Install
$ agentstack add skill-wyre-ai-msp-claude-plugins-api-patterns ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Blackpoint Cyber (CompassOne) MCP Tools & API Patterns
Overview
Blackpoint Cyber is a managed detection and response (MDR) provider. The CompassOne portal exposes a partner-tenant-asset hierarchy: a partner (the MSP) sees many tenants (their customers), each tenant has many assets (endpoints, identities, cloud accounts), and detections / vulnerabilities are produced against those assets.
Connection & Authentication
Blackpoint uses an API token passed via header. CompassOne issues the token in the partner portal.
| Header | Value | |--------|-------| | X-Blackpoint-Api-Token | The raw CompassOne token |
The gateway maps the environment variable BLACKPOINT_API_TOKEN onto the X-Blackpoint-Api-Token header automatically. Internally, the Blackpoint MCP server forwards this to CompassOne as a Bearer token — you do not need to add the Bearer prefix yourself.
export BLACKPOINT_API_TOKEN="your-compassone-token"
Optional: BLACKPOINT_BASE_URL overrides the CompassOne base URL for regional or partner-specific deployments.
Hierarchy
Partner (MSP)
└── Tenant (customer)
└── Asset (endpoint / identity / cloud account)
└── Detections / Vulnerabilities
Always pivot top-down: identify the tenant first, then drill into assets, then look at detections/vulnerabilities for that asset.
Navigation Tools
| Tool | Purpose | |------|---------| | blackpoint_navigate | Discover available domains | | blackpoint_back | Pop back to the prior context | | blackpoint_status | Health/status check |
Functional Tool Surface (today)
Tools follow blackpoint__. Currently functional domains:
tenantsassetsdetectionsvulnerabilities
Additional domains (alerts, cloud security, notifications, partners, threat intel, tickets) are stubbed in the MCP server but not yet implemented — do not call those.
Pagination
Blackpoint list endpoints use page/limit-style pagination. Always check whether more pages exist before claiming a result is complete, especially for detections and vulnerabilities — those can run into the thousands.
Error Handling
| Status | Meaning | Action | |--------|---------|--------| | 401 | Bad/missing Bearer token | Re-check BLACKPOINT_API_TOKEN | | 403 | Token valid but no access to the requested tenant | Check partner-tenant scoping | | 404 | Unknown tenant / asset / detection | Re-list to confirm | | 429 | Rate limit | Back off and retry |
Best Practices
- For incident-response work, always list the affected tenant's
assets and detections together — a detection without its asset context is hard to action.
- For multi-tenant rollups (partner view), iterate
blackpoint_tenants_list first and then drill in per-tenant.
- The current tool surface is read-only — there are no write tools
yet. Any "respond to detection" workflow must happen in the CompassOne portal itself.
Related Skills
- [incident-response](../incident-response/SKILL.md) - Primary investigation skill
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: WYRE-AI
- Source: WYRE-AI/msp-claude-plugins
- License: Apache-2.0
- Homepage: https://mcp.wyre.ai/getting-started/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.