list_capabilities
Traverse the capability spine joining books, guides (capability packages), KSAO-grade elements and jobs. Use min_guides=2 for the cross-cutting capabilities that span many guides, role=<role> for what a job requires, capability_detail=<slug> for one package with its elements and books hydrated. k...
This record as markdown: /tools/com-aiengineerprofessional-guide-registry/list-capabilities.md
What list_capabilities does on Guide Registry
AI agents call list_capabilities to retrieve information from Guide Registry without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
q | string | — | Substring match on the element label. |
role | string | — | Elements required by this job role, e.g. compensation-analyst. |
limit | number | — | Cap the rows returned (default 200). `total` always reports the true count. |
has_job | boolean | — | Only elements that some job requires (via a career guide). |
ksao_type | string | — | knowledge | skill | ability | other — from a panel validated at 95.1% on gold O*NET labels. 'other' is UNVALIDATED (no gold labels existed for it). |
capability | string | — | Elements taught by this capability (guide slug). |
min_guides | number | — | Only elements taught by >= N capabilities. 2 gives the cross-cutting spine. |
conflicting | boolean | — | Only elements where 2+ non-career guides define the same label differently — these need a ruling. |
construct_class | string | — | person-attribute (knowledge/skill/ability — what a JOB requires and a learner develops) | condition-or-outcome (what a capability PRODUCES, e.g. 'Retention & Wo |
capability_detail | string | — | Return ONE capability with its elements and books hydrated, instead of querying elements. |
has_canon_identity | boolean | — | true = only elements resolved to a JobFrame canon component (an IDENTITY, panel-adjudicated). false = only unresolved. |
canon_promotion_candidate | boolean | — | true = only elements the JobFrame canon has NO component for. This is a real answer, not a failed lookup — these are the constructs to PROMOTE into the canon. |
Parameters from the server's own tool schema.
Why list_capabilities is rated Low
Even though list_capabilities only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsHigh parameter count (12 properties)
Attacks that exploit this kind of access
The rule that runs list_capabilities safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Guide Registry, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_capabilities, this is the rule to start with:
list_capabilities is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Guide Registry, apply this rule, and every list_capabilities call is checked against it from then on.
Questions about list_capabilities
Traverse the capability spine joining books, guides (capability packages), KSAO-grade elements and jobs. Use min_guides=2 for the cross-cutting capabilities that span many guides, role=<role> for what a job requires, capability_detail=<slug> for one package with its elements and books hydrated. ksao_type/canon_component_id are null by design where unresolved — treat null as 'not yet joined', never as 'no link'. It is categorised as a Read tool in the Guide Registry MCP Server, which means it retrieves data without modifying state.
list_capabilities accepts 12 parameters: q, role, limit, has_job, ksao_type, capability, min_guides, conflicting, construct_class, capability_detail, has_canon_identity, canon_promotion_candidate. The full parameter table on this page comes from the server's own tool schema.
Register the Guide Registry MCP server in PolicyLayer and add a rule for list_capabilities: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Guide Registry. Nothing to install.
list_capabilities is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_capabilities rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_capabilities. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_capabilities is provided by the Guide Registry MCP server (https://aiengineerprofessional.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Guide Registry, and thousands of servers like it.
This server
Across the catalogue