MCP-Server
DEEPBOM
io.github.JunHwan-Kwon/deepbom
Was dieses MCP kann
Statically analyzes supported deployed AI model artifacts, producing hash-bound format-neutral model information without executing model code.
Funktionen
Tools
7
Tools
deepbom_analyze_file
Analyze an AI model artifact
Use when the user asks to inspect, summarize, or visualize an attached TFLite, ONNX, GGUF, SafeTensors, Core ML, or ExecuTorch deployment artifact. Opens a browser-local analyzer, returns a hash-bound format-neutral Model IR table and static evidence summary, and provides deterministic document views without executing model code. Do not use for training checkpoints, measured latency, task accuracy, clinical validity, regulatory compliance, or actual runtime placement.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', '$defs': {'OpenAIFile': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string'}, 'file_name': {'type': 'string'}, 'mime_type': {'type': 'string'}, 'download_url': {'type': 'string'}}, 'additionalProperties': False}}, 'required': ['file'], 'properties': {'file': {'$ref': '#/$defs/OpenAIFile'}, 'analysis_depth': {'enum': ['structure', 'payload_integrity'], 'type': 'string', 'default': 'structure', 'description': 'Use structure unless the user explicitly asks to inspect serialized tensor payload values. Payload integrity can require reading the complete attachment.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['status', 'analyzer_version', 'file', 'analysis_depth', 'privacy'], 'properties': {'file': {'type': 'object', 'required': ['file_id', 'file_name', 'mime_type'], 'properties': {'file_id': {'type': 'string'}, 'file_name': {'type': ['string', 'null']}, 'mime_type': {'type': ['string', 'null']}}, 'additionalProperties': False}, 'status': {'type': 'string', 'const': 'browser_analysis_started'}, 'privacy': {'type': 'string'}, 'analysis_depth': {'type': 'string'}, 'analyzer_version': {'type': 'string'}}, 'additionalProperties': False}
deepbom_capabilities
Check DEEPBOM capabilities
Use before analysis when format support, privacy boundaries, or the difference between the ChatGPT and local DEEPBOM paths is unclear. Returns capability metadata only and does not inspect a file.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', 'properties': {}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['schema', 'version', 'supported_formats', 'chatgpt_path', 'local_path', 'evidence_boundary'], 'properties': {'schema': {'type': 'string'}, 'version': {'type': 'string'}, 'local_path': {'type': 'object'}, 'chatgpt_path': {'type': 'object'}, 'evidence_boundary': {'type': 'string'}, 'supported_formats': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}
deepbom_publish_analysis
Return a DEEPBOM analysis to chat
Receives one bounded browser-produced DEEPBOM result, validates its structure, and returns it to the conversation. This tool accepts analysis results, never model bytes.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'object', 'anyOf': [{'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'artifact', 'verdict', 'graph', 'storage', 'quantization', 'model_summary', 'findings', 'evidence_boundary', 'transfer_boundary', 'reproduction'], 'properties': {'graph': {'type': 'object', 'required': ['operator_count', 'tensor_count', 'total_macs', 'mac_confidence'], 'properties': {'total_macs': {'type': ['number', 'null'], 'minimum': 0}, 'tensor_count': {'type': ['integer', 'null'], 'minimum': 0}, 'mac_confidence': {'type': 'string'}, 'operator_count': {'type': ['integer', 'null'], 'minimum': 0}}, 'additionalProperties': False}, 'schema': {'type': 'string', 'const': 'deepbom.chatgpt_analysis_result.v1'}, 'storage': {'type': ['object', 'null']}, 'verdict': {'type': 'object', 'required': ['status', 'artifact_defect_count', 'caution_count', 'evidence_needed_count'], 'properties': {'status': {'type': 'string'}, 'caution_count': {'type': 'integer', 'minimum': 0}, 'artifact_defect_count': {'type': 'integer', 'minimum': 0}, 'evidence_needed_count': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'artifact': {'type': 'object', 'required': ['filename', 'format', 'sha256', 'byte_length'], 'properties': {'format': {'type': 'string'}, 'sha256': {'type': 'string'}, 'filename': {'type': 'string'}, 'byte_length': {'type': 'integer', 'minimum': 0}, 'artifact_ir_sha256': {'type': ['string', 'null']}}, 'additionalProperties': False}, 'findings': {'type': 'object'}, 'quantization': {'type': 'object'}, 'reproduction': {'type': ['object', 'null']}, 'model_summary': {'type': 'object'}, 'analyzer_version': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'evidence_boundary': {'type': 'string'}, 'transfer_boundary': {'type': 'string'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'artifact', 'verdict', 'graph', 'storage', 'quantization', 'model_summary', 'findings', 'evidence_boundary', 'transfer_boundary', 