# audit_mcp_oauth

Audit MCP OAuth 2.1 authorization: validate RFC 9728 protected-resource-metadata, check RFC 8707 audience binding, and assess token-passthrough / confused-deputy risk. Use when a developer is securing an MCP server's authorization. Renders the interactive AINumbers tool as a widget; inputs are applied via the AIN Bridge and the tool runs client-side (zero PII, zero network).

Agent View of the PolicyLayer registry record for `audit_mcp_oauth`. HTML page: https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/audit-mcp-oauth

## Facts

- Tool: `audit_mcp_oauth`
- Server: Ainumbers Mcp Apps (`postoaklabs/ainumbers-mcp-apps`) — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps.md
- Homepage: https://github.com/PostOakLabs/ainumbers-mcp-apps
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server auth posture: open
- Server CORS policy: https://ainumbers.co
- Server rate-limited: no
- Parameters: 1
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `inputs` | object | no | Map of tool input element IDs to values (see manifest input_schema). Applied via AIN Bridge prefill. |

Parameters from the server's own tool schema.

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "audit_mcp_oauth",
    "arguments": {}
  }
}
```

## Why audit_mcp_oauth is rated Low

This is fundamentally a security audit and validation tool. It reads/analyzes OAuth configurations and security postures (validating metadata, checking bindings, assessing risks) but does not create, modify, delete, execute arbitrary code, or move money. The "assess" language indicates evaluation rather than enforcement.

From the tool's own definition: "Tool performs validation and assessment activities: 'validate RFC 9728 protected-resource-metadata, check RFC 8707 audience binding, and assess token-passthrough / confused-deputy risk.' These are auditing/checking operations that retrieve and analyze…"

## Use case

AI agents call audit_mcp_oauth to retrieve information from Ainumbers Mcp Apps without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Ainumbers Mcp Apps:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "audit_mcp_oauth": {}
  }
}
```

## Other tools on Ainumbers Mcp Apps (687)

- `agentic_mandate_sandbox` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/agentic-mandate-sandbox.md
- `allocate_ihb_interest` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/allocate-ihb-interest.md
- `amortize_asc606_commissions` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/amortize-asc606-commissions.md
- `anchor_document_integrity` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/anchor-document-integrity.md
- `apply_climate_scenario` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/apply-climate-scenario.md
- `assemble_aiuc1_evidence_pack` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/assemble-aiuc1-evidence-pack.md
- `assemble_ocg_evidence_bundle` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/assemble-ocg-evidence-bundle.md
- `attest_bulk_disbursement_integrity` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/attest-bulk-disbursement-integrity.md
- `attest_calc_agent_independence` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/attest-calc-agent-independence.md
- `attest_daily_reconciliation` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/attest-daily-reconciliation.md
- `attest_margin_call_lifecycle` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/attest-margin-call-lifecycle.md
- `bind_attested_subject` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/bind-attested-subject.md
- `build_226j_response_evidence_pack` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-226j-response-evidence-pack.md
- `build_agent_test_evidence` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-agent-test-evidence.md
- `build_agent_traffic_policy` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-agent-traffic-policy.md
- `build_ai_conformity_pack` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-ai-conformity-pack.md
- `build_ai_workpaper_record` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-ai-workpaper-record.md
- `build_allocation_decision_receipt` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-allocation-decision-receipt.md
- `build_amortization_schedule` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-amortization-schedule.md
- `build_ap2_cartmandate_hashchain` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-ap2-cartmandate-hashchain.md
- `build_cbcr_report` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-cbcr-report.md
- `build_chaingraph` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-chaingraph.md
- `build_claim_dispute_bundle` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-claim-dispute-bundle.md
- `build_conditional_relief_collateral_receipt` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-conditional-relief-collateral-receipt.md
- `build_conversion_receipt` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-conversion-receipt.md
- `build_digest_manifest` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-digest-manifest.md
- `build_disclosure_manifest` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-disclosure-manifest.md
- `build_dora_roi_register` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-dora-roi-register.md
- `build_dual_control_certification` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-dual-control-certification.md
- `build_etr_possession_chain` — Execute — https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps/build-etr-possession-chain.md
- …and 657 more: https://policylayer.com/tools/postoaklabs-ainumbers-mcp-apps.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=postoaklabs-ainumbers-mcp-apps · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/postoaklabs-ainumbers-mcp-apps