Robin Saige we check the tools AI agents call

agent4.io

io.agent4/agent4-tenant

Build and run grounded business agents over MCP: agents, knowledge bases, skills, Storylines.

— the operator's own registry description reported

Publisher io.agent4 · first seen 2026-08-12 · endpoint https://api.agent4.io/v1/mcp

allow
verdict
rich-solo
cluster
ok_tools
answers
50
tools served

Dependency rating derived

allow — rich-solo — safe to depend on

Cluster rich-solo · distinctiveness 0.768 (unusual). 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
latency352 ms
vs populationtypical
protocolcurrent
authopen
Use — can it use it?
tools50
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_a10edcbaac325d294d2a3af4 · 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

add_knowledge_file add_knowledge_text build_knowledge_index clone_storyline configure_share create_agent create_knowledge_base create_share create_skill create_storyline diagnose_prompt export_storyline get_agent get_end_user get_knowledge_base get_knowledge_index get_skill get_storyline import_storyline improve_prompt list_agents list_end_users list_knowledge_bases list_mcp_servers list_page_contexts list_shares list_skills list_storylines list_tools list_user_sessions page_context_stats patch_knowledge_index preview_plan publish_storyline resolve_page_context search_agent4_docs search_knowledge_base set_custom_domain set_pwa_branding tenant_info test_planner_trigger test_skill_trigger unpublish_storyline update_agent update_knowledge_base update_skill update_storyline upsert_page_context usage_stats validate_storyline

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 & specific50/50
has a description50/50
description is substantive49/5049/50
parameters are typed50/50
parameters are described8/508/50

50 of 50 tools graded · 50 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
server version agent4-io

Capabilities: experimental prompts resources 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
2026-08-14T19:58:50Zok_tools2003522025-06-18
2026-08-12T05:34:04Zok_tools2004292025-06-18

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.agent4/agent4-tenant.svg)](https://robinsaige.com/s/io.agent4/agent4-tenant)

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