'reproduction'], 'properties': {'graph': {'type': 'object', 'required': ['operator_count', 'tensor_count', 'total_macs', 'mac_confidence'], 'properties': {'total_macs': {'type': ['number', 'null'], 'minimum': 0}, 'tensor_count': {'type': ['integer', 'null'], 'minimum': 0}, 'mac_confidence': {'type': 'string'}, 'operator_count': {'type': ['integer', 'null'], 'minimum': 0}}, 'additionalProperties': False}, 'schema': {'type': 'string', 'const': 'deepbom.chatgpt_analysis_result.v2'}, 'storage': {'type': ['object', 'null']}, 'verdict': {'type': 'object', 'required': ['status', 'artifact_defect_count', 'caution_count', 'evidence_needed_count'], 'properties': {'status': {'type': 'string'}, 'caution_count': {'type': 'integer', 'minimum': 0}, 'artifact_defect_count': {'type': 'integer', 'minimum': 0}, 'evidence_needed_count': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'artifact': {'type': 'object', 'required': ['filename', 'format', 'sha256', 'byte_length'], 'properties': {'format': {'type': 'string'}, 'sha256': {'type': 'string'}, 'filename': {'type': 'string'}, 'byte_length': {'type': 'integer', 'minimum': 0}, 'artifact_ir_sha256': {'type': ['string', 'null']}}, 'additionalProperties': False}, 'findings': {'type': 'object'}, 'quantization': {'type': 'object'}, 'reproduction': {'type': ['object', 'null']}, 'model_summary': {'type': 'object'}, 'analyzer_version': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'evidence_boundary': {'type': 'string'}, 'transfer_boundary': {'type': 'string'}, 'provenance_summary': {'type': 'object', 'required': ['schema', 'artifact_sha256', 'model_ir_sha256', 'provenance_ir_sha256', 'status', 'node_count', 'relationship_count', 'observed_file_count', 'check_count', 'field_count', 'mapped_declared_field_count', 'unsupported_field_count', 'attested_relationship_count', 'check_counts', 'metadata_truth_verified', 'publisher_authenticity'], 'properties': {'schema': {'type': 'string', 'const': 'deepbom.provenance_summary.v1'}, 'status': {'enum': ['contradiction_observed', 'incomplete', 'no_contradiction_observed'], 'type': 'string'}, 'node_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'check_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'field_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'check_counts': {'type': 'object', 'required': ['match', 'mismatch', 'not_assessed', 'unresolved', 'unsupported'], 'properties': {'match': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'mismatch': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'unresolved': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'unsupported': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'not_assessed': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}}, 'additionalProperties': False}, 'artifact_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'model_ir_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'relationship_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'observed_file_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'provenance_ir_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'publisher_authenticity': {'type': 'string', 'const': 'not_verified'}, 'metadata_truth_verified': {'type': 'boolean', 'const': False}, 'unsupported_field_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'attested_relationship_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'mapped_declared_field_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}}, 'additionalProperties': False}}, 'additionalProperties': False}]}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'anyOf': [{'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'artifact', 'verdict', 'graph', 'storage', 'quantization', 'model_summary', 'findings', 'evidence_boundary', 'transfer_boundary', 'reproduction'], 'properties': {'graph': {'type': 'object', 'required': ['operator_count', 'tensor_count', 'total_macs', 'mac_confidence'], 'properties': {'total_macs': {'type': ['number', 'null'], 'minimum': 0}, 'tensor_count': {'type': ['integer', 'null'], 'minimum': 0}, 'mac_confidence': {'type': 'string'}, 'operator_count': {'type': ['integer', 'null'], 'minimum': 0}}, 'additionalProperties': False}, 'schema': {'type': 'string', 'const': 'deepbom.chatgpt_analysis_result.v1'}, 'storage': {'type': ['object', 'null']}, 'verdict': {'type': 'object', 'required': ['status', 'artifact_defect_count', 'caution_count', 'evidence_needed_count'], 'properties': {'status': {'type': 'string'}, 'caution_count': {'type': 'integer', 'minimum': 0}, 'artifact_defect_count': {'type': 'integer', 'minimum': 0}, 'evidence_needed_count': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'artifact': {'type': 'object', 'required': ['filename', 'format', 'sha256', 'byte_length'], 'properties': {'format': {'type': 'string'}, 'sha256': {'type': 'string'}, 'filename': {'type': 'string'}, 'byte_length': {'type': 