AxioRank: Zero-Trust for AI Agents

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Zero-trust gateway for AI agents: score tool calls, verify agent cards, enforce policy, audit.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "AxioRank: Zero-Trust for AI Agents": {
      "url": "https://app.axiorank.com/api/mcp-server/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (22)

• axiorank_score_tool_call

  Inspect a proposed agent tool call BEFORE executing it. AxioRank scores its risk (0–100), runs content inspection (secrets, PII, destructive ops, prompt-injection, egress), applies your policies, records an audit log, and returns a decision: `allow`, `deny`, or `hold`. On `hold`, a human must approve. Poll `axiorank_check_approval` with the returned `approvalId`. Call this in your tool-use loop and refuse or wait on any non-`allow` decision. Requires the `gateway:write` scope.

  Parameters:

  • tool (required) — string
  • model — string
  • phase — string
  • intent — string
  • source — string
  • context — string
  • costUsd — number
  • traceId — string
  • metadata — object
  • passport — boolean
  • arguments — object
  • sessionId — string
  • stepIndex — integer
  • durationMs — integer
  • promptText — string
  • resultText — string
  • inputTokens — integer
  • taintHandle — string
  • outputTokens — integer
  • completionText — string
  • parentStepIndex — integer

  Hints: read-only no · destructive no · idempotent no · open-world yes

• axiorank_verify_card

  Vet a remote agent or tool's identity card (A2A Agent Card, MCP server card, OAuth metadata, x402, …) BEFORE connecting to it. Supply EITHER `url` (AxioRank fetches the card) OR an inline `document`. AxioRank verifies signatures, scores supply-chain risk, folds in cross-tenant threat intel, and returns `allow` / `review` / `deny` with the resolved identity, capabilities and auth. Use it as a connection preflight. Requires the `cards:verify` scope.

  Parameters:

  • url — string
  • document
  • protocol — string

  Hints: read-only no · destructive no · idempotent no · open-world yes

• axiorank_check_approval read-only

  Poll the verdict of a held (`hold`) tool call. Pass the `approvalId` returned by `axiorank_score_tool_call`. Blocks briefly server-side and returns as soon as an operator approves/denies; otherwise returns the still-`pending` status so you can call again. Requires the `gateway:write` scope and the same agent key that made the original call.

  Parameters:

  • approvalId (required) — string — The approvalId returned by axiorank_score_tool_call when the decision was 'hold'.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_get_protocol_coverage read-only

  List the agent-interop protocols AxioRank can govern (A2A, MCP, OAuth, x402, DIDs, robots.txt/llms.txt, AP2, …), grouped into six planes, each with coverage status (live/beta/planned) and direction (inbound/outbound/both). Use this to discover what AxioRank speaks before wiring up card verification or inbound bot management.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_get_health read-only

  Liveness/readiness probe for the AxioRank control plane (API + database reachability). Returns `status: ok|degraded`.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_list_agents read-only

  List the active agents in your AxioRank workspace (id, name, labels, quarantine + last-used status). Use this to find an agent's id before calling agent-specific tools. Requires the `agents:read` scope.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_get_agent read-only

  Fetch one agent's posture (quarantine state, labels, last-used, revocation) by id, scoped to your workspace. Requires the `agents:read` scope.

  Parameters:

  • agentId (required) — string — The agent's UUID (from axiorank_list_agents).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_quarantine_agent destructive

  Reversible kill switch: quarantine an agent so the gateway DENIES all of its tool calls, or release it. Set `quarantine: false` to restore. Requires the `agents:write` scope.

  Parameters:

  • agentId (required) — string — The agent's UUID (from axiorank_list_agents).
  • quarantine (required) — boolean — true = quarantine (deny all its calls); false = release.

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• axiorank_revoke_agent destructive

  Permanently revoke an agent: its API keys stop authenticating immediately (incident response). Irreversible. Issue a new agent to restore access. Its audit history is kept. Requires the `agents:write` scope. Prefer `axiorank_quarantine_agent` for a reversible pause.

  Parameters:

  • agentId (required) — string — The agent's UUID (from axiorank_list_agents).

  Hints: read-only no · destructive yes · idempotent yes · open-world no

• axiorank_list_policies read-only

  List the outbound governance policies in your workspace (enabled or not), each with its tool pattern, action (allow/deny/require_approval/redact), risk threshold, priority and enabled flag. Requires the `policies:read` scope.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_get_policy read-only

  Fetch one outbound policy by id, scoped to your workspace. Requires the `policies:read` scope.

  Parameters:

  • policyId (required) — string — The policy's UUID (from axiorank_list_policies).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_create_policy

  Create an outbound governance policy. It is created DISABLED so an LLM can never arm enforcement unattended. Review it (axiorank_get_policy) then enable it with axiorank_update_policy. `toolPattern` is a glob over tool names; `action` is allow / deny / require_approval / redact (redact masks PII in a model completion). Requires the `policies:write` scope.

