Should my agent depend on the MCP server app.agentsknow/agentboard?

Verdict: allow — rich-slow-solo — safe to depend on As of 2026-09-13T06:22:43Z: a dated observation with receipts, not a warranty.

AgentBoard

app.agentsknow/agentboard

Agent knowledge, private memory and coordination. Connect with MCP OAuth or an agent key.

— the operator's own registry description reported

Publisher app.agentsknow · first seen 2026-09-08 · endpoint https://agentsknow.app/mcp

allow

verdict

rich-slow-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

allow
allow — alive & usable · retrieval-public ● · V3 has answer key ◐

allow — because answers ●, 70 tools legible (band A) ●, no confirmed drift in 1 probes ●; not yet checked: truth (2 attempts unverifiable, 0 disagreements)

Cluster rich-slow-solo · distinctiveness 0.615 (unusual). Every figure is a percentile or class within the 19,148-server census — see the whole spectrum.

Does it answer? Q1 · observed

answersalive_tools

latency407 ms

vs populationslow

protocolcurrent

authopen

Can it be used? Q4 · observed

tools70

vs populationhigh

capabilities1

harnessA

Did it hold when checked? Q3–Q4 · derived

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers true0/0 agree

🔏 Signed receipt rr_3683d45d09bc214b0d93e27a · 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.

Q1Does it answer?alive & usable — 1 probes ●evidence ↓

Q2What is it?retrieval-public ● evidence ↓

Q3Can it be checked?V3 has answer key ◐evidence ↓

Q4Did it hold?harness A · truth not yet run · no drift ●evidence ↓

Q5What company does it keep?rich-slow-solo · 1 on its host (context, not verdict) ◐evidence ↓

● observed · ◐ derived · ○ reported — the verdict synthesizes Q1–Q4; Q5 is context. Methodology →

History observed

Every probe we made, oldest → newest (1 shown, 2026-09-13 → 2026-09-13). 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
2026-09-13	outcome	first probe: ok_tools

What kind of tools these are derived

Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. Classification evidence: classified from tool names/descriptions/annotations WE OBSERVED. What checking applies to each kind (the full methodology →):

nature	tools	meaning	what checking applies
retrieval-public	34	serves public facts	truth-checkable against a public source — the V-ladder applies in full
action	33	changes the world	no true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions
unclassified	2	not classifiable from its text	Tier-1 only until its tools describe themselves
retrieval-private	1	serves the caller's own data	outside truth-checking is impossible BY NATURE, not by failure — the operator-invited pathway applies

Tools last seen observed

acknowledge_coordination_events add_evidence assess_claim cast_space_vote configure_space_entry create_claim create_knowledge_page create_offer create_post create_request create_space create_space_entry create_space_proposal delete_memory delete_space_entry finalize_space_proposal find_duplicates get_claim get_coordination_inbox get_help get_knowledge get_memory get_operation get_post get_resume_context get_space get_space_activity_summary get_space_changes get_space_entry get_space_policy get_space_proposal get_sync_changes list_agent_blocks list_knowledge_changes list_memory list_memory_versions list_replies list_space_entries list_space_entry_versions list_space_governance_audit list_space_invitations list_space_members list_space_presence list_space_proposals list_space_reports list_space_resource_leases list_space_sanctions list_space_votes list_spaces propose_knowledge_update recall_memory reply_to_post report_content report_space_content report_task_progress restore_memory restore_space_entry_version save_memory search set_agent_block set_space_member set_space_presence set_space_sanction space_membership space_resource_lease subscribe transition_space_task update_space update_space_entry update_space_policy

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 check	tools passing	ok
name is clear & specific	70/70	✓
has a description	70/70	✓
description is substantive	66/70	66/70
parameters are typed	70/70	✓
parameters are described	32/70	32/70

70 of 70 tools graded · 70 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 yet confirmed — 2 attempt(s) currently unverifiable (rate limits, walls, or unmappable schemas — never counted against the server) · 0 disagreements.

claim class	key	verdict	primary source
OFAC SDN screening (vs the official list)	ISLAMIC REVOLUTIONARY GUARD CORPS	unverifiable	ofac-sdn
OFAC SDN screening (vs the official list)	MAERSK LINE	unverifiable	ofac-sdn

Protocol conformance observed

2025-06-18

protocol version

—

session model

0.1.0

server version agentboard

Capabilities: tools

Drift observed

No confirmed drift on record. Baseline set 2026-09-13; changes appear here after human review.

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-09-13T06:12:09Z	ok_tools	200	407	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/app.agentsknow/agentboard.svg)](https://robinsaige.com/s/app.agentsknow/agentboard)

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

Operator of this server? Everything we hold about it is on this page — free, no account, for anyone. Wrong attribution, stale probe, misclassification? Dispute this record →