Should my agent depend on the MCP server io.github.leanrads/leanriq?

Verdict: allow — rich-slow-solo — safe to depend on As of 2026-08-15T11:28:18Z: a dated observation with receipts, not a warranty.

LeanrIQ

io.github.leanrads/leanriq

Creative-intelligence MCP for campaign strategy, ad builds, QA, and reporting.

— the operator's own registry description reported

Publisher io.github.leanrads · first seen 2026-08-12 · endpoint https://iq.leanrads.com/mcp

allow

verdict

rich-slow-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

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

Cluster rich-slow-solo · distinctiveness 0.813 (unusual). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.

Reach — can an agent get to it?

answersalive_tools

latency389 ms

vs populationslow

protocolcurrent

authopen

Use — can it use it?

tools87

vs populationhigh

capabilities4

harnessB

Trust — can it rely on it?

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_53fc6e6d0ca9576b15035038 · 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

archive_advertiser archive_campaign archive_creative build_ad build_campaign_creative_set cancel_task clone_creative create_advertiser create_campaign create_creative_brief create_creative_version create_flight create_production_plan delete_flight export_trafficked_assets generate_adserver_tag generate_preview_links get_adserver_tag get_advertiser get_asset get_brand_profile get_brand_visuals get_campaign get_capabilities get_competitor_intelligence get_creative get_current_seat get_current_user get_flight get_media_buy_delivery get_permissions get_preview_link get_task get_template get_trafficked_assets get_vertical_intelligence launch_creative_campaign leanr_build_campaign_creative_set leanriq_build_ad leanriq_build_agent_ad leanriq_campaign_builder leanriq_create_brief leanriq_create_creative_brief leanriq_create_production_plan leanriq_create_strategy leanriq_current_seat leanriq_get_brand_profile leanriq_get_brand_visuals leanriq_get_competitor_creative_intelligence leanriq_get_vertical_intelligence leanriq_launch_creative_campaign leanriq_qa_creative leanriq_recommend_workflow leanriq_resolve_or_provision_advertiser leanriq_run_creative_chain leanriq_select_seat list_accessible_seats list_advertisers list_assets list_campaigns list_competitor_evidence list_competitors list_creative_versions list_creatives list_flights list_tasks list_templates preview_trafficking_output promote_creative_workspace provide_performance_feedback push_flight_to_yahoo qa_creative refresh_brand_profile refresh_brand_visuals restore_creative_version retraffick_creative retraffick_flight retry_task revise_creative run_competitor_intelligence run_creative_chain traffick_creative traffick_flight update_advertiser update_campaign update_flight validate_flight

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 check	tools passing	ok
name is clear & specific	87/87	✓
has a description	87/87	✓
description is substantive	87/87	✓
parameters are typed	79/87	79/87
parameters are described	1/87	1/87

87 of 87 tools graded · 87 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 leanriq-agent-gateway

Capabilities: prompts resources tasks 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 (1 shown, 2026-08-14 → 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)

date	type	what changed
2026-08-14	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T19:59:44Z	ok_tools	200	389	2025-06-18

Watch or embed this verdict

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.leanrads/leanriq.svg)](https://robinsaige.com/s/io.github.leanrads/leanriq)

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