Blatant Why — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "blatant-why",
"source": {
"kind": "package",
"origin": "blatant-why"
},
"server": {
"name": "blatant-why"
}
},
"grade": "B",
"score": {
"score": 83,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "client",
"term": "capability-exposure",
"level": "critical",
"label": "capability blast radius (critical) — client exposure if the model is manipulated",
"appliedPenalty": 10
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.9"
},
"capability": {
"level": "critical",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can send data / act on an external service",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code",
"untrusted-input, sensitive-source and egress co-exist across tools (toxic-flow surface)",
"untrusted input can reach code execution"
],
"tags": [
"untrusted-input",
"external-sink",
"sensitive-source",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (83 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-FLOW-002",
"title": "Completed toxic-flow trifecta across tools",
"category": "exfiltration",
"severity": "critical",
"confidence": "strong",
"description": "This server (without client built-ins) exposes a complete data-exfiltration chain: cloud_get_results → tamarind_list_files → tamarind_upload_file. Untrusted input is ingested, private data is read, and it can be sent to an external sink via the agent composing the tools (→). Static analysis proves the primitive exists, not that a specific run will occur.",
"remediation": "Remove one leg of the trifecta: isolate untrusted-input tools from secret-reading tools and from egress tools, or require human approval between them.",
"location": {
"kind": "flow",
"name": "cloud_get_results → tamarind_list_files → tamarind_upload_file"
},
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"references": [],
"data": {
"untrusted": [
"cloud_get_results",
"pdb_fetch_structure",
"pdb_download",
"uniprot_fetch_protein"
],
"sources": [
"tamarind_list_files"
],
"sinks": [
"tamarind_upload_file"
],
"path": [
"cloud_get_results",
"tamarind_list_files",
"tamarind_upload_file"
],
"edges": [
{
"from": "cloud_get_results",
"to": "tamarind_list_files",
"kind": "agent-mediated"
},
{
"from": "tamarind_list_files",
"to": "tamarind_upload_file",
"kind": "agent-mediated"
}
],
"wired": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/init.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/init.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/init.js"
},
"evidence": "{ execSync } from \"node:child_process\"; import { readFileSync, writeFileSync, existsSync, mkdirSync } from \"node:fs\"; im",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/init.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/templates.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/templates.js:3`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/templates.js"
},
"evidence": "{ execSync } from \"node:child_process\"; import { fileURLToPath } from \"node:url\"; /** * Resolve the templates/ director",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/templates.js",
"line": 3,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/verify.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/verify.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/verify.js"
},
"evidence": "{ execSync } from \"node:child_process\"; export function verifyMcpServers() { const failed = []; let passed = 0;",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/verify.js",
"line": 1,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (templates/.claude/mcp_servers/local_compute/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`templates/.claude/mcp_servers/local_compute/server.py:74`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "templates/.claude/mcp_servers/local_compute/server.py"
},
"evidence": "try: result = subprocess.run( [\"nvidia-smi\", \"--query-gpu=name\", \"--format=csv,noheader\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "templates/.claude/mcp_servers/local_compute/server.py",
"line": 74,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (dist/templates.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`dist/templates.js:170`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "dist/templates.js"
},
"evidence": "try { execSync(`claude mcp add -s project ${envFlags} \"${serverName}\" -- uv run --script \"${scriptPath",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "dist/templates.js",
"line": 170,
"nonRuntime": false
}
}
],
"toxicFlows": [
{
"id": "flow-1",
"severity": "critical",
"confidence": "strong",
"untrustedInput": [
"cloud_get_results",
"pdb_fetch_structure",
"pdb_download",
"uniprot_fetch_protein"
],
"sensitiveSource": [
"tamarind_list_files"
],
"externalSink": [
"tamarind_upload_file"
],
"selfContained": false,
"path": [
"cloud_get_results",
"tamarind_list_files",
"tamarind_upload_file"
],
"pathWired": false,
"description": "A cross-tool exfiltration chain exists: cloud_get_results → tamarind_list_files → tamarind_upload_file."
}
],
"capabilities": [
{
"tool": "adaptyv_estimate_cost",
"tags": [],
"reasons": {}
},
{
"tool": "adaptyv_prepare_submission",
"tags": [],
"reasons": {}
},
{
"tool": "adaptyv_confirm_submission",
"tags": [],
"reasons": {}
},
{
"tool": "adaptyv_get_experiment_status",
"tags": [],
"reasons": {}
},
{
"tool": "adaptyv_get_results",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_create",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_get",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_update_status",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_add_round",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_update_round",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_record_scores",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_get_summary",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_get_cost_estimate",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_export_fasta",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_export_csv",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_log_decision",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_get_decisions",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_generate_visualization",
"tags": [],
"reasons": {}
},
{
"tool": "campaign_suggest_next_round",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_list_providers",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_estimate_cost",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_submit_job",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_submit_batch",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_get_status",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_get_batch_status",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_wait_batch",
"tags": [],
"reasons": {}
},
{
"tool": "cloud_get_results",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "knowledge_store_campaign",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_query_similar",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_scaffold_rankings",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_store_failure",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_get_recommendations",
"tags": [],
"reasons": {}
},
{
"tool": "knowledge_consolidate",
"tags": [],
"reasons": {}
},
{
"tool": "local_detect_tools",
"tags": [],
"reasons": {}
},
{
"tool": "local_detect_gpu",
"tags": [],
"reasons": {}
},
{
"tool": "local_run_boltzgen",
"tags": [],
"reasons": {}
},
{
"tool": "local_run_pxdesign",
"tags": [],
"reasons": {}
},
{
"tool": "local_run_protenix",
"tags": [],
"reasons": {}
},
{
"tool": "ssh_detect_tools_remote",
"tags": [],
"reasons": {}
},
{
"tool": "ssh_detect_gpu_remote",
"tags": [],
"reasons": {}
},
{
"tool": "ssh_run_job",
"tags": [],
"reasons": {}
},
{
"tool": "pdb_search",
"tags": [],
"reasons": {}
},
{
"tool": "pdb_fetch_structure",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "pdb_get_chains",
"tags": [],
"reasons": {}
},
{
"tool": "pdb_interface_residues",
"tags": [],
"reasons": {}
},
{
"tool": "pdb_download",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "research_search_prior_art",
"tags": [],
"reasons": {}
},
{
"tool": "research_get_target_info",
"tags": [],
"reasons": {}
},
{
"tool": "research_analyze_known_binders",
"tags": [],
"reasons": {}
},
{
"tool": "research_find_similar_targets",
"tags": [],
"reasons": {}
},
{
"tool": "research_check_novelty",
"tags": [],
"reasons": {}
},
{
"tool": "sabdab_search_antibodies",
"tags": [],
"reasons": {}
},
{
"tool": "sabdab_get_structure",
"tags": [],
"reasons": {}
},
{
"tool": "sabdab_cdr_sequences",
"tags": [],
"reasons": {}
},
{
"tool": "sabdab_search_by_antigen",
"tags": [],
"reasons": {}
},
{
"tool": "screen_liabilities",
"tags": [],
"reasons": {}
},
{
"tool": "screen_developability",
"tags": [],
"reasons": {}
},
{
"tool": "screen_net_charge",
"tags": [],
"reasons": {}
},
{
"tool": "score_ipsae",
"tags": [],
"reasons": {}
},
{
"tool": "score_ipsae_multi_seed",
"tags": [],
"reasons": {}
},
{
"tool": "screen_composite",
"tags": [],
"reasons": {}
},
{
"tool": "interpret_scores",
"tags": [],
"reasons": {}
},
{
"tool": "screen_diversity",
"tags": [],
"reasons": {}
},
{
"tool": "screen_diagnose_failures",
"tags": [],
"reasons": {}
},
{
"tool": "screen_pareto_front",
"tags": [],
"reasons": {}
},
{
"tool": "screen_align_sequences",
"tags": [],
"reasons": {}
},
{
"tool": "screen_cross_validate",
"tags": [],
"reasons": {}
},
{
"tool": "screen_shape_complementarity",
"tags": [],
"reasons": {}
},
{
"tool": "screen_naturalness",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_list_tools",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_upload_file",
"tags": [
"external-sink"
],
"reasons": {
"external-sink": [
"keyword \"upload_file\""
]
}
},
{
"tool": "tamarind_list_files",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "tamarind_submit_job",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_submit_batch",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_list_jobs",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_get_job",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_wait_for_job",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_screen_developability",
"tags": [],
"reasons": {}
},
{
"tool": "tamarind_screen_naturalness",
"tags": [],
"reasons": {}
},
{
"tool": "uniprot_search",
"tags": [],
"reasons": {}
},
{
"tool": "uniprot_fetch_protein",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "uniprot_get_domains",
"tags": [],
"reasons": {}
},
{
"tool": "uniprot_get_variants",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "7ef32f0933672ddbfbf3a3e5b40d3824af10b08573a1dd1c8491b9606f542f78",
"stats": {
"tools": 83,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 1,
"high": 4,
"medium": 1,
"low": 0,
"info": 0
}
}
}