DRIFT DETECTION — audit a batch of AI-stated facts against live ground-truth in one call. Pass claims (a list of statements an LLM produced) or text (a paragraph that's split into claims); each is fact-checked and graded — drifted / confirmed / unverifiable, with a severity — plus a summary (drif...
Part of the Dynamic Feed server.
Free to start. No card required.
AI agents call detect_drift to retrieve information from Dynamic Feed 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 detect_drift 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": {
"detect_drift": {}
}
}See the full Dynamic Feed policy for all 50 tools.
These attack patterns abuse exactly the kind of access detect_drift 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.
DRIFT DETECTION — audit a batch of AI-stated facts against live ground-truth in one call. Pass claims (a list of statements an LLM produced) or text (a paragraph that's split into claims); each is fact-checked and graded — drifted / confirmed / unverifiable, with a severity — plus a summary (drifted_count, overall). Use it to self-audit an answer before sending it. Args: claims: list of statements to check. text: alternatively, a paragraph that gets split into claims.. It is categorised as a Read tool in the Dynamic Feed MCP Server, which means it retrieves data without modifying state.
Register the Dynamic Feed MCP server in PolicyLayer and add a rule for detect_drift: 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 Dynamic Feed. Nothing to install.
detect_drift 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 detect_drift 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 detect_drift. 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.
detect_drift is provided by the Dynamic Feed MCP server (https://dynamicfeed.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 50 Dynamic Feed 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.