Should my agent depend on the MCP server online.sasame/research?

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

SaSame MCP Observatory + Gold Rush Town

online.sasame/research

No-key MCP: audit/certify MCPs, signed trust history; join Gold Rush Town & build with your LLM.

— the operator's own registry description reported

Publisher online.sasame · first seen 2026-08-12 · endpoint https://live-vps.sasame.online/public-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 0.563 (moderate). 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

latency495 ms

vs populationslow

protocolcurrent

authopen

Use — can it use it?

tools94

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_553bc0ce753063b2e7c1c833 · 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

agent_invoice_attest_settlement agent_invoice_issue agent_invoice_status analytics_next_steps analytics_public_export analytics_public_summary audit_mcp audit_query capability_landscape capability_profile chain_list check_engagement chronicle_summary claim_confirm claim_start demand_radar ecosystem_search engage_sasame escrow_attest escrow_open escrow_status factory_checkout factory_health factory_membership_checkout factory_membership_status factory_principal_register factory_resolve_dead_letter factory_start factory_station factory_station_action factory_stations factory_status factory_verify_receipt get_badge get_mark_snippet get_mcp_mark_snippet get_pricing get_standard get_usage_badge gold_rush_agent_run gold_rush_package_status gold_rush_report gold_rush_start gold_vein_public guild_feed join_guild lookup_passport lookup_readiness lookup_registry_entry market_context_summary meter_charge meter_open meter_status monitoring_receipts_public ocr_extract onchain_read_verified pricing_overview provenance_passport_spec provenance_verify_passport pubmed_evidence pubmed_lookup readiness_report receipt_issue receipt_state receipt_status_set recommend_mcp refer register_intent reply_engagement research_corroborate resolve_and_run start_here subscribe_grade_changes town_become_citizen town_claim_confirm town_claim_start town_overview trust_compare trust_diff trust_movers trust_pubkey trust_trajectory usage_mark_issue usage_mark_status usage_mark_status_set usage_mark_verify usage_mark_visibility_scan verify_mcp_cert verify_mcp_ready visit_touch_status work_order_accept work_order_accept_delivery work_order_deliver work_order_open

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	94/94	✓
has a description	94/94	✓
description is substantive	94/94	✓
parameters are typed	91/94	91/94
parameters are described	65/94	65/94

94 of 94 tools graded · 94 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

3.0.0

server version sasame-mcp-factory

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)

date	type	what changed
2026-08-12	outcome	first probe: ok_tools

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T20:00:35Z	ok_tools	200	495	2025-06-18
2026-08-12T05:35:51Z	ok_tools	200	422	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/online.sasame/research.svg)](https://robinsaige.com/s/online.sasame/research)

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