  Parameters:

  • name (required) — string
  • toolPattern (required) — string
  • action (required) — string
  • context
  • priority — integer
  • riskThreshold
  • signalCategory
  • enforcementMode — string

  Hints: read-only no · destructive no · idempotent no · open-world no

• axiorank_update_policy

  Update an existing policy: enable/disable it, rename it, or change its priority. (Other fields are edited in the dashboard.) Requires the `policies:write` scope.

  Parameters:

  • policyId (required) — string — The policy's UUID (from axiorank_list_policies).
  • name — string
  • enabled — boolean — Arm (true) or disarm (false) the policy.
  • priority — integer — Lower runs first; ties broken by creation order.

  Hints: read-only no · destructive no · idempotent no · open-world no

• axiorank_search_audit_logs read-only

  Search your workspace's governance audit trail, newest first, with filters: decision (allow/deny/hold), source (sdk/mcp), agentId, tool name (substring), minimum risk, and a time window (ISO `from`/`to`). Payloads are already secret-redacted. Use it to answer questions like "show denied tool calls in the last 24h". Requires the `logs:read` scope.

  Parameters:

  • to — string — ISO timestamp: exclusive upper bound on created_at.
  • from — string — ISO timestamp: inclusive lower bound on created_at.
  • tool — string — Case-insensitive substring of the tool name.
  • limit — integer
  • source — string
  • agentId — string
  • minRisk — integer
  • decision — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_list_incidents read-only

  List security alerts/incidents in your workspace, newest first, filterable by status (open/acknowledged/resolved/suppressed), severity (low/medium/high/critical) and kind (high_risk/anomaly/auto_response/kill_chain/ml_threat). Requires the `logs:read` scope.

  Parameters:

  • kind — string
  • limit — integer
  • status — string
  • severity — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_get_incident read-only

  Fetch the kill-chain finding behind an alert (the multi-step attack pattern, severity, and the contributing tool-call ids) by alert id. Returns null evidence for a non-kill-chain alert. Requires the `logs:read` scope.

  Parameters:

  • alertId (required) — string — The alert/incident UUID (from axiorank_list_incidents).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_list_threat_intel read-only

  List external identities (card hosts/keys) flagged across the AxioRank network, with k-anonymity-gated aggregate counts (workspaces, sightings, deny/review, max risk). This is the shared cross-tenant feed, not your private data. Requires the `logs:read` scope.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_list_ml_assessments read-only

  List your workspace's most recent ML/LLM threat assessments (model verdict, threat class, confidence, recommendation) for tool calls and cards. Requires the `logs:read` scope.

  Parameters:

  • limit — integer

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_get_usage read-only

  Report this billing period's usage for your workspace: plan tier, governed events used vs the monthly limit, and ML assessments used. Requires the `logs:read` scope.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• axiorank_issue_token

  Mint a short-lived, scoped `axr_tok_…` access token for an existing agent. This is the Zero-Trust credential the agent sends as `Authorization: Bearer <token>`. It expires within the hour and cannot be replayed afterwards. Durable static keys are issued in the dashboard, not here. Requires the `keys:write` scope.

  Parameters:

  • agentId (required) — string — The agent's UUID (from axiorank_list_agents).
  • scopes — array — Operational scopes for the token (gateway:write, cards:verify, logs:read).
  • ttlSeconds — integer — Token lifetime in seconds (60–3600). Defaults to 900 (15 min).

  Hints: read-only no · destructive no · idempotent no · open-world no

• axiorank_create_agent

  Create a new agent in your workspace and return a SHORT-LIVED bootstrap token to start using it immediately (no durable secret is emitted). For long-term auth, add a static key or a federation binding in the dashboard. Requires the `agents:write` scope.

  Parameters:

  • name (required) — string
  • labels — array
  • ttlSeconds — integer — Token lifetime in seconds (60–3600). Defaults to 900 (15 min).
  • description — string
  • tokenScopes — array — Operational scopes for the token (gateway:write, cards:verify, logs:read).

  Hints: read-only no · destructive no · idempotent no · open-world no

• axiorank_author_detector

  Describe a risk in plain English and AxioRank's AI proposes a custom content detector (regex or keyword) and SAVES it DISABLED for your review. An LLM never arms detection unattended. Outbound content categories only (secret/pii/destructive/injection/egress). Requires the `policies:write` scope and an AI-assessments-enabled plan (Team+).

  Parameters:

  • description (required) — string — What to detect, e.g. 'flag AWS secret access keys in tool arguments'.

  Hints: read-only no · destructive no · idempotent no · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.