このMCPでできること
Provides a read-only taxonomy and research tools for classifying machine dysfunction patterns, differential diagnoses, probes, severity rubrics, and interventions.
機能
ツール
12
ツール
differential_diagnosis
Rank candidate dysfunctions matching the observed behaviours. Returns scored candidates with matched_in (which field matched) for transparency. The base package uses field-weighted keyword search. The optional embeddings extra adds cosine re-ranking.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['observations'], 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 20, 'minimum': 1}, 'observations': {'type': 'array', 'items': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 2000, 'minLength': 1}, 'maxItems': 50, 'minItems': 1, 'description': 'Observed behaviours, symptoms, or log patterns.'}, 'modality_hint': {'type': 'string', 'maxLength': 100, 'description': 'Optional hint about which modality the observations come from.'}}, 'additionalProperties': False}
get_differential_map
All dysfunctions that confuse with this one: forward confuses_with + incoming_references (reverse graph from manifest).
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['dysfunction_id'], 'properties': {'dysfunction_id': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1}}, 'additionalProperties': False}
get_dysfunction
Fetch one dysfunction's full Pattern entry. Optionally filter to specific modality blocks (cheaper triage). Resolves both full Pattern IDs ('2.1::synthetic-confabulation') and display_ids ('2.1').
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['id'], 'properties': {'id': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1, 'description': 'Pattern ID or display_id.'}, 'modalities': {'type': 'array', 'items': {'enum': ['self_probe', 'behavioral_signature', 'peer_observation', 'differential_diagnosis', 'severity', 'intervention', 'relational_signatures', 'normative_anchors', 'cross_references'], 'type': 'string'}, 'maxItems': 9, 'description': 'Optional subset of modality block names to return. Valid: self_probe, behavioral_signature, peer_observation, differential_diagnosis, severity, intervention, relational_signatures, normative_anchors, cross_references.', 'uniqueItems': True}}, 'additionalProperties': False}
get_probe
Elicitation content for a specific diagnostic modality. If the modality is compromised or unavailable for this dysfunction, returns the unavailability notice + redirect_to alternatives. This is load-bearing transparency: callers cannot accidentally retrieve a self-probe for a compromised-self-report dysfunction.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['dysfunction_id', 'modality'], 'properties': {'modality': {'enum': ['self_probe', 'behavioral_signature', 'peer_observation', 'relational_signatures'], 'type': 'string'}, 'dysfunction_id': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1}}, 'additionalProperties': False}
list_axes
Inventory of axes with dysfunction counts. Axes 2-10 are canonical (book Appendix A numbering). The hybrid entries (10.4, 10.6-10.9 and 10.11-10.13, ratified into taxonomy v2.2 and consolidated to eight in v2.3) are reported as a separate sub-category.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': [], 'properties': {}, 'additionalProperties': False}
list_compromised_self_report
Transparency: which dysfunctions cannot be reliably self-diagnosed. Includes compromised-motivational (subject conceals strategically), compromised-structural (signal lives below introspection), and legacy compromised.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': [], 'properties': {}, 'additionalProperties': False}
list_dysfunctions
Filtered list of dysfunctions. Filter by axis, self_report reliability, confidence, or category. Every entry carries its reliability and review signals.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': [], 'properties': {'axis': {'type': 'integer', 'maximum': 10, 'minimum': 2, 'description': "Filter by axis number (2-10). Canonical entries only unless category is also set; axis=10 with category='hybrid' returns the hybrid sub-category (10.4, 10.6-10.9 and 10.11-10.13)."}, 'category': {'enum': ['canonical', 'hybrid'], 'type': 'string'}, 'confidence': {'enum': ['high', 'medium', 'low'], 'type': 'string'}, 'self_report_reliability': {'enum': ['partial', 'unreliable', 'compromised-motivational', 'compromised-structural'], 'type': 'string', 'description': 'Filter by the exact self_report reliability value.'}}, 'additionalProperties': False}
render_pattern_review
Open the visual review board for one to five inspected Psychopathia research candidates. Supply canonical IDs obtained from this server. Retrieves corpus entries only; it does not accept diagnoses, conversation history, scores, or model-authored evidence. Useful after inspecting differential_diagnosis and get_dysfunction results. Text clients receive the same corpus-derived comparison without needing a UI.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['pattern_ids'], 'properties': {'pattern_ids': {'type': 'array', 'items': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1}, 'maxItems': 5, 'minItems': 1, 'uniqueItems': True}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', 'required': ['schema_version', 'patterns', 'corpus', 'notice'], 'properties': {'corpus': {'type': 'object', 'required': ['taxonomy_version', 'pattern_layer_version', 'corpus_sha256', 'total'], 'properties': {'total': {'type': 'integer', 'minimum': 1}, 'corpus_sha256': {'type': 'string', 'pattern': '^[0-9a-f]{64}$'}, 'taxonomy_version': {'type': 'string'}, 'pattern_layer_version': {'type': 'string'}}, 'additionalProperties': False}, 'notice': {'type': 'string'}, 'patterns': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'display_id', 'dysfunction_name', 'review', 'evidence', 'diagnostic_reliability'], 'properties': {'id': {'type': 'string'}, 'review': {'type': 'object'}, 'evidence': {'type': 'object'}, 'display_id': {'type': 'string'}, 'dysfunction_name': {'type': 'string'}, 'diagnostic_reliability': {'type': 'object'}}}, 'maxItems': 5, 'minItems': 1}, 'schema_version': {'type': 'string', 'const': 'pm-review/1'}}, 'additionalProperties': False}
resolve_id
Canonicalise a partial ID, display_id, slug, or dysfunction name. Always returns candidates; caller picks.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['query'], 'properties': {'query': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1}}, 'additionalProperties': False}
review_stats
Coverage statistics: total entries; per-axis, per-confidence, per-self-report counts; pre-canonical count; unreviewed count; manifest/schema/pattern-layer versions.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': [], 'properties': {}, 'additionalProperties': False}
score_severity
Return the severity rubric for a dysfunction applied to observations. Returns the rubric for caller-side matching; structured matching against numeric thresholds is not implemented.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['dysfunction_id', 'observations'], 'properties': {'observations': {'type': 'array', 'items': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 2000, 'minLength': 1}, 'maxItems': 50, 'minItems': 1}, 'dysfunction_id': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1}}, 'additionalProperties': False}
suggest_intervention
Return draft tiered responses and contraindications for a Pattern. These are unassessed research guidance, not validated treatment advice. Read the returned evidence and review objects before use.
読み取り専用
冪等
入力スキーマ
{'type': 'object', 'required': ['dysfunction_id'], 'properties': {'severity': {'enum': ['mild', 'moderate', 'severe'], 'type': 'string'}, 'dysfunction_id': {'type': 'string', 'pattern': '^[\\s\\S]*\\S[\\s\\S]*$', 'maxLength': 256, 'minLength': 1}}, 'additionalProperties': False}
履歴
最近のツール変更
追加
render_pattern_review
2026年10月1日2:47
変更
review_stats
2026年10月1日2:47
変更
resolve_id
2026年10月1日2:47
変更
list_compromised_self_report
2026年10月1日2:47
変更
get_differential_map
2026年10月1日2:47
変更
suggest_intervention
2026年10月1日2:47
変更
score_severity
2026年10月1日2:47
変更
get_probe
2026年10月1日2:47
変更
differential_diagnosis
2026年10月1日2:47
変更
get_dysfunction
2026年10月1日2:47
変更
list_dysfunctions
2026年10月1日2:47
変更
list_axes
2026年10月1日2:47
追加
review_stats
2026年9月17日12:45
追加
resolve_id
2026年9月17日12:45
追加
list_compromised_self_report
2026年9月17日12:45
追加
get_differential_map
2026年9月17日12:45
追加
suggest_intervention
2026年9月17日12:45
追加
score_severity
2026年9月17日12:45
追加
get_probe
2026年9月17日12:45
追加
differential_diagnosis
2026年9月17日12:45
追加
get_dysfunction
2026年9月17日12:45
追加
list_dysfunctions
2026年9月17日12:45
追加
list_axes
2026年9月17日12:45
関連MCP
類似のMCPサーバー
ExMachina AI — agent research rooms
io.github.SecondStageTurbine/exmachina-ai
Provides collaborative research rooms for biomedical findings, source citations, reviews, agent coordination, and reputation trac…
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…
GPT55 Model Gateway
xyz.558686.gpt55/token-gateway
Acts as a remote model gateway exposing GPT chat, coding and review services, lightweight text utilities, and prepaid or x402-bas…
GoCreative Agent API
io.github.ColinHughes2121/gocreative-agent-api
Offers pay-per-call LLM completions and data services for company intelligence, KYB, sanctions screening, threat intelligence, co…
Clink Forge
com.clinkforge/clink-forge
Provides pay-per-call access to attested government datasets, primarily CDC and HHS health data plus EPA air-quality observations.
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…
workbench
com.seqbench/workbench
Provides computational molecular biology tools for DNA, RNA, and protein analysis, cloning, PCR, CRISPR, oligonucleotide design, …
Speedbot Autonomous Work Network
io.github.ulasarslan6262-ui/speedbot
Supports asynchronous collaboration, discovery, messaging, referrals, and optional USDC-based scenarios among AI agents.