MSPbots MCP

MSPbots + 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 MSPbots API. Not affiliated with, endorsed by, or sponsored by MSPbots, Inc.

[MSPbots demo - animated preview]

_{▶ Watch the 30-second demo - demo data is simulated; every command shown exists in the real CLI.}

The first MSPbots tool we could find anywhere (June 2026) - readable filters, alias-named resources, full exports, and the KPI history MSPbots itself doesn't keep. 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

The six agents MSP owners actually use (self-serve, works today):

The ChatGPT desktop app runs mspbots-mcp locally and shares MCP configuration with Codex (OpenAI). ChatGPT on the web needs a remote server, which msp-skills does not support 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.md directly 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 .mcpb launches on macOS (Intel and Apple Silicon), Windows x64 and Linux x64. Every tool shells out to the companion mspbots-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 set MSPBOTS_CLI_PATH to an existing binary). Details: #331.

Download MSPbots MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every MSPbots release on the releases page.)

Prefer the Claude Code plugin? Add the marketplace once, then install - works immediately, no directory listing required:

/plugin marketplace add Servosity/msp-skills/plugin install mspbots@msp-skills

Path A - paste one prompt into your AI agent (recommended)

Copy this into Claude Code, Codex CLI, or Claude Cowork:

Install the MSPbots 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/mspbots/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/mspbots/install.ps1 | iex. Then authenticate per the README and run mspbots-cli --help to explore.

The same prompt works in any agent that can run shell.

Path B - run the installer yourself

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/mspbots/install.ps1 | iex

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/mspbots/install.sh)

The installer drops both mspbots-cli (the CLI) and mspbots-mcp (the MCP server) into your user bin path. Claude Code, Codex, and Cowork discover the Skill via SKILL.md in this directory.

Verify:

mspbots-cli --version

Upgrade to the latest version

The installer always fetches the current release - re-run it to upgrade:

macOS / Linux:

bash <(curl -fsSL https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/mspbots/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/mspbots/install.ps1 | iex

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 mspbots@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:

hermes skills install servosity/msp-skills/skills/mspbots --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/mspbots --force

Hermes speaks MCP natively, so it can also use the mspbots-mcp server directly - same install path, same env vars.

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the mspbots skill from https://github.com/servosity/msp-skills/tree/main/skills/mspbots. The skill defines how its required CLI (mspbots-cli) can be installed via the openclaw: 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 MSPbots portal):

MSPBOTS_API_KEY=<value> mspbots-cli doctor

doctor checks config, paths, and API reachability and reports whether a credential is loaded. The MSPBots API exposes no argument-free GET endpoint, so doctor cannot verify the key itself - it says not verified rather than claiming health. Run any read command to confirm the key works end-to-end.

What this skill does

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

There was no MSPbots tool to be different from - as of June 2026 we could find no published CLI, SDK, or MCP server for the MSPbots Public API. And a thin wrapper would inherit everything painful about that API: two endpoints, 19-digit resource IDs, comma-encoded filters, no list endpoint, no metadata, no history. It dies the moment you ask "is our backlog up or down versus last week" - the API only knows now.

This skill adds the missing layers locally. registry add gives resources names instead of snowflake IDs. pull --where "Update Date >= 2026-06-01" compiles readable predicates into the wire DSL. export walks every page automatically. And snapshot + diff + trend keep timestamped copies in a local SQLite store - the KPI history MSPbots itself doesn't keep, computed offline with zero API calls.

The pain this closes

MSPbots' own Public API documentation (the wiki.mspbots.ai Public API article, archived April 2024) describes the entire programmatic surface: two GET endpoints, resource IDs copied one at a time out of Settings > Public API, filters encoded as comma-rules in query params, rate limits with unspecified numbers, and intermittent HTTP 502s on heavy widget fetches. No history, no enumeration, no tooling - not even a curl gist.

So the ops manager who lives in MSPbots dashboards keeps the week-over-week column by hand: screenshot the widget on Monday, paste the count into a spreadsheet, repeat. The trend dies the week someone forgets.

• mspbots-cli snapshot open_tickets - capture a timestamped copy of any dataset or widget into local SQLite. Schedule it and history accrues.
• mspbots-cli trend open_tickets --agg count - the week-over-week answer, computed from your snapshots, offline.
• mspbots-cli diff open_tickets - row-level added/removed/changed between any two snapshots.
• mspbots-cli pull open_tickets --where "Update Date >= 2026-06-01" - readable filters compiled into the comma-encoded DSL, correct the first time.
• mspbots-cli export open_tickets --format csv - the full table, auto-paginated, with an honest partial-dump flag when a page cap is hit.

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 mspbots-mcp runs, and shares MCP configuration with Codex (OpenAI): add mspbots-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 server. 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 MSPbots credentials once.

Is my MSPbots 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.

Can this write to MSPbots?

No. The MSPbots Public API is read-only - datasets and widgets out, nothing in. The only things this skill writes are local: alias registrations, snapshots, and the sync cache in your own SQLite store. No command can change anything in your MSPbots tenant.

What credentials do I need?

An MSPbots API key: an admin creates it at Settings > Public API in the MSPbots app and binds each dataset or widget to it. Set MSPBOTS_API_KEY in your environment or run mspbots-cli auth set-token. The binding is the permission boundary - the key can only read resources explicitly bound to it, and the global Enable Public API toggle gates everything.

Why do I register datasets before pulling them?

The Public API has no list endpoint - it cannot tell you what is bound to your key. You copy each resource ID from Settings > Public API once, register it with mspbots-cli registry add open_tickets <resourceId>, and every other command accepts the alias from then on.

Will this hit MSPbots rate limits?

The API documents rate limits without publishing numbers. The CLI ships a --rate-limit throttle, export bounds its page-walking with --max-pages and reports when the cap was hit, and the history questions (trend, diff) run entirely against local snapshots - zero API calls after capture.

Does it support widgets as well as datasets?

Yes - pull, export, snapshot, describe, and registry add all accept --type widget. One documented exception inherited from the API: widgets with measure or calculate layers are not supported by the Public API itself.

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 MSPbots 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 MSPbots 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: 2026-06-05.