Hosting & data

A check contains your agent's tool call and the user's request, which can be sensitive. Here is where it goes and what we keep.

Where a check runs

PartMeaning
API edgeCloudflare (api.mcp-guard.ai): authentication, rate limiting, validation and billing.
InferenceOur GPUs in Switzerland. The model runs there; no third-party model API is called.
Account dataSupabase, EU (Zurich region): your account, workspaces, API key hashes, credit balance and usage records.

What we keep

DataMeaning
PayloadsNot stored. The action, intent, context and conversation you send are used to answer the request and then dropped.
MetadataKept 30 days: request id, API key id, endpoint, status or error code, latency, number of checks and credits charged. It powers the usage view and billing.
API keysOnly a hash and a short prefix are stored; the full key is shown once when you create it.

Details, sub-processors and your rights are in the privacy policy. Questions: support@mcp-guard.ai.

Sending less

The model reads about 384 tokens per check, so a long conversation or a full document adds little. Send the tool call, the user's request and a line of context. Redact secrets in arguments when the decision does not depend on them (the guard needs to know an email is being sent to an outside address, not the API token in the header).