Governance

Tracker & rate guard

Budgets, alerts, and signed usage events keep MCP calls predictable—even when multiple clients share the same server URL.

Tracker & guard acts like a copilot for finance and ops. It watches budgets per office, user, tool, vendor, model, and time window, and it logs every call with enough metadata to satisfy auditors.

Preflight → Postflight loop

Every MCP call starts with a policy read. Tracker & guard checks counters scoped to office, user, tool, vendor, model, and time window. It also confirms consent scopes remain valid. Only then does the tool execute.

After execution, the postflight service signs the event, updates counters, and streams alerts if thresholds are crossed. Finance teams can trust the ledger because each step is deterministic.

Prevent surprise bills: nothing runs without budget headroom, and every call logs cost + consent for auditors.
  • read policy & counters
  • check consent scopes
  • decide pass/queue/deny

Budgets, alerts, and backoff

Budgets layer by layer: daily, monthly, per-call maxima, burst buffers, and vendor-aware backoff. Ops can raise or lower any budget mid-month, and the new limits apply immediately across every client.

  • daily caps
  • monthly caps
  • per-call max
  • burst buffers
  • vendor-aware backoff
  • soft at 80%
  • hard at 100% with admin override
  • spike on throttle/error/latency

Live dashboard

The dashboard shows usage by office and tool, vendor health, cost trends, hot users, failures, queued calls, and controls to edit limits or add credit. Because the MCP server feeds the same ledger, you never reconcile multiple reports.

  • live usage by office & tool
  • vendor health & headroom
  • cost trend
  • hot tools/users
  • failed/queued calls
  • edit limits/add credit/pause tool/export for billing

Usage event schema

These fields land in your warehouse or SIEM. They power compliance (prove who ran which tool), operations (watch latency + cost spikes), and product (spot hot tools).

json
{
  "event_id": "evt_98f4",
  "ts_utc": "2025-01-12T19:22:04Z",
  "actor_id": "agent_447",
  "role": "Agent",
  "office_id": "austin_downtown",
  "tool_name": "generate_sales_comps_pdf",
  "vendor_name": "atlas_default",
  "model_name": "gpt-4o-mini",
  "subject_ref": "txn_A123",
  "input_tokens": 1200,
  "output_tokens": 1850,
  "input_bytes": 34210,
  "output_bytes": 57210,
  "api_cost_usd": 0.74,
  "atlas_fee_usd": 0.21,
  "total_cost_usd": 0.95,
  "rate_bucket": "office.daily",
  "rl_allowed": true,
  "rl_action": "pass",
  "latency_ms": 2410,
  "cache_hit": false,
  "success": true,
  "artifact_uri": "atlas://artifacts/txn_A123/comps_240112.pdf",
  "consent_scopes": [
    "mls.read",
    "atlas.data"
  ],
  "signature": "0xb2f1...c9"
}
Sample signed event
Usage event fields
FieldDescription
event_idSigned UUID per call
ts_utcTimestamp the call completed
actor_idUser or bot that triggered the tool
roleActor role (Owner/Admin/Client)
office_idOffice or team identifier for budgets
tool_nameCanonical tool name
vendor_nameDownstream vendor (Atlas default or partner)
model_nameLLM or automation model invoked
subject_refTransaction/Item/File reference
input_tokensNumber of model input tokens
output_tokensNumber of model output tokens
input_bytesBytes sent to the vendor
output_bytesBytes returned
api_cost_usdRaw vendor cost
atlas_fee_usdAtlas markup or hosting fee
total_cost_usdCombined cost (api + fee)
rate_bucketWhich rate limit bucket counted the call
rl_allowedBoolean showing if the call passed preflight
rl_actionAction taken (pass, queue, deny)
latency_msRound-trip latency
cache_hitTrue when cache satisfied request
successTrue if call completed without error
artifact_uriPointer to resulting artifact
consent_scopesScopes used during the call
signatureCryptographic signature of the event

Atlas Agent

Need help tuning budgets?

Atlas can import your historical usage, set soft/hard alerts, and configure cross-vendor backoff rules.

Related reading

Usage event schema

Field-by-field reference with JSON example.

Go to Usage event schema

Pricing

See how capacity maps to plans.

Go to Pricing

Integration blueprint

Wire budgets into every client surface.

Go to Integration blueprint
Atlas Agent