← Back to search

OpenClaw Consensus

MICONNM Scanned 1d ago

9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.

MCP Registry ↗
B
88.2 / 100

Versions

0.1.1latest
first seen May 19, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 3

consensus
annotations: none low

Get a 9-LLM consensus answer. Args: prompt: The user question or instruction. mode: ``deep`` (9 models), ``balanced`` (5), or ``fast`` (3). Returns: A dict with ``answer``, ``confidence`` (0..1), ``models_used`` (list), and ``disagreement`` (0..1, higher = riskier hallucination signal).

mode str prompt str
disagreement_score
annotations: none low

Score how much the 9 models disagree on a prompt (0..1). A high score is a useful hallucination warning: when frontier models disagree, single-model answers are more likely to be wrong. Returns: ``{"score": float, "per_model": {model: answer_summary}}``.

prompt str
cheapest_route
annotations: none low

Recommend the cheapest model combination that meets a quality bar. Args: prompt: The user prompt to route. target_quality: Minimum acceptable quality, 0..1. Default 0.85. Returns: ``{"models": [...], "estimated_cost_usd": float, "estimated_quality": float}``.

prompt str target_quality float

Permissions 3

network medium
Server uses network capabilities via: httpx
filesystem low
Server uses filesystem capabilities via: os
env_vars low
Server uses env_vars capabilities via: os.environ

Scan Findings 16

low
Tool 'consensus' has no annotations annotation_checker · 100%
low
Tool 'disagreement_score' has no annotations annotation_checker · 100%
low
Tool 'cheapest_route' has no annotations annotation_checker · 100%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
info
pyproject.toml metadata manifest_parser · 100%
info
Tool: consensus manifest_parser · 90%
info
Tool: disagreement_score manifest_parser · 90%
info
Tool: cheapest_route manifest_parser · 90%
info
Required env vars (4) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 90%
low
Permission: filesystem access detected permission_analyzer · 70%
low
Permission: env_vars access detected permission_analyzer · 90%
info
No dependency files found for SBOM generation sbom_generator · 100%
high
Generic API Key Assignment found in MICONNM-openclaw-consensus-mcp-8f02319/smithery.yaml secret_scanner · 75%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%