'integer', 'minimum': 0}, 'artifact_ir_sha256': {'type': ['string', 'null']}}, 'additionalProperties': False}, 'findings': {'type': 'object'}, 'quantization': {'type': 'object'}, 'reproduction': {'type': ['object', 'null']}, 'model_summary': {'type': 'object'}, 'analyzer_version': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'evidence_boundary': {'type': 'string'}, 'transfer_boundary': {'type': 'string'}}, 'additionalProperties': False}, {'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'artifact', 'verdict', 'graph', 'storage', 'quantization', 'model_summary', 'findings', 'evidence_boundary', 'transfer_boundary', 'reproduction'], 'properties': {'graph': {'type': 'object', 'required': ['operator_count', 'tensor_count', 'total_macs', 'mac_confidence'], 'properties': {'total_macs': {'type': ['number', 'null'], 'minimum': 0}, 'tensor_count': {'type': ['integer', 'null'], 'minimum': 0}, 'mac_confidence': {'type': 'string'}, 'operator_count': {'type': ['integer', 'null'], 'minimum': 0}}, 'additionalProperties': False}, 'schema': {'type': 'string', 'const': 'deepbom.chatgpt_analysis_result.v2'}, 'storage': {'type': ['object', 'null']}, 'verdict': {'type': 'object', 'required': ['status', 'artifact_defect_count', 'caution_count', 'evidence_needed_count'], 'properties': {'status': {'type': 'string'}, 'caution_count': {'type': 'integer', 'minimum': 0}, 'artifact_defect_count': {'type': 'integer', 'minimum': 0}, 'evidence_needed_count': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'artifact': {'type': 'object', 'required': ['filename', 'format', 'sha256', 'byte_length'], 'properties': {'format': {'type': 'string'}, 'sha256': {'type': 'string'}, 'filename': {'type': 'string'}, 'byte_length': {'type': 'integer', 'minimum': 0}, 'artifact_ir_sha256': {'type': ['string', 'null']}}, 'additionalProperties': False}, 'findings': {'type': 'object'}, 'quantization': {'type': 'object'}, 'reproduction': {'type': ['object', 'null']}, 'model_summary': {'type': 'object'}, 'analyzer_version': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'evidence_boundary': {'type': 'string'}, 'transfer_boundary': {'type': 'string'}, 'provenance_summary': {'type': 'object', 'required': ['schema', 'artifact_sha256', 'model_ir_sha256', 'provenance_ir_sha256', 'status', 'node_count', 'relationship_count', 'observed_file_count', 'check_count', 'field_count', 'mapped_declared_field_count', 'unsupported_field_count', 'attested_relationship_count', 'check_counts', 'metadata_truth_verified', 'publisher_authenticity'], 'properties': {'schema': {'type': 'string', 'const': 'deepbom.provenance_summary.v1'}, 'status': {'enum': ['contradiction_observed', 'incomplete', 'no_contradiction_observed'], 'type': 'string'}, 'node_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'check_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'field_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'check_counts': {'type': 'object', 'required': ['match', 'mismatch', 'not_assessed', 'unresolved', 'unsupported'], 'properties': {'match': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'mismatch': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'unresolved': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'unsupported': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'not_assessed': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}}, 'additionalProperties': False}, 'artifact_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'model_ir_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'relationship_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'observed_file_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'provenance_ir_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'publisher_authenticity': {'type': 'string', 'const': 'not_verified'}, 'metadata_truth_verified': {'type': 'boolean', 'const': False}, 'unsupported_field_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'attested_relationship_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}, 'mapped_declared_field_count': {'type': 'integer', 'maximum': 1000000, 'minimum': 0}}, 'additionalProperties': False}}, 'additionalProperties': False}]}
deepbom_publish_error
Return a DEEPBOM analysis error to chat
Receives one bounded browser-produced DEEPBOM error and returns a recovery action to the conversation. This tool accepts diagnostic text, never model bytes.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', 'required': ['error'], 'properties': {'error': {'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'code', 'message', 'suggested_action', 'file_name', 'transfer_boundary'], 'properties': {'code': {'type': 'string'}, 'schema': {'type': 'string', 'const': 'deepbom.chatgpt_error.v1'}, 'message': {'type': 'string'}, 'file_name': {'type': ['string', 'null']}, 'analyzer_version': {'type': 'string'}, 'suggested_action': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'transfer_boundary': {'type': 'string', 'const': 'model_bytes_not_sent_to_deepbom_service'}}, 'additionalProperties': False}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'code', 'message', 'suggested_action', 'file_name', 'transfer_boundary'], 'properties': {'code': {'type': 'string'}, 'schema': {'type': 'string', 'const': 'deepbom.chatgpt_error.v1'}, 'message': {'type': 'string'}, 'file_name': {'type': ['string', 'null']}, 'analyzer_version': {'type': 'string'}, 'suggested_action': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'transfer_boundary': {'type': 'string', 'const': 'model_bytes_not_sent_to_deepbom_service'}}, 'additionalProperties': False}
deepbom_publish_query
Return requested model evidence to chat
Component-only: validates and returns a bounded Evidence IR query projection for the same attachment. No model bytes, state persistence, or runtime execution. Result digests establish consistency, not independent server attestation.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', 'required': ['result'], 'properties': {'result': {'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'artifact', 'model_ir_sha256', 'query', 'query_sha256', 'status', 'coverage', 'context', 'rows', 'evidence_boundary', 'transfer_boundary', 'result_sha256'], 'properties': {'rows': {'type': 'array', 'items': {'type': 'object', 'required': ['subject_ref', 'kind', 'title', 'details', 'detail_truncations'], 'properties': {'kind': {'type': 'string'}, 'title': {'type': 'string'}, 'details': {'type': 'object'}, 'subject_ref': {'type': 'string'}, 'detail_truncations': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}, 'maxItems': 40}, 'query': {'type': 'object', 'required': ['section'], 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 40, 'minimum': 1}, 'offset': {'type': 'integer', 'default': 0, 'minimum': 0}, 'search': {'type': 'string', 'maxLength': 160, 'description': 'Literal case-insensitive filter over row names and references.'}, 'target': {'type': 'string', 'maxLength': 128, 'minLength': 1, 'description': 'Optional TFLite CPU planning profile ID from capabilities. Not detected hardware or a GPU delegate selector.'}, 'section': {'enum': ['operators', 'operator', 'findings', 'placement', 'fusion', 'improvements', 'profiles', 'weights'], 'type': 'string'}, 'profile_ids': {'type': 'array', 'items': {'type': 'string', 'maxLength': 128, 'minLength': 1}, 'maxItems': 4, 'description': 'Exact static backend profile IDs returned by section=profiles. Independent eligibility profiles, not runtime assignments.', 'uniqueItems': True}, 'subject_ref': {'type': 'string', 'maxLength': 512, 'minLength': 1, 'description': 'Exact Model IR subject_ref from a previous result; preferred over an index.'}, 'weight_view': {'enum': ['distribution', 'channels', 'similarity', 'spectrum', 'sparsity', 'quantization'], 'type': 'string', 'description': 'Only for section=weights: explicitly opt into bounded payload analysis; use returned weight subject_ref to select a tensor. Default distribution.'}, 'source_index': {'type': 'integer', 'minimum': 0, 'description': 'Native serialized operator index, not display order. Ambiguous indices require subject_ref.'}}, 'additionalProperties': False}, 'schema': {'type': 'string', 'const': 'deepbom.evidence_query_result.v1'}, 'status': {'enum': ['complete', 'partial', 'not_assessable', 'no_matches'], 'type': 'string'}, 'context': {'type': 'object'}, 'artifact': {'type': 'object', 'required': ['filename', 'format', 'sha256'], 'properties': {'format': {'type': 'string'}, 'sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'filename': {'type': 'string'}}, 'additionalProperties': False}, 'coverage': {'type': 'object', 'required': ['total_rows', 'matched_rows', 'returned_rows', 'offset', 'next_offset', 'detail_truncated'], 'properties': {'offset': {'type': 'integer', 'minimum': 0}, 'total_rows': {'type': 'integer', 'minimum': 0}, 'next_offset': {'type': ['integer', 'null'], 'minimum': 0}, 'matched_rows': {'type': 'integer', 'minimum': 0}, 'returned_rows': {'type': 'integer', 'maximum': 40, 'minimum': 0}, 'detail_truncated': {'type': 'boolean'}}, 'additionalProperties': False}, 'query_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'result_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'model_ir_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'analyzer_version': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'evidence_boundary': {'type': 'string'}, 'transfer_boundary': {'type': 'string', 'const': 'model_bytes_not_sent_to_deepbom_service'}}, 'additionalProperties': False}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['schema', 'analyzer_version', 'analysis_location', 'artifact', 'model_ir_sha256', 'query', 'query_sha256', 'status', 'coverage', 'context', 'rows', 'evidence_boundary', 'transfer_boundary', 'result_sha256'], 'properties': {'rows': {'type': 'array', 'items': {'type': 'object', 'required': ['subject_ref', 'kind', 'title', 'details', 'detail_truncations'], 'properties': {'kind': {'type': 'string'}, 'title': {'type': 'string'}, 'details': {'type': 'object'}, 'subject_ref': {'type': 'string'}, 'detail_truncations': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}, 'maxItems': 40}, 'query': {'type': 'object', 'required': ['section'], 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 40, 'minimum': 1}, 'offset': {'type': 'integer', 'default': 0, 'minimum': 0}, 'search': {'type': 'string', 'maxLength': 160, 'description': 'Literal case-insensitive filter over row names and references.'