Should my agent depend on the MCP server ai.tunnelmind/data?

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

TunnelMind Data API

ai.tunnelmind/data

Tracker / Sigil / Cross-lens — every TunnelMind Data API operation as one MCP surface.

— the operator's own registry description reported

Publisher ai.tunnelmind · first seen 2026-08-12 · endpoint https://mcp-data.tunnelmind.ai/mcp

allow

verdict

stale-rich-shared

cluster

ok_tools

answers

tools served

Dependency rating derived

allow — stale-rich-shared — safe to depend on

Cluster stale-rich-shared · distinctiveness 0.467 (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

latency109 ms

vs populationtypical

protocolbehind

authopen

Use — can it use it?

tools93

vs populationhigh

capabilities2

harnessA

Trust — can it rely on it?

identityshared

servers on its host1

servers on its domain3

verifiabilityunassessed

duplicate inventoryno

drift events0

answers true0/0 agree

🔏 Signed receipt rr_c1e6a7c36332268eb0944cca · 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_registries_lookup attributes_lookup audit_export cancel_task check_receipt_revoked compliance_configure compliance_export compliance_ledger compliance_profile compliance_verify create_free_key create_subscription cross_lens_lookup cross_lens_verify delete_subscription explain_verdict generate_receipt get_analyst_config get_api_key get_bgp_events get_domain get_entity get_feedback get_freshness get_receipt get_self_view get_stats get_subscription get_task get_website_history ghostroute_ai_lookup ghostroute_asn_lookup ghostroute_check ghostroute_ct_alerts ghostroute_ct_proofs ghostroute_ct_witness ghostroute_verify health_check intel_agent intel_http intel_inject intel_optout intel_robots intel_stack list_domains list_entities list_subscriptions preflight_should_i_act profile_entity receipt_log_consistency_proof receipt_log_inclusion_proof receipt_log_sth receipt_lookup revoke_api_key scan_injection scan_mcp search sigil_ads_txt_history sigil_atap_ait_status sigil_atap_register_ait sigil_atap_roll_block sigil_atap_witness sigil_receipt_generate sigil_score_batch sigil_score_entity sigil_score_weights sigil_traverse sigil_verify_ads_txt sigil_verify_ads_txt_batch sigil_verify_adscert sigil_verify_app_bundle sigil_verify_domain sigil_verify_ip_type sigil_verify_supply_chain sigil_verify_supply_path sigil_verify_token signal_dark_pool_risk signal_halo_score signal_team_signal signal_tracker_density snapshot_data snapshot_diff snapshot_manifest status_history stream_task submit_feedback tracker_verify traction verdict_lookup verify_agent verify_agent_signature verify_receipt x402_echo

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	93/93	✓
has a description	93/93	✓
description is substantive	92/93	92/93
parameters are typed	93/93	✓
parameters are described	37/93	37/93

93 of 93 tools graded · 93 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

0/0 answers agree with the published primary source · 2 unverifiable.

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

2025-03-26

protocol version

—

session model

1.0.0

server version tunnelmind-data-api

Capabilities: prompts 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
2026-08-14T19:57:42Z	ok_tools	200	109	2025-03-26
2026-08-12T05:33:00Z	ok_tools	200	137	2025-03-26

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/ai.tunnelmind/data.svg)](https://robinsaige.com/s/ai.tunnelmind/data)

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