# AP Control Labs Finance Controls (remote · api-production-9502.up.railway.app)

Read-only finance and operations controls for AI agents with evidence and safe next actions.

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-16

## Components

- remote · `api-production-9502.up.railway.app`: 72/100 (this document), [markdown](https://verifymcp.io/servers/juodoc-ap-control/api-production-9502.md), [page](https://verifymcp.io/servers/juodoc-ap-control/api-production-9502)

## Channel facts

- Endpoint: `https://api-production-9502.up.railway.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `1.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-16.

- **Endpoint Security**: 89/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, but the challenge carries no valid RFC 9728 metadata, so a client cannot discover where to get a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 2289 tokens (~71/item across 32 items; 32 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http juodoc-ap-control https://api-production-9502.up.railway.app/mcp
```

### Codex

```toml
[mcp_servers.juodoc-ap-control]
url = "https://api-production-9502.up.railway.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "juodoc-ap-control": {
      "type": "remote",
      "url": "https://api-production-9502.up.railway.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add juodoc-ap-control --url https://api-production-9502.up.railway.app/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  juodoc-ap-control:
    url: "https://api-production-9502.up.railway.app/mcp"
```

### Other

```json
{
  "mcpServers": {
    "juodoc-ap-control": {
      "type": "http",
      "url": "https://api-production-9502.up.railway.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-16 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-14 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-12 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-11 (score 69, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-10 (score 66)

First indexed and scored.

## MCP tools (32)

### `analyze_invoice` (~56 tokens)

Submit one normalized invoice for asynchronous duplicate analysis. Use the returned ID to poll; do not resubmit the same work with a new idempotency key.

Input parameters:

- `idempotency_key` (string, required)
- `invoice` (object, required)

Output parameters:

- `decision`
- `exceptions` (array)
- `id` (string)
- `status`

### `get_invoice_status` (~36 tokens)

Retrieve one analysis owned by the caller's organization. Poll until status is COMPLETED or FAILED.

Input parameters:

- `invoice_id` (string, required)

Output parameters:

- `decision`
- `exceptions` (array)
- `id` (string)
- `status`

### `get_invoice_exceptions` (~30 tokens)

Retrieve the agent-readable exception packet for one caller-owned invoice.

Input parameters:

- `invoice_id` (string, required)

Output parameters:

- `exceptions` (array)

### `create_purchase_order` (~67 tokens)

Register one customer-provided purchase order as the baseline for AP Match. This stores only the caller's data and never writes to an ERP.

Input parameters:

- `currency` (string)
- `lines` (array, required)
- `po_number` (string, required)
- `vendor_name` (string, required)

Output parameters:

- `id` (string)
- `lines` (array)
- `po_number` (string)
- `status` (string)

### `record_receipt` (~73 tokens)

Record a customer-provided goods receipt for a registered purchase order. Use it before a THREE_WAY AP Match; it never updates a warehouse or ERP.

Input parameters:

- `lines` (array, required)
- `purchase_order_id` (string, required)
- `receipt_number` (string, required)
- `received_at` (string|null)

Output parameters:

- `id` (string)
- `lines` (array)
- `purchase_order_id` (string)
- `receipt_number` (string)

### `match_invoice` (~62 tokens)

Run a read-only two- or three-way match against one registered purchase order. Supply exactly one purchase-order identifier.

Input parameters:

- `invoice_id` (string, required)
- `mode`
- `purchase_order_id` (string)
- `purchase_order_number` (string)

Output parameters:

- `decision`
- `exceptions` (array)
- `invoice_id` (string)
- `line_results` (array)
- `mode`
- `purchase_order_id` (string)

### `get_invoice_extraction` (~37 tokens)

Retrieve canonical fields, OCR confidence, source evidence, and a next action for a submitted invoice.

Input parameters:

- `invoice_id` (string, required)

Output parameters:

- `confidence` (number|null)
- `evidence` (object)
- `fields`
- `invoice_id` (string)
- `next_action` (string)
- `status`

### `validate_invoice` (~39 tokens)

Run deterministic required-field, date, and line-total checks before AP routing. This does not create or alter accounting records.

Input parameters:

- `invoice` (object, required)

Output parameters:

- `decision`
- `exceptions` (array)
- `next_action` (string)

### `search_invoice_history` (~47 tokens)

Find exact and near matches in the caller's own completed invoice history. Scores are explainable, not a fraud probability.

Input parameters:

- `invoice` (object, required)
- `limit` (integer)

Output parameters:

- `matches` (array)
- `next_action` (string)

### `upsert_vendor_baseline` (~73 tokens)

Create or replace a customer-controlled remittance baseline. Provide a fingerprint, not a raw account number. This is not bank-account ownership verification.