}, 'target': {'type': 'string', 'maxLength': 128, 'minLength': 1, 'description': 'Optional TFLite CPU planning profile ID from capabilities. Not detected hardware or a GPU delegate selector.'}, 'section': {'enum': ['operators', 'operator', 'findings', 'placement', 'fusion', 'improvements', 'profiles', 'weights'], 'type': 'string'}, 'profile_ids': {'type': 'array', 'items': {'type': 'string', 'maxLength': 128, 'minLength': 1}, 'maxItems': 4, 'description': 'Exact static backend profile IDs returned by section=profiles. Independent eligibility profiles, not runtime assignments.', 'uniqueItems': True}, 'subject_ref': {'type': 'string', 'maxLength': 512, 'minLength': 1, 'description': 'Exact Model IR subject_ref from a previous result; preferred over an index.'}, 'weight_view': {'enum': ['distribution', 'channels', 'similarity', 'spectrum', 'sparsity', 'quantization'], 'type': 'string', 'description': 'Only for section=weights: explicitly opt into bounded payload analysis; use returned weight subject_ref to select a tensor. Default distribution.'}, 'source_index': {'type': 'integer', 'minimum': 0, 'description': 'Native serialized operator index, not display order. Ambiguous indices require subject_ref.'}}, 'additionalProperties': False}, 'schema': {'type': 'string', 'const': 'deepbom.evidence_query_result.v1'}, 'status': {'enum': ['complete', 'partial', 'not_assessable', 'no_matches'], 'type': 'string'}, 'context': {'type': 'object'}, 'artifact': {'type': 'object', 'required': ['filename', 'format', 'sha256'], 'properties': {'format': {'type': 'string'}, 'sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'filename': {'type': 'string'}}, 'additionalProperties': False}, 'coverage': {'type': 'object', 'required': ['total_rows', 'matched_rows', 'returned_rows', 'offset', 'next_offset', 'detail_truncated'], 'properties': {'offset': {'type': 'integer', 'minimum': 0}, 'total_rows': {'type': 'integer', 'minimum': 0}, 'next_offset': {'type': ['integer', 'null'], 'minimum': 0}, 'matched_rows': {'type': 'integer', 'minimum': 0}, 'returned_rows': {'type': 'integer', 'maximum': 40, 'minimum': 0}, 'detail_truncated': {'type': 'boolean'}}, 'additionalProperties': False}, 'query_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'result_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'model_ir_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}, 'analyzer_version': {'type': 'string'}, 'analysis_location': {'type': 'string', 'const': 'chatgpt_browser_sandbox'}, 'evidence_boundary': {'type': 'string'}, 'transfer_boundary': {'type': 'string', 'const': 'model_bytes_not_sent_to_deepbom_service'}}, 'additionalProperties': False}
deepbom_query_file
Inspect specific model evidence
Use for follow-up questions about an already identified attachment: inspect a layer by subject_ref, search or page through all operations, inspect findings, rank improvement investigations, inspect encoded activation fusion, compare source-pinned static delegate eligibility, or explicitly analyze weight distributions, channels, similarity, singular spectra, sparsity and quantization with section=weights and optional weight_view. Weight analysis reads payloads on demand with explicit decoder/budget coverage (128 MiB widget limit). Reuse the ChatGPT-authorized file and the exact SHA-256 from its previous DEEPBOM result. section=profiles lists available backend profiles; query.target selects only a TFLite CPU planning profile from capabilities. The browser computes the query from the shared Evidence IR and returns a bounded result; model bytes are not sent to DEEPBOM. Static candidate eligibility is not observed placement, speed, accuracy, or runtime fusion. Do not invent findings while browser_query_started is pending.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', '$defs': {'OpenAIFile': {'type': 'object', 'required': ['download_url', 'file_id'], 'properties': {'file_id': {'type': 'string'}, 'file_name': {'type': 'string'}, 'mime_type': {'type': 'string'}, 'download_url': {'type': 'string'}}, 'additionalProperties': False}}, 'required': ['file', 'expected_sha256', 'query'], 'properties': {'file': {'$ref': '#/$defs/OpenAIFile'}, 'query': {'type': 'object', 'required': ['section'], 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 40, 'minimum': 1}, 'offset': {'type': 'integer', 'default': 0, 'minimum': 0}, 'search': {'type': 'string', 'maxLength': 160, 'description': 'Literal case-insensitive filter over row names and references.'