SECOPS

Geo-Velocity Step-Up MFA Challenge Router

On each login webhook, scores geo-velocity risk in real time and routes the session to allow, step-up MFA challenge.

CategorySecOps
Enginesim
Difficultyadvanced
Triggerwebhook
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerPre-auth login webhook from IdPHTTP webhook
  • ActionFetch user login baseline from AxiomAxiom
  • LogicScore attempt into low / medium / high risk band
  • ActionIssue step-up MFA challenge via identity MCP serverCustom MCP server
  • OutputReturn allow/challenge/block decision and log to AxiomAxiom

What it does

This workflow sits inline with your login flow and decides, per attempt, whether to wave the user through, force a step-up MFA challenge, or block the session outright. The decision is driven by how anomalous the login's geography and velocity are relative to the user's recent history.

When to use it

Use this when you want adaptive authentication without rebuilding your IdP's risk engine. It fits teams whose identity provider exposes a challenge/decision API over a custom MCP server and who want explainable, tunable routing logic they control.

How it works

  1. 1An HTTP webhook fires the moment your IdP emits a pre-authentication event with the candidate IP and geo.
  2. 2The flow queries Axiom for the user's last several logins to establish a baseline of locations and devices.
  3. 3A logic step buckets the attempt into low, medium, or high risk based on geo-velocity, new-country, and new-device signals.
  4. 4Low risk returns an allow decision; medium risk calls the custom MCP server to issue a step-up MFA challenge; high risk returns a block.
  5. 5The final decision is written back to the IdP via the webhook response and logged to Axiom for audit.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect AxiomLog streams, queries, dashboards.
  3. 3
    Connect Custom MCP serverConnect any MCP-compatible tool you own.
  4. 4
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  5. 5
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  6. 6
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.