Robin Saige we check the tools AI agents call

mcp server

com.cryptorefills/mcp-server

Buy gift cards and top-ups from the industry leader. 6000+ brands, 195 countries. 4.7★, 98% CSAT

— the operator's own registry description reported

Publisher com.cryptorefills · first seen 2026-08-12 · endpoint https://api.cryptorefills.com/mcp/sse

allow
verdict
stale-mid-slow-solo
cluster
ok_tools
answers
10
tools served

Dependency rating derived

allow — stale-mid-slow-solo — safe to depend on

Cluster stale-mid-slow-solo · distinctiveness 0.234 (typical). Every figure is a percentile or class within the 11,094-server censussee the whole spectrum.

Reach — can an agent get to it?
answersalive_tools
latency438 ms
vs populationslow
protocolstale
authopen
Use — can it use it?
tools10
vs populationmid
capabilities1
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_19a03ec74056d6dc3830151f · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.

Tools last seen

createOrder getCurrencies getOrderStatus getPaymentViasWithCurrencies getProductPrice listBrands listProductsForCountry purchaseElicitation searchProducts validateOrder

Harness readiness observed

Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band B — usable, with rough edges.

legibility checktools passingok
name is clear & specific10/10
has a description10/10
description is substantive9/109/10
parameters are typed10/10
parameters are described3/103/10

10 of 10 tools graded · 10 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.

Truth checks observed

Not in the Tier-2 trade lane, or not yet checked. Tier-2 re-derives a server's answers against published primary sources — see truth checks.

Protocol conformance observed

2024-11-05
protocol version
session model
1.0.0
server version CryptoRefills MCP Server

Capabilities: tools

Drift

No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.

History observed

Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.

changelog (1 events)
datetypewhat changed
2026-08-12outcomefirst probe: ok_tools
raw probe records
probed (UTC) outcomehttpmsprotocol
2026-08-14T19:58:02Zok_tools2004382024-11-05
2026-08-12T05:33:18Zok_tools2004072024-11-05

Watch or embed this verdict

verdict badge

Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:

[![Robin Saige verdict](https://robinsaige.com/badge/com.cryptorefills/mcp-server.svg)](https://robinsaige.com/s/com.cryptorefills/mcp-server)

Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.

← overview