. The SQLite mirror sits in a directory under your user account. The AI agent only sees what the CLI returns - typically a query result, not raw bulk data. Credentials are read from your environment or your agent's config; never bundled into this repo or transmitted anywhere by MSP Skills.
Will this hit my Syncro API rate limits?
Day-to-day questions read from the local SQLite mirror, not the live API, so they don't touch your rate limit at all. Only sync and explicit live reads call Syncro, and the CLI ships a --rate-limit flag plus response caching to stay polite.
Do I need to be a Syncro partner or on a specific plan?
No. You need a Syncro account and an API token from your own portal (Admin area). It authenticates as you, against your subdomain, with whatever permissions that token is scoped to - no partner program or special tier required.
Will this replace my Syncro portal?
No. It reads from your Syncro account for the cross-customer questions and bulk analysis the portal makes tedious. You still run tickets, billing, and RMM day-to-day in Syncro; this is the fast lane for the questions an owner keeps re-asking.
What does it cost?
Free. Apache-2.0 licensed. You pay only for whichever AI agent you use (Claude, ChatGPT, Codex, etc.), and that's billed by your AI provider, not by us.
Safety model
The strongest control is the scope you grant the Syncro credentials - the CLI can only do what the credentials are permitted to do. Full details, including how to lock it down, are in governance.md.
Status
Beta. Validated against the Syncro API surface and being validated with MSPs running it live against their own production tenant in our weekly Build Sessions. RSVP at compoundingteams.com/build-sessions.
Standards. Conforms to the open Agent Skills spec (Anthropic, Dec 2025; 40+ agents). MCP-compatible - works with any MCP-capable agent including Hermes. OpenClaw-ready (frontmatter pre-wired, awaiting OpenClaw launch).
Maintained by Servosity. Apache-2.0 licensed. Built with CLI Printing Press. Last updated: 2026-06-06.
来源:skills/syncro/README.md,提交 061ec05
工具
0版本历史
4- v0.1.7最新Oct 23, 2026
- v0.1.5Oct 22, 2026
- v0.1.4Oct 16, 2026
- v0.1.3Sep 16, 2026
评分
已满足适用检查项的 40%
该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。
- 近 30 天内可连通25 分
请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。
- 已声明认证方式10 分
请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。
- 已列出工具15 分
请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。
- 描述必需15 分
- 图标10 分
- 文档15 分
- 许可证10 分
请在仓库或注册中心条目中声明许可证。