Pin and re-check a 16-string canary against the active embedding provider. Catches silent provider model swaps (OpenAI/Voyage/etc.) that quietly degrade hybrid retrieval. First call (or with capture=true) saves the baseline; subsequent calls report max cosine distance vs baseline. Read-only or wr...
AI agents call check_embedding_drift to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While the tool has a write component (capture=true saves baseline), its core purpose is monitoring and diagnostics—reading embedding data and comparing it to detect drift. The write operation is administrative baseline-setting, not a business-logic mutation. The 'read-only' framing in the description emphasizes the default behavior. No code execution, deletion, or external effects triggered by the results.
From the tool's definition Tool performs 'pin and re-check' with 'read-only or write-only (capture)' modes. The capture mode saves a baseline (write operation), but the primary function is checking/comparing embeddings against a baseline—a retrieval and analysis task.
Documented attack patterns abuse exactly the kind of access check_embedding_drift gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for check_embedding_drift:
{
"version": "1",
"default": "deny",
"tools": {
"check_embedding_drift": {}
}
}check_embedding_drift is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Pin and re-check a 16-string canary against the active embedding provider. Catches silent provider model swaps (OpenAI/Voyage/etc.) that quietly degrade hybrid retrieval. First call (or with capture=true) saves the baseline; subsequent calls report max cosine distance vs baseline. Read-only or write-only (capture). Returns JSON: { status, message, max_distance?, mean_distance?, per_string? }. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for check_embedding_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 Trace. Nothing to install.
check_embedding_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 check_embedding_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 check_embedding_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.
check_embedding_drift is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.