Check if a capability is reliable before calling it. Returns SQS quality score (0-100), Quality grade (A-F for code correctness), Reliability grade (A-F for uptime and latency), and execution guidance: whether to call directly, retry with backoff, queue for later, or use a fallback. Also returns ...
Part of the Strale MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call strale_trust_profile to retrieve information from Strale without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though strale_trust_profile only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
strale_trust_profile:
rules:
- action: allowSee the full Strale policy for all 8 tools.
Agents calling read-class tools like strale_trust_profile have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Check if a capability is reliable before calling it. Returns SQS quality score (0-100), Quality grade (A-F for code correctness), Reliability grade (A-F for uptime and latency), and execution guidance: whether to call directly, retry with backoff, queue for later, or use a fallback. Also returns 30-day test pass rate, known limitations, and cost envelope. Use this to decide whether a capability is safe for production use right now.. It is categorised as a Read tool in the Strale MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for strale_trust_profile. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Strale MCP server.
strale_trust_profile 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 strale_trust_profile rule in your Intercept 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 Intercept policy for strale_trust_profile. 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.
strale_trust_profile is provided by the Strale MCP server (strale-io/strale). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept