Blackpoint Cyber CompassOne MCP

Blackpoint Cyber CompassOne + 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 Blackpoint Cyber API. Not affiliated with, endorsed by, or sponsored by Blackpoint Cyber.

[Blackpoint Cyber demo - animated preview]

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

CompassOne from the terminal: tenants, detections, assets, vulnerabilities, posture, reports and Cloud Response admin, plus a cross-tenant fleet view of open detections, stale agents and coverage gaps. 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 blackpoint-mcp --transport http with BLACKPOINT_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 Blackpoint Cyber MCP (.mcpb) - then open Claude Desktop > Settings > Extensions and select the file. One click, no JSON, no shell. (Browse every Blackpoint Cyber 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 blackpoint@msp-skills

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

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

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

macOS / Linux:

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

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

Verify:

blackpoint-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/blackpoint/install.sh)

Windows (PowerShell):

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

Inside a Hermes chat session:

/skills install servosity/msp-skills/skills/blackpoint --force

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

Install for OpenClaw

Tell your OpenClaw agent (copy this):

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

BLACKPOINT_API_TOKEN=<value> blackpoint-cli doctor

doctor checks config, paths, and API reachability, then sends one authenticated read and reports the credential as valid, rejected (401), scope-limited (403), or pointed at the wrong base URL (404).

What this skill does

The cross-tenant commands (triage, stale-agents, gaps, cve-spread, leaderboard, geo-audit, overview) read the local mirror: run blackpoint-cli fleet-sync first, and again whenever you want fresh numbers. Before the first sync they return an empty list with a hint on stderr. client-report and the endpoint commands call the API live.

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 Blackpoint Cyber 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 "which open detection, across all 40 of my CompassOne tenants, has waited longest?" Every CompassOne detection, asset, vulnerability and scan call is scoped to one tenant, so the live answer is one call per customer.

This skill syncs Blackpoint Cyber 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 triage, gaps and cve-spread join across every tenant's detections, devices, vulnerabilities, scans, contact groups and posture ratings - work a stateless API wrapper can't do.

The pain this closes

CompassOne is built tenant by tenant: every detection, asset, vulnerability, scan and report call names one customer tenant (the API's x-tenant-id header), and the portal views follow the same shape. Reviews of Blackpoint for MSPs say the same thing from the operator's side: Flamingo's Blackpoint Cyber review notes reviewers find the partner portal "less polished than the detection engine behind it, with a learning curve on reporting and day-to-day navigation." At 30 or 80 customers, "which fire do I put out first?" and "who has no coverage?" become a tab-by-tab exercise.

This skill closes that gap:

• One detection queue for every client - blackpoint-cli triage --older-than 24h lists open detections across all tenants, oldest first, with tenant, age, alert count and ticket status.
• Agents that went quiet - blackpoint-cli stale-agents --days 14 lists devices across every tenant whose agent has not reported, with Defender status.
• Coverage gaps before an incident finds them - blackpoint-cli gaps --scan-days 30 flags tenants with no recent completed scan, no or empty escalation contact group, or no posture rating.
• Which patch campaign helps the most customers - blackpoint-cli cve-spread --exploited ranks exploited CVEs by tenants and assets affected.
• Client reporting in one call - blackpoint-cli client-report "Acme Dental" --since 30d gathers detection count and weekly trend, top entities and threats, posture and report runs for one customer.

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 Blackpoint Cyber MCP server runs locally over stdio by default. Its HTTP mode (blackpoint-mcp --transport http) serves http://127.0.0.1:7777/mcp, refuses to start until BLACKPOINT_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 Blackpoint Cyber credentials once.

Is my Blackpoint Cyber 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.

What Blackpoint access do I need?

A CompassOne API token, created in the CompassOne portal under API tokens. A partner token reaches every customer tenant; a tenant token sees one customer. A read-only partner token is enough for every read and rollup command. Some routes need entitlements: a 403 on vulnerabilities or users means the account is not entitled, and fleet-sync records that tenant's slice as failed instead of empty.

Will this hit my Blackpoint API rate limits?

The key quota is 2000 requests per 15 minutes. fleet-sync makes one or more calls per tenant and data kind, so on a large fleet limit it with --tenant and --kinds. After a sync, triage, gaps, stale-agents, cve-spread, leaderboard, geo-audit and overview read the local mirror and make no API calls; client-report and the endpoint commands call the API live.

Will this replace the CompassOne portal?

No. The portal stays your console for investigations, Cloud Response configuration and reports. This connector answers the questions that span customers, and gives your AI agent a safe, previewable path to the few changes the API allows.

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

These policies are yours to apply in your agent setup; the binary does not enforce the Credential tier. The MCP server answers darkweb-exposures reads even with BLACKPOINT_MCP_READ_ONLY=1 (read-only mode drops writes, not reads). Each breached password and each Duo secret key is replaced by [withheld] before any output, in every mode, and is never written to the response cache or the local store: read a breached password in the CompassOne portal.

From the CLI, a write sends as soon as you run it: pass --dry-run first to preview the exact request. Over MCP, every write returns a preview until the call passes confirm: true, and BLACKPOINT_MCP_READ_ONLY=1 hides every write tool.

The strongest control is the scope you grant the Blackpoint Cyber 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 Blackpoint Cyber 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: 2026-10-28.