Free. TensorFeed's signed ruling on whether an AI benchmark is still a trustworthy capability signal or saturated, contaminated, or near ceiling so a high score should be down-weighted. Returns a trust band (reliable, use_with_caution, saturated, contaminated, deprecated) and a 0-100 trust score ...
Part of the TensorFeed server.
Free to start. No card required.
AI agents call benchmark_trust_verdict_preview to retrieve information from TensorFeed 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 benchmark_trust_verdict_preview 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.
{
"version": "1",
"default": "deny",
"tools": {
"benchmark_trust_verdict_preview": {}
}
}See the full TensorFeed policy for all 79 tools.
These attack patterns abuse exactly the kind of access benchmark_trust_verdict_preview gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Free. TensorFeed's signed ruling on whether an AI benchmark is still a trustworthy capability signal or saturated, contaminated, or near ceiling so a high score should be down-weighted. Returns a trust band (reliable, use_with_caution, saturated, contaminated, deprecated) and a 0-100 trust score per benchmark. Pass benchmark to narrow to one, or category to filter, or neither for the registry. For the per-signal detail (ceiling proximity, frontier compression, contamination) and the down-weight recommendation with an alternative, use benchmark_trust_verdict. 10 calls per day per IP.. It is categorised as a Read tool in the TensorFeed MCP Server, which means it retrieves data without modifying state.
Register the TensorFeed MCP server in PolicyLayer and add a rule for benchmark_trust_verdict_preview: 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 TensorFeed. Nothing to install.
benchmark_trust_verdict_preview 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 benchmark_trust_verdict_preview 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 benchmark_trust_verdict_preview. 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.
benchmark_trust_verdict_preview is provided by the TensorFeed MCP server (https://mcp.tensorfeed.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 79 TensorFeed tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.