Resolve a planning-time capability gap into a selected TokRepo asset, verification evidence, and install plan. Use this as the default first action when the agent identifies a missing skill, MCP, prompt, script, workflow, or reusable capability. Read-only.
AI agents call tokrepo_resolve_capability to retrieve information from TokRepo — AI Asset Registry without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is explicitly marked read-only and its function is to identify and select an asset plus generate an install plan, without actually executing any installation or write operation. It returns information (selected asset, verification evidence, install plan) for downstream use. Severity is low because misuse would only result in inappropriate asset recommendations, not direct system changes.
From the tool's definition 'Read-only' explicitly stated in description; 'Resolve a planning-time capability gap into a selected TokRepo asset, verification evidence, and install plan' — resolves/selects but does not install or modify anything
Attacks that exploit this kind of access
Resolve a planning-time capability gap into a selected TokRepo asset, verification evidence, and install plan. Use this as the default first action when the agent identifies a missing skill, MCP, prompt, script, workflow, or reusable capability. Read-only. It is categorised as a Read tool in the TokRepo — AI Asset Registry MCP Server, which means it retrieves data without modifying state.
Register the TokRepo — AI Asset Registry MCP server in PolicyLayer and add a rule for tokrepo_resolve_capability: 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 TokRepo — AI Asset Registry. Nothing to install.
tokrepo_resolve_capability 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 tokrepo_resolve_capability 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 tokrepo_resolve_capability. 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.
tokrepo_resolve_capability is provided by the TokRepo — AI Asset Registry MCP server (tokrepo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →