Should my agent depend on the MCP server io.github.ogasurfproject-jpg/horizon-shield?

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

HORIZON SHIELD — construction & renovation estimate auditor

io.github.ogasurfproject-jpg/horizon-shield

Independent pre-transaction audit for construction estimates. Free, and every verdict recomputes.

— the operator's own registry description reported

Publisher io.github.ogasurfproject-jpg · first seen 2026-08-12 · endpoint https://mcp.horizonshield.dev

allow

verdict

mid-fast-shared

cluster

ok_tools

answers

tools served

Dependency rating derived

allow — mid-fast-shared — safe to depend on

Cluster mid-fast-shared · distinctiveness 0.275 (typical). 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

latency59 ms

vs populationfast

protocolcurrent

authopen

Use — can it use it?

tools14

vs populationmid

capabilities2

harnessA

Trust — can it rely on it?

identityshared

servers on its host1

servers on its domain4

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_0318ddfac54702933e9ad7c2 · 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

audit_estimate check_red_flags create_ap2_fairness_attestation get_agent_card get_estimate_reading_guide get_fair_price_sources get_jccdb_dataset_info get_price_range list_cost_categories preview_reverse_estimate search_cost_category suggest_ehn verify_fair_price verify_integrity_claim

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	14/14	✓
has a description	14/14	✓
description is substantive	14/14	✓
parameters are typed	14/14	✓
parameters are described	14/14	✓

14 of 14 tools graded · 14 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

1.0.5

server version horizon-shield

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
2026-08-14T19:59:54Z	ok_tools	200	59	2025-06-18
2026-08-12T05:35:10Z	ok_tools	200	47	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.ogasurfproject-jpg/horizon-shield.svg)](https://robinsaige.com/s/io.github.ogasurfproject-jpg/horizon-shield)

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