api-patterns
3CX's native PBX MCP server: the per-PBX endpoint shape (every PBX is its own FQDN and its own OAuth authorization server — there is no shared mcp.3cx.com),…
Tracing a compliance control (CIS, SOC 2, HIPAA, or a cyber-insurance questionnaire line item) to concrete, retrievable tool evidence: which vendor family can observe what — CIPP for live M365/Entra configuration, Liongard for point-in-time infrastructure state, IT Glue/Hudu for
$ npx -y skills add wyre-technology/msp-claude-plugins --skill evidence-mapping --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/evidence-mappingContext preview
The summary Claude sees to decide when to auto-load this skill.
Tracing a compliance control (CIS, SOC 2, HIPAA, or a cyber-insurance questionnaire line item) to concrete, retrievable tool evidence: which vendor family can observe what — CIPP for live M365/Entra configuration, Liongard for point-in-time infrastructure state, IT Glue/Hudu for
name: "Evidence Mapping" description: > Tracing a compliance control (CIS, SOC 2, HIPAA, or a cyber-insurance questionnaire line item) to concrete, retrievable tool evidence: which vendor family can observe what — CIPP for live M365/Entra configuration, Liongard for point-in-time infrastructure state, IT Glue/Hudu for documentation — a representative control-to-tool-call map, and the evidentiary weights that separate Configured from Documented, Contradicted, and Unable to Verify. when_to_use: >- When mapping a named control or questionnaire line item to live tool evidence, when deciding whether a piece of evidence proves configuration or only proves documentation, or when assembling a source-cited evidence package for an audit. Use when: compliance evidence, control evidence, evidence mapping, map this control, what proves this control, audit evidence, evidence source, is this control met, documented vs enforced, policy vs configuration.
Every compliance framework and every cyber-insurance questionnaire ultimately reduces to the same operation: take a control statement in English ("MFA is enforced for all users," "access to PHI systems is logged," "endpoint detection and response is deployed fleet-wide") and produce evidence that either supports or contradicts it. The failure mode this skill exists to prevent is answering from a policy document, a vendor's marketing claim, or a technician's recollection when a live tool query would give a verifiable answer. If a tool can answer it, pull the tool. If no connected tool can answer it, say so explicitly — never fill the gap with an assumption.
Evidence in an MSP's toolchain comes from three vendor families, each proving a different kind of thing:
Treat these as different evidentiary weights, not interchangeable sources.
models risks, controls, evidence, policies, and framework objectives per client; use `scalepad-controlmap` when working inside that product. This skill maps a control statement onto live queries across whatever happens to be connected.
inspection state, or a document is that connector's surface; use `cipp-standards`, `liongard-systems`, or `itglue-documents`.
This is the single most important judgment call in evidence mapping, and getting it wrong is what turns an evidence package into a liability during an actual audit.
When assembling an evidence package, always label each piece of evidence with which of these three states it represents. Never let a documentation hit stand in for a configuration check when a configuration check is possible. If only documentation is available (no connector exists for the underlying system), say the control is "documented, unverified" — not "met."
| Control (typical phrasing) | Vendor family | Tool calls | Evidence type | |---|---|---|---| | MFA enforced for all users | CIPP | `cipp__list_mfa_users`, `cipp__list_conditional_access_policies` | Configured | | Conditional access restricts legacy auth / risky sign-in | CIPP | `cipp__list_conditional_access_policies`, `cipp__list_named_locations` | Configured | | Tenant meets baseline security standards (CIS-aligned) | CIPP | `cipp__list_standards`, `cipp__run_standards_check`, `cipp__list_bpa` | Configured | | Email authentication (SPF/DKIM/DMARC) configured | CIPP | `cipp__list_domain_health` | Configured | | Privileged/admin access is scoped and reviewed | CIPP | `cipp__list_gdap_roles`, `cipp__list_groups`, `cipp__list_users` | Configured | | Access and admin activity is logged | CIPP | `cipp__list_audit_logs`, `cipp__list_logs` | Configured | | Server/network baseline configuration is known and current | Liongard | `liongard__systems_list`, `liongard__inspections_run`, `liongard__environments_get` | Configured (point-in-time) | | Device and identity inventory is current | Liongard | `liongard__inventory_devices`, `liongard__inventory_identities` | Configured | | A named policy/procedure exists (IR plan, access policy, patch policy) | IT Glue / Hudu | `itglue__search_documents`, `itglue__get_document` | Documented | | Configuration item is recorded with current state | IT Glue | `itglue__search_configurations`, `itglue__get_configur
One command to supercharge Claude Code for MSP workflows. Then restart Claude Code. That's it. Documentation: mcp.wyre.ai
Repo: wyre-technology/msp-claude-plugins
3CX's native PBX MCP server: the per-PBX endpoint shape (every PBX is its own FQDN and its own OAuth authorization server — there is no shared mcp.3cx.com),…
3CX's live-operations surface: read-only visibility into active calls, recordings, voicemail, department and queue membership, and forwarding/presence…
3CX's read-only directory surface: resolving a caller by email or by exact extension, searching the PBX's own phonebooks, searching contacts synced from an…
3CX's system-and-configuration surface: server time, PBX event log and application log search, service status, database schema and the read-only SELECT-only…
Abnormal Security abuse mailbox cases: user-reported email submissions, case statuses and judgments, the case lifecycle, bulk and remediation actions, and…
Abnormal Security message analysis: message retrieval, email header inspection, attachments, sender reputation, delivery context, and SPF/DKIM/DMARC…