}, 'target': {'type': 'string', 'maxLength': 128, 'minLength': 1, 'description': 'Optional TFLite CPU planning profile ID from capabilities. Not detected hardware or a GPU delegate selector.'}, 'section': {'enum': ['operators', 'operator', 'findings', 'placement', 'fusion', 'improvements', 'profiles', 'weights'], 'type': 'string'}, 'profile_ids': {'type': 'array', 'items': {'type': 'string', 'maxLength': 128, 'minLength': 1}, 'maxItems': 4, 'description': 'Exact static backend profile IDs returned by section=profiles. Independent eligibility profiles, not runtime assignments.', 'uniqueItems': True}, 'subject_ref': {'type': 'string', 'maxLength': 512, 'minLength': 1, 'description': 'Exact Model IR subject_ref from a previous result; preferred over an index.'}, 'weight_view': {'enum': ['distribution', 'channels', 'similarity', 'spectrum', 'sparsity', 'quantization'], 'type': 'string', 'description': 'Only for section=weights: explicitly opt into bounded payload analysis; use returned weight subject_ref to select a tensor. Default distribution.'}, 'source_index': {'type': 'integer', 'minimum': 0, 'description': 'Native serialized operator index, not display order. Ambiguous indices require subject_ref.'}}, 'additionalProperties': False}, 'analysis_depth': {'enum': ['structure', 'payload_integrity'], 'type': 'string', 'default': 'structure', 'description': 'Use structure unless the user explicitly asks to inspect serialized tensor payload values. Payload integrity can require reading the complete attachment.'}, 'expected_sha256': {'type': 'string', 'pattern': '^[a-f0-9]{64}$'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['status', 'analyzer_version', 'expected_sha256', 'analysis_depth', 'query'], 'properties': {'query': {'type': 'object', 'required': ['section'], 'properties': {'limit': {'type': 'integer', 'default': 20, 'maximum': 40, 'minimum': 1}, 'offset': {'type': 'integer', 'default': 0, 'minimum': 0}, 'search': {'type': 'string', 'maxLength': 160, 'description': 'Literal case-insensitive filter over row names and references.'}, 'target': {'type': 'string', 'maxLength': 128, 'minLength': 1, 'description': 'Optional TFLite CPU planning profile ID from capabilities. Not detected hardware or a GPU delegate selector.'}, 'section': {'enum': ['operators', 'operator', 'findings', 'placement', 'fusion', 'improvements', 'profiles', 'weights'], 'type': 'string'}, 'profile_ids': {'type': 'array', 'items': {'type': 'string', 'maxLength': 128, 'minLength': 1}, 'maxItems': 4, 'description': 'Exact static backend profile IDs returned by section=profiles. Independent eligibility profiles, not runtime assignments.', 'uniqueItems': True}, 'subject_ref': {'type': 'string', 'maxLength': 512, 'minLength': 1, 'description': 'Exact Model IR subject_ref from a previous result; preferred over an index.'}, 'weight_view': {'enum': ['distribution', 'channels', 'similarity', 'spectrum', 'sparsity', 'quantization'], 'type': 'string', 'description': 'Only for section=weights: explicitly opt into bounded payload analysis; use returned weight subject_ref to select a tensor. Default distribution.'}, 'source_index': {'type': 'integer', 'minimum': 0, 'description': 'Native serialized operator index, not display order. Ambiguous indices require subject_ref.'}}, 'additionalProperties': False}, 'status': {'type': 'string', 'const': 'browser_query_started'}, 'analysis_depth': {'enum': ['structure', 'payload_integrity'], 'type': 'string', 'default': 'structure', 'description': 'Use structure unless the user explicitly asks to inspect serialized tensor payload values. Payload integrity can require reading the complete attachment.'}, 'expected_sha256': {'type': 'string'}, 'analyzer_version': {'type': 'string'}}, 'additionalProperties': False}
deepbom_workflow_guide
Choose a DEEPBOM analysis workflow
Use to discover how to answer a model-analysis question across ChatGPT, the interactive deepbom.org workspace and the local CLI. Returns real query sections, visualization/export actions, explicit web continuation links, required inputs, CLI argument templates and evidence limits for weights, pruning investigation, comparison, BOM verification, metadata/OMOP, activation evidence, runtime, batch/CI and integrations. No attachment is required. This is guidance, not a completed analysis or local command execution. Prefer answering from existing evidence; inspect supported follow-ups with deepbom_query_file before offering web continuation for richer interaction. Website links transfer only a workflow ID, never model data.