Input parameters:

- `account_fingerprint` (string, required)
- `remittance_reference` (string, required)
- `vendor_name` (string, required)
- `vendor_reference` (string, required)

Output parameters:

- `account_fingerprint` (string)
- `id` (string)
- `reference` (string)
- `remittance_reference` (string)
- `vendor_name` (string)

### `check_remittance_change` (~67 tokens)

Compare submitted fingerprinted remittance details with a customer-controlled vendor baseline. A change requires human out-of-band verification; this is not bank-account ownership verification.

Input parameters:

- `account_fingerprint` (string, required)
- `remittance_reference` (string, required)
- `vendor_reference` (string, required)

Output parameters:

- `decision`
- `exceptions` (array)
- `next_action` (string)

### `normalize_invoice_lines` (~44 tokens)

Private preview. Deterministically normalize customer-supplied invoice descriptions, SKUs, and units. It does not invent missing values.

Input parameters:

- `line_items` (array, required)

Output parameters:

- `issues` (array)
- `line_items` (array)
- `next_action` (string)
- `status`

### `get_invoice_risk_score` (~44 tokens)

Private preview. Return the deterministic 0-100 control score, priority band, and named evidence signals for a completed invoice.

Input parameters:

- `invoice_id` (string, required)

Output parameters:

- `band`
- `invoice_id` (string)
- `next_action` (string)
- `score` (integer)
- `signals` (array)

### `extract_purchase_order` (~50 tokens)

Private preview. Queue one uploaded customer-owned purchase-order document for structured extraction. Poll with get_purchase_order_extraction.

Input parameters:

- `idempotency_key` (string, required)
- `upload_id` (string, required)

Output parameters:

- `fields` (object|null)
- `id` (string)
- `next_action` (string)
- `status`

### `get_purchase_order_extraction` (~40 tokens)

Private preview. Get the caller-owned PO extraction status, canonical fields, OCR evidence, and next action.

Input parameters:

- `extraction_id` (string, required)

Output parameters:

- `fields` (object|null)
- `id` (string)
- `next_action` (string)
- `status`

### `save_extracted_purchase_order` (~46 tokens)

Private preview. Save a completed extraction as a named PO revision before matching or amendment diffing.

Input parameters:

- `extraction_id` (string, required)
- `revision_label` (string, required)

Output parameters:

- `id` (string)
- `po_number` (string)
- `revision_label` (string)

### `diff_purchase_order_amendment` (~53 tokens)

Private preview. Compare two saved caller-owned PO revisions and return explicit header, term, and line changes.

Input parameters:

- `after_purchase_order_id` (string, required)
- `before_purchase_order_id` (string, required)

Output parameters:

- `decision`
- `exceptions` (array)
- `next_action` (string)

### `preflight_erp_bill` (~125 tokens)

Check a proposed NetSuite or QuickBooks vendor bill using customer-supplied record references. This tool never connects to or writes to an ERP.

Input parameters:

- `approval_present` (boolean)
- `approval_required_above` (string|number)
- `erp` (required)
- `existing_bill_reference` (string)
- `expected_currency` (string)
- `expected_vendor_reference` (string)
- `invoice` (object, required)
- `purchase_order_reference` (string)
- `source_record_id` (string, required)
- `vendor_reference` (string, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `preflight_subcontractor_invoice` (~173 tokens)

Check a subcontractor invoice against supplied commitment, retainage, schedule-of-values, work, lien-waiver, and insurance evidence. It does not determine legal validity of documents.

Input parameters:

- `approved_change_order_amount` (string|number)
- `approved_contract_amount` (string|number, required)
- `billed_to_date` (string|number)
- `current_application_amount` (string|number, required)
- `insurance_status`
- `invoice` (object, required)
- `lien_waiver_status`
- `project_reference` (string, required)
- `retainage_rate` (string|number)
- `retainage_withheld` (string|number)
- `schedule_of_values_matched` (boolean, required)
- `subcontract_reference` (string, required)
- `work_completed_verified` (boolean, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `preflight_freight_invoice` (~157 tokens)

Check a freight invoice against supplied shipment, linehaul, fuel, and accessorial policy data. It does not connect to a TMS or carrier system.

Input parameters:

- `allowed_accessorials` (array)
- `carrier_scac` (string, required)
- `duplicate_shipment_invoice` (boolean)
- `invoice` (object, required)
- `invoiced_accessorials` (array)
- `invoiced_fuel_surcharge` (string|number)
- `invoiced_linehaul` (string|number, required)
- `quoted_fuel_surcharge` (string|number)
- `quoted_linehaul` (string|number, required)
- `shipment_delivered` (boolean, required)
- `shipment_reference` (string, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `preflight_franchise_invoice` (~92 tokens)

Find exact same-vendor, same-invoice, same-amount duplicates across customer-supplied multi-location history. It never searches another organization’s records.

