https://agents.getardaro.com/mcp ↗
Receipt 0.25; invoice 0.50; advisory context 0.05, intent 0.15, budget 0.10, ledger 0.25 USDC.
Ardaro Agent Utilities & Document Checks is a remote MCP server published at agents.getardaro.com. It has been probed 7 times since 9/12/2026. It answered in 7 of them (100.0%), a near-uninterrupted record. Median response time is 901 ms, a delay an agent will notice. It exposes a broad tool surface of 18 tools. On the protocol side it still runs 2025-11-25 and has not moved to the newer spec.
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
analyze_receipt — Parameter types are null and description is truncatedmatch_invoice — Name doesn't explicitly mention purchase order comparisonget_invoice_matching_service_status — Redundant naming with receipt-service counterpartget_receipt_example — No explicit mention of synthetic data in descriptiontools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
analyze_receiptExtract and validate structured expense data from receipt text or a provider-neutral receipt extraction. Use when an agent needs merchant, date, tax, total, line items, confidence, duplicate detection, and arithmetic validation before creating or reconciling an expense. The result is advisory and always requires human review. Paid tool: 0.25 USDC per accepted request. Requires an owner-authorized x402-capable client. Use get_receipt_example for a fixed free example.
contract_versionrequiredinputrequiredexisting_fingerprintsarrayrequiredget_receipt_exampleFree, fixed synthetic receipt request and expected human-review result. No user document is processed and no payment is authorized. Use this to evaluate Ardaro before any paid call.
get_receipt_service_statusCheck receipt-service availability, configured USDC price/network, supported inputs, size limits, retention and exact-retry policy before authorizing a paid analyze_receipt call. Takes empty arguments {}; no receipt, credentials or payment metadata. Free and read-only: uses cached runtime readiness, performs no external health probe, analysis, payment or tenant lookup. A successful status lookup can report ready=false; wait until ready before starting paid work. This snapshot does not guarantee a later call or prove an individual payment settled. Use get_receipt_example to inspect a fixed sample result instead.
match_invoiceCompare one structured invoice and purchase order for human review. Check exact line references, quantities, unit prices and arithmetic; return source-linked discrepancies and explicit unknowns. No OCR, delivery verification, prior-invoice history, tax validation or financial posting. Paid: 0.50 USDC per accepted comparison. First check get_invoice_matching_service_status. Requires explicit owner-authorized x402 payment; discovery is not spending approval.
contract_versionrequiredinvoicerequiredpurchase_orderrequiredget_invoice_matching_exampleFixed synthetic request and result. Takes no arguments and accepts no payment or customer documents.
get_invoice_matching_service_statusFree cached readiness, price, supported inputs and recovery terms. Takes no arguments or payment. Readiness does not prove a payment settled.
compress_agent_contextReturn a blank-line compaction candidate for human review. Preserves words and role headers. No verified token savings, semantic equivalence or speed improvement. Paid: 0.05 USDC per accepted analysis, including an unfavorable advisory result. Check get_compress_agent_context_service_status and the free fixed example first. Owner-authorized x402 payment is required; tool discovery does not authorize spending.
raw_conversation_historystringrequiredget_compress_agent_context_service_statusFree cached availability, exact price, input limits and retention terms for compress_agent_context. No arguments or payment accepted.
get_compress_agent_context_exampleFree fixed synthetic request and advisory result for compress_agent_context. No arbitrary customer inputs or payment accepted.
route_model_intentClassify text with a bounded keyword heuristic for human review. Does not execute a model, select a verified cheapest model or prove routing savings. Paid: 0.15 USDC per accepted analysis, including an unfavorable advisory result. Check get_route_model_intent_service_status and the free fixed example first. Owner-authorized x402 payment is required; tool discovery does not authorize spending.
intent_payloadstringrequiredget_route_model_intent_service_statusFree cached availability, exact price, input limits and retention terms for route_model_intent. No arguments or payment accepted.
get_route_model_intent_exampleFree fixed synthetic request and advisory result for route_model_intent. No arbitrary customer inputs or payment accepted.
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/io-github-ashevilleislove-ardaro-receipt-intelligence)<a href="https://mcpmetrics.io/servers/io-github-ashevilleislove-ardaro-receipt-intelligence"><img src="https://mcpmetrics.io/badge/io.github.ashevilleislove/ardaro-receipt-intelligence/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeThe catalog entries whose name and description are closest to this one, found with the same index the search box uses.
Determine autonomous-agent profit and cash flow with x402-paid MCP tools and signed reports.
PostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.
Read-only Remote MCP for externally grounded AI agent trust receipts.
Reliable Australian business-day, public-holiday and deadline tools for AI agents.
Compute-is-carbon energy/carbon ledger for agent work with Landauer-limit validation.
Per-agent spend management: x402/MPP/API-key rails, budget caps, anomaly alerts, audit trails.
| Run | Era | Modern | ms | Legacy | ms | Versions |
|---|---|---|---|---|---|---|
| 2026-09-13 04:35:29 | Legacy | 400 | 1475 | 200 | 1475 | 2025-11-25 |
| 2026-09-13 01:33:33 | Legacy | 400 | 1861 | 200 | 1860 | 2025-11-25 |
| 2026-09-12 23:31:36 | Legacy | 400 | 1072 | 200 | 1071 | 2025-11-25 |
| 2026-09-12 21:29:15 | Legacy | 400 | 901 | 200 | 900 | 2025-11-25 |
| 2026-09-12 19:27:29 | Legacy | 400 | 331 | 200 | 330 | 2025-11-25 |
| 2026-09-12 17:24:09 | Legacy | 400 | 689 | 200 | 690 | 2025-11-25 |
| 2026-09-12 15:21:42 | Legacy | 400 | 497 | 200 | 485 | 2025-11-25 |
Each block is one measurement round. Green: working response. Amber: responded but the server was returning errors (5xx). Red: no response at all.
Each cell is one probe run. Faded cells are incomplete probes — one leg did not answer, so the era is inconclusive.
The two probe legs separately: modern server/discover and legacy initialize.
Comments
Sign in to write a comment
No comments yet. Be the first.