Nur Lesen
Idempotent
Eingabeschema
{'type': 'object', 'properties': {'format': {'enum': ['tflite', 'onnx', 'gguf', 'safetensors', 'coreml', 'executorch'], 'type': 'string', 'description': 'Optional known artifact format; filters applicable workflows, not per-file analysis coverage.'}, 'workflow': {'enum': ['all', 'audit', 'layers', 'findings', 'quantization', 'placement', 'fusion', 'visualization', 'weights', 'pruning', 'compare', 'redesign', 'exports', 'verify', 'provenance', 'activation', 'runtime', 'batch', 'integrations'], 'type': 'string', 'default': 'all'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['schema', 'catalog_version', 'status', 'format', 'workflows', 'boundary'], 'properties': {'format': {'type': ['string', 'null']}, 'schema': {'type': 'string'}, 'status': {'type': 'string'}, 'boundary': {'type': 'string'}, 'workflows': {'type': 'array', 'items': {'type': 'object'}}, 'catalog_version': {'type': 'string'}}, 'additionalProperties': False}
Verlauf
Letzte Tool-Änderungen
Hinzugefügt
deepbom_workflow_guide
1. October 2026 02:45
Hinzugefügt
deepbom_publish_query
1. October 2026 02:45
Hinzugefügt
deepbom_query_file
1. October 2026 02:45
Geändert
deepbom_publish_analysis
1. October 2026 02:45
Geändert
deepbom_publish_analysis
29. September 2026 02:52
Hinzugefügt
deepbom_publish_error
17. September 2026 12:42
Hinzugefügt
deepbom_publish_analysis
17. September 2026 12:42
Hinzugefügt
deepbom_capabilities
17. September 2026 12:42
Hinzugefügt
deepbom_analyze_file
17. September 2026 12:42
Entdecken
Ähnliche MCP-Server
kernelcad
com.kernelcad/kernelcad
Authors, evaluates, reviews, simulates, edits, and exports parametric CAD assemblies and geometry from editable TypeScript-based …
Affine.Earth Math Court
earth.affine/math-court
Performs exact integer and rational mathematical verification across algebra, geometry, physics, quantum-computing witnesses, rob…
RQM Studio Jobs
com.rqmtechnologies/studio
Provides bounded quantum-circuit parsing, validation, compilation, optimization, equivalence checks, repair, simulation, provider…
Bioregistry
io.github.pipeworx-io/bioregistry
Looks up biomedical identifier prefixes and metadata, including URI patterns, aliases, homepages, and cross-registry mappings.
RQM Jobs MCP
com.rqmtechnologies/jobs
Runs bounded robotics and control-system analyses such as trajectory validation, controller comparison, calibration assessment, c…
Mathjs
io.github.pipeworx-io/mathjs
Evaluates mathematical expressions and performs unit conversions through the Math.js API.
DOI Shape
io.github.sadri-dridi/doi-shape
Checks the structural format of a DOI.
Cords to cubic meters, number discarded
io.github.sadri-dridi/cord-m3
Provides cord-to-cubic-meter conversion along with small URL, parsing, time, weather, and validation utilities.