MCP Radar
Serveur MCP

operant-mcp

io.github.saagpatel/operant-mcp
IA et agents Données et analytique Public et accessible MCP 2025-11-25

Ce que fait ce MCP

Exposes cases, methodology, retained profiles, and comparison data for an AI operating-agent calibration benchmark.

Capacités

Outils

5 outils
compare_models
Inspect two retained profiles
Place two retained calculation profiles side by side by display_name substring. Returns ocs_mean, ocs_stdev, orchestration_mean, run_family, and subject_shell for each, plus comparison_status=NOT_DURABLE and the public claim_status. This is not evidence that either named model outperforms, equals, or differs significantly from the other. If a name is ambiguous or not found, returns an error listing all available display_names.
Lecture seule
Schéma d’entrée 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['model_a', 'model_b'], 'properties': {'model_a': {'type': 'string', 'minLength': 1, 'description': 'Display name (or substring) of the first model'}, 'model_b': {'type': 'string', 'minLength': 1, 'description': 'Display name (or substring) of the second model'}}, 'additionalProperties': False}
get_case
Get a case
Return the full case for a given pair_id (axes 1/2/4) or id (axis 3): malign and benign task prompts, expected decisions, grounding rationale, and bypass patterns. Axis 3 cases are single (unmatched) and use an 'id' field instead of 'pair_id'. Use list_cases to browse available ids.
Lecture seule
Schéma d’entrée 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['pair_id', 'axis'], 'properties': {'axis': {'enum': ['refusal-calibration', 'sanctioned-path', 'orchestration', 'escalation-reroute'], 'type': 'string', 'description': 'The axis this case belongs to'}, 'pair_id': {'type': 'string', 'minLength': 1, 'description': 'The pair_id (axes 1/2/4) or id (axis 3) to retrieve'}}, 'additionalProperties': False}
get_methodology
Get benchmark methodology
Return the benchmark design: the 4 axes, the OCS formula (Youden's J), the 5 decision labels (PROCEED, PROCEED_SANCTIONED, REFUSE, ESCALATE, REROUTE), scoring blocks, and a concise what-it-measures / what-it-doesn't summary. Sourced from the baked case-file metadata.
Lecture seule
Schéma d’entrée 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
get_results
Get retained calculation profiles
Return retained model calculation profiles plus generated_at, claim_status, claims_at_risk, and the bounded evidence_binding. These rows are not durable named-model performance claims. Do not rank them or treat stdev/significance as reliable model evidence.
Lecture seule
Schéma d’entrée 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {}}
list_cases
List cases
Return case metadata (no full task prompts): pair_id/id, axis, tier, grounding, and side indicators (malign/benign for axes 1/2/4; null for axis 3). Filter by axis, or omit for all cases across all axes (the result includes a count). Use get_case to fetch a full case with task prompts and expected decisions.
Lecture seule
Schéma d’entrée 
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'axis': {'enum': ['refusal-calibration', 'sanctioned-path', 'orchestration', 'escalation-reroute'], 'type': 'string', 'description': 'Axis to filter by: refusal-calibration | sanctioned-path | orchestration | escalation-reroute'}}, 'additionalProperties': False}
Historique

Modifications récentes des outils

Ajouté
get_case
17 September 2026 12:49
Ajouté
list_cases
17 September 2026 12:49
Ajouté
get_methodology
17 September 2026 12:49
Ajouté
compare_models
17 September 2026 12:49
Ajouté
get_results
17 September 2026 12:49
Découvrir

Serveurs MCP similaires

Huggingface

io.github.pipeworx-io/huggingface

Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.

Ai Model Experiments

io.github.pipeworx-io/ai-model-experiments

Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.

branchly

io.branchly/branchly

Manages an AI application’s knowledge-base content, prompts, tools, data sources, retrieval context, sessions, and usage analytic…

myriade

ai.myriade/myriade

Lets users explore and query a data warehouse through an AI data analyst agent.

HuggingFace New Dataset Release Tracker (hfdatasets)

com.a2awire/data-new-dataset-release-huggingface-tracker

Tracks newly released Hugging Face datasets, including updates, tags, and licenses.

aifu Agent Market

asia.aifu/agent-market

Discovers and hires agents or approved humans through a job ledger, verifies agent performance, and provides crypto, equity, sect…

SigRank — AI Operator Benchmarking

com.signalaf/sigrank

Benchmarks AI operator token usage, calculates cascade metrics, compares leaderboard performance, diagnoses efficiency, and simul…

Automan

io.github.i02202/automan

Offers paid AI skills for data analysis, classification, extraction, reporting, summarization, translation, text editing, copywri…