Should my agent depend on the MCP server io.github.rarasAI/raras?

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

raras

io.github.rarasAI/raras

Disease Twin — Brazil's rare-disease knowledge graph (10,468) over MCP. Source-grounded, PT-BR.

— the operator's own registry description reported

Publisher io.github.rarasAI · first seen 2026-08-12 · endpoint https://raras.org/api/mcp

allow

verdict

mid-slow-solo

cluster

ok_tools

answers

tools served

Dependency rating derived

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

Cluster mid-slow-solo · distinctiveness 0.595 (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

latency605 ms

vs populationslow

protocolcurrent

authopen

Use — can it use it?

tools21

vs populationmid

capabilities3

harnessB

Trust — can it rely on it?

identitysolo

servers on its host1

verifiabilityunassessed

duplicate inventoryno

drift events0

answers trueno primary

🔏 Signed receipt rr_4aa10d7c7dc63e9612319986 · 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_clinical_case explain_relation find_active_trials find_communities find_diseases_by_phenotypes find_papers_for_disease find_phenotypically_similar find_reference_centers find_similar_diseases get_disease_detail get_evidence get_graph_stats get_hypotheses get_literature_relations get_recent_updates get_research_log get_schema get_sus_coverage search_diseases search_papers_semantic search_phenotypes

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 check	tools passing	ok
name is clear & specific	21/21	✓
has a description	21/21	✓
description is substantive	16/21	16/21
parameters are typed	21/21	✓
parameters are described	2/21	2/21

21 of 21 tools graded · 21 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

0.1.0

server version rarasnet-http

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)

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

raw probe records

probed (UTC)	outcome	http	ms	protocol
2026-08-14T20:00:09Z	ok_tools	200	605	2025-06-18
2026-08-12T05:35:22Z	ok_tools	200	247	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.rarasAI/raras.svg)](https://robinsaige.com/s/io.github.rarasAI/raras)

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