Keeper Security MCP

Keeper Security + AI - for ChatGPT, Claude, GitHub Copilot, Microsoft 365 Copilot, Gemini, and any agent that speaks MCP

Unofficial. Community-built Claude Code Skill and MCP server for the Keeper Security API. Not affiliated with, endorsed by, or sponsored by Keeper Security, Inc.

[Keeper Security demo - animated preview]

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

Read-only Keeper MSP posture across every client, with history, a change feed and no path to a vault secret. Works with the AI you already use - ChatGPT (Plus/Pro+), Claude Desktop, Codex, Claude Code, Claude Cowork, and GitHub Copilot - plus Microsoft 365 Copilot / Copilot Studio and Google Gemini via the remote path. 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):

For ChatGPT, run keeper-mcp --transport http with KEEPER_MCP_HTTP_TOKEN set, on an HTTPS host; every request sends that token. See mcp-install.md.

Also for the Microsoft and Google stacks

Big install base, but an honest heads-up: these are the remote / enterprise path, not the local binary you just installed.

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

Download Keeper Security MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every Keeper Security 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 keeper@msp-skills

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

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

Install the Keeper Security 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/keeper/install.sh). If it uses Windows PowerShell, run iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/keeper/install.ps1 | iex. Then authenticate per the README and run keeper-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/keeper/install.ps1 | iex

macOS / Linux:

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

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

Verify:

keeper-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/keeper/install.sh)

Windows (PowerShell):

iwr -useb https://raw.githubusercontent.com/Servosity/msp-skills/main/skills/keeper/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 keeper@msp-skills.

Add to Claude Desktop, GitHub Copilot, Gemini CLI, Microsoft 365 Copilot, 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 remote Microsoft 365 Copilot / Copilot Studio path. 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/keeper --force

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/keeper --force

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

Install for OpenClaw

Tell your OpenClaw agent (copy this):

Install the keeper skill from https://github.com/servosity/msp-skills/tree/main/skills/keeper. The skill defines how its required CLI (keeper-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 Keeper Security portal):

KEEPER_API_KEY=<value> KEEPER_BASE_URL=<value> keeper-cli doctor

doctor checks config and paths, then tests the API key with one read of Service Mode's queue status, so it tells a working key from a rejected one and a wrong base URL. A Service Mode in legacy mode has no queue status, so there doctor says it could not test the key. That read runs no Commander command, so run a real read such as keeper-cli companies list to confirm the key's -c allowlist.

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

Most password-manager integrations, and an MCP server that only forwards each tool call, answer about one tenant now. That's fine for one user. It stops working when a QBR asks which of 40 clients have admins without 2FA and what moved since last quarter.

posture report reads every managed company in one run through your own Commander Service Mode host and stores the run in a local SQLite file. posture diff, users risk, users hygiene, users find and events list then answer from that file: instant, offline, and the AI sees the answer. Typed reads such as users list go live and are not saved.

Every command it can send is on a short fixed allowlist (keeper-cli allowlist), each with fixed read-only flags, and arguments cannot add a flag or a second command. There is no path to a vault record.

The pain this closes

Keeper's password-health and 2FA views are read per tenant (one 2026 review for MSPs describes them as "per tenant"), and comparing against last quarter means keeping the earlier numbers yourself.

• posture report: every client's 2FA, password health, BreachWatch, inactivity and seats, in one run
• posture diff: per-company deltas and per-user changes, such as 2FA turned off
• users risk --kind no-2fa: users with 2FA off across every client, admins first
• users hygiene: stale invites, locked, inactive and pending-transfer users
• events list: change events once each, for automation

See pain-point.md for the longer narrative.

Frequently asked questions

Does this work with ChatGPT?

Yes, on Plus, Pro, Team, Business, Enterprise, and Education plans (Free tier does not yet expose Developer Mode). ChatGPT connects to remote MCP servers over HTTPS, not local stdio binaries. The Keeper Security MCP server runs locally over stdio by default. Its HTTP mode (keeper-mcp --transport http) serves http://127.0.0.1:7777/mcp, refuses to start until KEEPER_MCP_HTTP_TOKEN is set, requires Authorization: Bearer <token> on every request, and needs --tls-cert/--tls-key for any other address. See mcp-install.md. Step-by-step in mcp-install.md.

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 Keeper Security credentials once.

Is my Keeper Security data safe?

Your data stays on your machine and your own Service Mode host. Typed reads print and are not saved; only posture report saves metrics and per-user facts to a local SQLite file under your user account. The AI agent only sees what the CLI returns. The API key is sent only to KEEPER_BASE_URL, and is withheld from every output, log, file and MCP result. It is never bundled into this repo or sent anywhere by MSP Skills.

Can this read passwords from a client's vault?

No. It can send only the admin and MSP reports keeper-cli allowlist prints, each with fixed read-only flags, and a response shaped like record content is refused whole. Set the same list on your Service Mode key with service-create -c, so Service Mode refuses anything else too.

What do I need from Keeper?

Keeper Commander running in Service Mode on a host you control, over TLS (service-create with -crtf and -crtp), and its API key. Service Mode defaults to plain http; this CLI refuses plain http on every host, localhost included, so the key is never sent in clear. Trust a private certificate with KEEPER_CA_CERT.

Do I need a Keeper MSP account?

The cross-client commands need one. An account that is not an MSP is reported as its own enterprise, one company in the same format.

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

This connector has no write path to Keeper. Scope the Service Mode key to the same command list with service-create -c, so the key itself cannot do more. Full details, including how to lock it down, are in governance.md.

Status

Beta. Validated against the Keeper Security 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: 2026-11-04.