Robin Saige we check the tools AI agents call

OpenLMNP

io.github.manganate006/openlmnp

Accounting MCP for French LMNP furnished rentals: income, expenses, depreciation, tax return & FEC

— the operator's own registry description reported

Publisher io.github.manganate006 · first seen 2026-08-12 · endpoint https://app.openlmnp.fr/mcp?demo_token=openlmnp_demo_ro_ebd891f45e8a771ca1a718f239b733b438a31d48

allow
verdict
rich-slow-solo
cluster
ok_tools
answers
44
tools served

Dependency rating derived

allow — rich-slow-solo — safe to depend on

Cluster rich-slow-solo · distinctiveness 0.817 (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
latency732 ms
vs populationslow
protocolcurrent
authopen
Use — can it use it?
tools44
vs populationhigh
capabilities3
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_0ed86e442915f58125d3a5f7 · 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

attach_document compare_micro_bic compute_depreciation compute_fiscal_year compute_loan_schedule compute_tva create_expense create_furniture create_income create_property create_property_work delete_document delete_expense delete_furniture delete_income delete_property_work export_documents generate_fec generate_tax_return get_dashboard_summary get_expense get_fiscal_year get_income get_loan get_loan_schedule get_onboarding_status get_projection get_property get_simulation import_airbnb_csv list_categories list_expenses list_fiscal_years list_furniture list_incomes list_loans list_properties list_property_components list_property_works update_expense update_furniture update_income update_property update_property_work

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 & specific44/44
has a description44/44
description is substantive44/44
parameters are typed44/44
parameters are described3/443/44

44 of 44 tools graded · 44 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
1.0.0
server version OpenLMNP

Capabilities: 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
2026-08-14T19:59:45Zok_tools2007322025-06-18
2026-08-12T05:34:58Zok_tools2006152025-06-18

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.github.manganate006/openlmnp.svg)](https://robinsaige.com/s/io.github.manganate006/openlmnp)

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