Robin Saige we check the tools AI agents call

Loyal Spark

io.github.aspekt19/loyal-spark

Onchain loyalty MCP on Base: programs, mint, rewards, vouchers for AI agents.

— the operator's own registry description reported

Publisher io.github.aspekt19 · first seen 2026-08-12 · endpoint https://api.loyalspark.online/loyalty-mcp

allow
verdict
rich-slow-solo
cluster
ok_tools
answers
39
tools served

Dependency rating derived

allow — rich-slow-solo — safe to depend on

Cluster rich-slow-solo · distinctiveness 0.539 (moderate). 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
latency547 ms
vs populationslow
protocolcurrent
authopen
Use — can it use it?
tools39
vs populationhigh
capabilities1
harnessA
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_5a397a035173959a0aed7c5f · 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

activate_loyalty_program bazaar_discover_mcp_servers bazaar_discover_resources bazaar_pay_and_call bazaar_probe_x402 cancel_stale_offers check_voucher_status confirm_mint_fee create_gift_certificate create_loyalty_program create_personalized_offer create_reward delete_report earn_points export_customers generate_program_defaults get_my_profile get_platform_info get_platform_stats get_program_analytics get_program_workflow_status get_token_balance list_gift_certificates list_loyalty_programs list_marketplace_offers list_my_reports list_rewards mark_gift_certificate_minted mint_loyalty_tokens redeem_reward register_loyalty_program revoke_gift_certificate send_report transfer_loyalty_tokens update_program_config update_program_status update_report_status update_reward_status use_voucher

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 A — an agent can pick and call these reliably.

legibility checktools passingok
name is clear & specific39/39
has a description39/39
description is substantive37/3937/39
parameters are typed38/3938/39
parameters are described37/3937/39

39 of 39 tools graded · 39 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

2025-06-18
protocol version
session model
1.0.0
server version loyal-spark-mcp

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
2026-08-14T19:59:23Zok_tools2005472025-06-18
2026-08-12T05:34:36Zok_tools2007072025-06-18

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/io.github.aspekt19/loyal-spark.svg)](https://robinsaige.com/s/io.github.aspekt19/loyal-spark)

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