Input parameters:

- `approved_vendor_references` (array)
- `historical_invoices` (array)
- `invoice` (object, required)
- `location_open` (boolean)
- `location_reference` (string, required)
- `vendor_reference` (string, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `check_procurement_agent_action` (~150 tokens)

Evaluate a proposed procurement agent action against supplied budget, authority, category, vendor, contract, and approval policy. It never authorizes a payment or vendor-record change.

Input parameters:

- `action` (required)
- `agent_id` (string, required)
- `amount` (string|number, required)
- `approval_present` (boolean)
- `approval_required_above` (string|number)
- `budget_available` (boolean, required)
- `category` (string, required)
- `contract_reference` (string)
- `currency` (string)
- `requester_authorized` (boolean, required)
- `restricted_categories` (array)
- `vendor_approved` (boolean)
- `vendor_reference` (string)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `resolve_vendor_entity` (~89 tokens)

Resolve customer-supplied vendor names, aliases, addresses, and domains against customer-provided expectations. It is not official verification.

Input parameters:

- `address` (string)
- `aliases` (array)
- `approved_domains` (array)
- `email_domain` (string)
- `expected_address` (string)
- `expected_name` (string)
- `vendor_name` (string, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `check_vendor_onboarding` (~71 tokens)

Check customer-defined supplier onboarding packet completeness. It does not approve or create a vendor.

Input parameters:

- `approved_by_customer` (boolean)
- `remittance_fingerprint_present` (boolean)
- `required_items` (array, required)
- `supplied_items` (array)
- `vendor_reference` (string, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `check_tax_form` (~106 tokens)

Check W-9 or W-8 form completeness using only a legal name, final four identifier digits, customer signature policy, and supplied dates. It is not tax advice or tax-ID verification.

Input parameters:

- `entity_country` (string)
- `expires_on` (string)
- `form_type` (required)
- `legal_name` (string)
- `signature_required_by_customer` (boolean)
- `signed_on` (string)
- `tax_identifier_last4` (string)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `check_vendor_domain_risk` (~66 tokens)

Compare a sender email domain with customer-provided approved and prior-domain baselines. Verify changes out of band.

Input parameters:

- `approved_domains` (array)
- `prior_sender_domains` (array)
- `sender_email` (string, required)
- `vendor_reference` (string, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `compare_quotes` (~41 tokens)

Compare customer-provided vendor quote lines and totals. It never selects or sends a quote.

Input parameters:

- `expected_currency` (string)
- `quotes` (array, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `extract_contract_obligations` (~69 tokens)

Find candidate ISO dates and obligation indicators in supplied contract text. Review results against the source; this is not legal advice.

Input parameters:

- `as_of_date` (string)
- `contract_reference` (string, required)
- `contract_text` (string, required)
- `lookahead_days` (integer)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `check_certificate_expiry` (~61 tokens)

Check expiry windows and customer verification flags for supplied certificate metadata. It does not validate certificate authenticity.

Input parameters:

- `as_of_date` (string)
- `certificates` (array, required)
- `vendor_reference` (string, required)
- `warning_days` (integer)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `match_remittance_advice` (~92 tokens)

Match a customer-supplied remittance amount and invoice references to the caller's supplied open-invoice baseline. It never posts a payment.

Input parameters:

- `currency` (string)
- `invoice_references` (array)
- `open_invoices` (array, required)
- `remittance_reference` (string, required)
- `remitted_amount` (string|number, required)
- `vendor_reference` (string)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `normalize_bank_statement` (~45 tokens)

Normalize customer-provided bank transaction records for reconciliation. It never connects to a bank or stores account numbers.

Input parameters:

- `account_reference` (string, required)
- `transactions` (array, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

### `match_reconciliation` (~53 tokens)

Produce deterministic candidate matches between two caller-provided record sets. It never posts a reconciliation.

Input parameters:

- `date_tolerance_days` (integer)
- `source_records` (array, required)
- `target_records` (array, required)

Output parameters:

- `decision`
- `evidence` (object)
- `exceptions` (array)
- `next_action` (string)
- `product` (string)
- `status`

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/juodoc-ap-control/api-production-9502#diagnostics

## Score history

- 2026-08-16: 72
- 2026-08-15: 71
- 2026-08-14: 71
- 2026-08-13: 70
- 2026-08-12: 70
- 2026-08-11: 69
- 2026-08-10: 66

## Links

- Remote endpoint: https://api-production-9502.up.railway.app/mcp
- Authorisation metadata: https://api-production-9502.up.railway.app/.well-known/oauth-protected-resource/mcp
- Website: https://console-production-0ac5.up.railway.app/catalog
- Changelog RSS feed: https://verifymcp.io/servers/juodoc-ap-control/api-production-9502.xml
- Changelog JSON feed: https://verifymcp.io/servers/juodoc-ap-control/api-production-9502.json
- HTML version of this page: https://verifymcp.io/servers/juodoc-ap-control/api-production-9502