MCP Radar
MCPサーバー

Batcave Detective Basic

io.github.Bjorn2-sol/batcave-detective
AI・エージェント 開発者向けツール 公開・接続可能 MCP 2025-11-25

このMCPでできること

Offers evidence-based agent conclusion audits, structured scenario reviews, JSON repair, and sandboxed Python execution.

機能

ツール

5 ツール
detective_basic
Detective Basic
Batcave paid product at /v1/audit-claims. The canonical product contract is published by STORE OpenAPI. Price: 0.02 USD via x402. Calling this MCP tool returns the canonical REST/x402 checkout contract; it does not execute the product or charge the caller yet.
入力スキーマ 
{'type': 'object', 'required': ['original_task', 'current_conclusion', 'claims'], 'properties': {'task': {'enum': ['audit_claims'], 'type': 'string'}, 'claims': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'text'], 'properties': {'id': {'type': 'string', 'maxLength': 64}, 'text': {'type': 'string', 'maxLength': 1000}}, 'additionalProperties': False}, 'maxItems': 12, 'minItems': 1}, 'job_id': {'type': 'string', 'maxLength': 128}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'text'], 'properties': {'id': {'type': 'string', 'maxLength': 64}, 'text': {'type': 'string', 'maxLength': 1200}}, 'additionalProperties': False}, 'maxItems': 20}, 'importance': {'enum': ['low', 'medium', 'high'], 'type': 'string'}, 'original_task': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'reasoning_summary': {'type': 'string', 'maxLength': 5000}, 'current_conclusion': {'type': 'string', 'maxLength': 3000, 'minLength': 1}, 'freshness_expectation': {'type': 'string', 'maxLength': 500}}, 'additionalProperties': True}
evidence_judge
Evidence Judge
Batcave paid product at /v1/review-decision. The canonical product contract is published by STORE OpenAPI. Price: 0.02 USD via x402. Calling this MCP tool returns the canonical REST/x402 checkout contract; it does not execute the product or charge the caller yet.
入力スキーマ 
{'type': 'object', 'required': ['proposed_action'], 'properties': {'risk': {'enum': ['low', 'medium', 'high'], 'type': 'string'}, 'task': {'enum': ['review_decision'], 'type': 'string'}, 'job_id': {'type': 'string', 'maxLength': 128}, 'evidence': {'type': 'array', 'items': {'type': 'string', 'maxLength': 1000}, 'maxItems': 16}, 'proposed_action': {'type': 'string', 'maxLength': 2000, 'minLength': 1}, 'reasoning_summary': {'type': 'string', 'maxLength': 4000}}, 'additionalProperties': True}
json_doctor
JSON Doctor
Deterministic CPU-only utility. Repairs a bounded set of common JSON syntax mistakes, returns canonical JSON, and optionally validates a documented JSON Schema subset. Missing fields are reported, never invented. Price: 0.003 USD via x402. Calling this MCP tool returns the canonical REST/x402 checkout contract; it does not execute the product or charge the caller yet.
入力スキーマ 
{'type': 'object', 'title': 'Job', 'required': ['text'], 'properties': {'mode': {'enum': ['repair_and_validate', 'repair_only', 'validate_only'], 'type': 'string', 'default': 'repair_and_validate'}, 'text': {'type': 'string', 'maxLength': 262144, 'minLength': 1, 'description': 'JSON or JSON-like text to parse, conservatively repair, and return.'}, 'job_id': {'type': 'string', 'maxLength': 128}, 'schema': {'type': 'object', 'description': 'Optional structural JSON Schema. JSON Doctor validates the documented supported keyword subset and reports unsupported keywords explicitly.'}}, 'additionalProperties': False}
run_python
Run Python
Execute supplied Python files in a fresh disposable CPU-only container. No outbound network, no GPU, and no host filesystem access beyond the disposable workspace. Returns bounded execution evidence, requested artifacts, and Execution Receipt v1. Price: 0.01 USD via x402. Calling this MCP tool returns the canonical REST/x402 checkout contract; it does not execute the product or charge the caller yet.
入力スキーマ 
{'type': 'object', 'required': ['files'], 'properties': {'cpus': {'type': 'number', 'maximum': 2.0, 'minimum': 0.1}, 'files': {'type': 'object', 'description': 'Relative file path -> UTF-8 text content.', 'maxProperties': 64, 'minProperties': 1, 'additionalProperties': {'type': 'string'}}, 'stdin': {'type': 'string'}, 'job_id': {'type': 'string'}, 'command': {'type': 'array', 'items': {'type': 'string'}, 'description': "Optional argv; defaults to ['python','main.py']."}, 'runtime': {'enum': ['python'], 'type': 'string'}, 'memory_mb': {'type': 'integer', 'maximum': 1024, 'minimum': 64}, 'artifact_paths': {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 16}, 'timeout_seconds': {'type': 'integer', 'maximum': 30, 'minimum': 1}}, 'additionalProperties': False}
scenario_council
Scenario Council
Runs exactly four fixed roles (Operator, Skeptic, Buyer, Adversary) for 1-3 bounded rounds over only the caller-supplied question, context, and evidence. Returns every role position, evidence lineage, structured peer challenges, belief changes, disagreements, falsifiers, deterministic process-integrity results, and one independent Detective Basic audit of the four final conclusions. Does not retrieve outside facts, execute actions, treat peer statements as evidence, or treat majority agreement as truth. Price: 0.25 USD via x402. Calling this MCP tool returns the canonical REST/x402 checkout contract; it does not execute the product or charge the caller yet.
入力スキーマ 
{'type': 'object', 'required': ['question'], 'properties': {'job_id': {'type': 'string', 'maxLength': 128}, 'rounds': {'type': 'integer', 'default': 3, 'maximum': 3, 'minimum': 1}, 'context': {'type': 'string', 'maxLength': 6000}, 'evidence': {'type': 'array', 'items': {'oneOf': [{'type': 'string', 'maxLength': 1200}, {'type': 'object', 'required': ['text'], 'properties': {'id': {'type': 'string', 'maxLength': 64}, 'text': {'type': 'string', 'maxLength': 1200, 'minLength': 1}}, 'additionalProperties': False}]}, 'maxItems': 20}, 'question': {'type': 'string', 'maxLength': 2000, 'minLength': 1}}, 'additionalProperties': True}
履歴

最近のツール変更

追加
json_doctor
2026年9月21日2:40
追加
scenario_council
2026年9月21日2:40
追加
run_python
2026年9月21日2:40
追加
detective_basic
2026年9月21日2:40
追加
evidence_judge
2026年9月21日2:40
関連MCP

類似のMCPサーバー

Andreax

io.github.moralito311-andr/andreax

Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…

IA-QA — 130+ QA & Dev Tools for AI Agents

io.github.JcJamet/ia-qa-toolbox

Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…

CompletionKit

com.completionkit/evals

Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…

Replicate

io.github.pipeworx-io/replicate

Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…

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.

rubrkit

com.rubrkit/rubrkit

Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.

Hipocampo MCP

io.github.carrasquelalex1/hipocampo

Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…