AI agents call resolve_capability to retrieve information from Unfragile without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool resolves a URI or natural-language input into a ranked list of AI artifacts. This is purely a read/query operation with no side effects, no data modification, and no execution of code. It is analogous to a search or lookup function. Severity is low because misuse would at worst return irrelevant results.
From the tool's definition 'Resolve a capability:// URI or natural-language capability into ranked AI artifacts' — this is a lookup/search operation that retrieves and ranks existing artifacts
Attacks that exploit this kind of access
Resolve a capability:// URI or natural-language capability into ranked AI artifacts. This is Unfragile. It is categorised as a Read tool in the Unfragile MCP Server, which means it retrieves data without modifying state.
Register the Unfragile MCP server in PolicyLayer and add a rule for 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 Unfragile. Nothing to install.
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 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 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.
resolve_capability is provided by the Unfragile MCP server (savirinc/unfragile-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 →