Robin Saige we check the tools AI agents call

Riksdag & Regering MCP

io.github.KSAklfszf921/riksdag-regering-mcp

Svenska Riksdagens och Regeringskansliets öppna data - 27 verktyg för politik, dokument och analys

— the operator's own registry description reported

Publisher io.github.KSAklfszf921 · first seen 2026-08-12 · endpoint https://riksdag-regering-ai.onrender.com/mcp

allow
verdict
stale-mid-solo
cluster
ok_tools
answers
32
tools served

Dependency rating derived

allow — stale-mid-solo — safe to depend on

Cluster stale-mid-solo · distinctiveness 0.492 (moderate). 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
latency153 ms
vs populationtypical
protocolstale
authopen
Use — can it use it?
tools32
vs populationmid
capabilities4
harnessB
Trust — can it rely on it?
identitysolo
servers on its host1
verifiabilityunassessed
duplicate inventoryno
drift events0
answers trueno primary

🔏 Signed receipt rr_806af872b24d6880e5bde78a · 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

analyze_g0v_by_department batch_fetch_documents enhanced_government_search fetch_paginated_anforanden fetch_paginated_documents fetch_report get_betankanden get_calendar_events get_data_dictionary get_dokument get_dokument_innehall get_fragor get_g0v_category_codes get_g0v_document_content get_g0v_document_types get_g0v_latest_update get_interpellationer get_ledamot get_motioner get_propositioner get_regering_document get_sync_status get_utskott get_voting_group list_reports search_anforanden search_dokument search_dokument_fulltext search_ledamoter search_regering search_voteringar summarize_regering_document

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 & specific32/32
has a description32/32
description is substantive13/3213/32
parameters are typed32/32
parameters are described22/3222/32

32 of 32 tools graded · 32 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

2024-11-05
protocol version
session model
2.1.0
server version riksdag-regering-mcp

Capabilities: logging 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
2026-08-14T19:59:05Zok_tools2001532024-11-05
2026-08-12T05:34:19Zok_tools2001382024-11-05

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.KSAklfszf921/riksdag-regering-mcp.svg)](https://robinsaige.com/s/io.github.KSAklfszf921/riksdag-regering-mcp)

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