Coaia Sequential Thinking — the complete, unedited output of the deterministic mcptrustchecker engine v1.13.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.13.0",
"methodologyVersion": "mcptrustchecker-1.13"
},
"target": {
"id": "mcp-coaia-sequential-thinking",
"source": {
"kind": "package",
"origin": "mcp-coaia-sequential-thinking"
},
"server": {
"name": "mcp-coaia-sequential-thinking"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"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-1.13"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (38 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-SRC-002",
"title": "Shell/command execution in server code (debug_mcp_connection.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`debug_mcp_connection.py:11`): 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": "debug_mcp_connection.py"
},
"evidence": "r process process = subprocess.Popen( [sys.executable, \"-u\", server_path], # -u for unbuffered output",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "debug_mcp_connection.py",
"line": 11,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (llms/sync_llms_ordered.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`llms/sync_llms_ordered.py:26`): 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": "llms/sync_llms_ordered.py"
},
"evidence": ". \"\"\" process = subprocess.run( [\"python3\", os.path.join(LLMS_DIR, \"transform_llms_content.py\")],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "llms/sync_llms_ordered.py",
"line": 26,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (mcp_coaia_sequential_thinking/wrapper.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`mcp_coaia_sequential_thinking/wrapper.py:28`): 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": "mcp_coaia_sequential_thinking/wrapper.py"
},
"evidence": "args try: subprocess.run(command, check=True) except subprocess.CalledProcessError as e: print",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "mcp_coaia_sequential_thinking/wrapper.py",
"line": 28,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (test_creative_orientation.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`test_creative_orientation.py:83`): 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": "test_creative_orientation.py"
},
"evidence": "result = subprocess.run(cmd, capture_output=True, text=True, cwd=\".\") if result.",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "test_creative_orientation.py",
"line": 83,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "process_thought",
"tags": [],
"reasons": {}
},
{
"tool": "generate_summary",
"tags": [],
"reasons": {}
},
{
"tool": "clear_history",
"tags": [],
"reasons": {}
},
{
"tool": "export_session",
"tags": [],
"reasons": {}
},
{
"tool": "import_session",
"tags": [],
"reasons": {}
},
{
"tool": "check_integration_status",
"tags": [],
"reasons": {}
},
{
"tool": "validate_thought_content",
"tags": [],
"reasons": {}
},
{
"tool": "validate_constitutional_compliance",
"tags": [],
"reasons": {}
},
{
"tool": "generate_active_pause_drafts",
"tags": [],
"reasons": {}
},
{
"tool": "make_constitutional_decision",
"tags": [],
"reasons": {}
},
{
"tool": "get_constitutional_audit_trail",
"tags": [],
"reasons": {}
},
{
"tool": "list_constitutional_principles",
"tags": [],
"reasons": {}
},
{
"tool": "initialize_polycentric_lattice",
"tags": [],
"reasons": {}
},
{
"tool": "submit_agent_task",
"tags": [],
"reasons": {}
},
{
"tool": "get_lattice_status",
"tags": [],
"reasons": {}
},
{
"tool": "query_agent_capabilities",
"tags": [],
"reasons": {}
},
{
"tool": "get_task_status",
"tags": [],
"reasons": {}
},
{
"tool": "create_agent_collaboration",
"tags": [],
"reasons": {}
},
{
"tool": "establish_system_goal",
"tags": [],
"reasons": {}
},
{
"tool": "conduct_novelty_search",
"tags": [],
"reasons": {}
},
{
"tool": "evaluate_resilient_connection",
"tags": [],
"reasons": {}
},
{
"tool": "integrate_emergent_possibility",
"tags": [],
"reasons": {}
},
{
"tool": "discover_emergent_opportunities",
"tags": [],
"reasons": {}
},
{
"tool": "adjust_exploration_balance",
"tags": [],
"reasons": {}
},
{
"tool": "get_goal_progress",
"tags": [],
"reasons": {}
},
{
"tool": "initiate_creative_emergence",
"tags": [],
"reasons": {}
},
{
"tool": "advance_creative_emergence",
"tags": [],
"reasons": {}
},
{
"tool": "synthesize_thinking_chain",
"tags": [],
"reasons": {}
},
{
"tool": "create_consensus_decision",
"tags": [],
"reasons": {}
},
{
"tool": "get_consensus_decision_status",
"tags": [],
"reasons": {}
},
{
"tool": "request_human_consultation",
"tags": [],
"reasons": {}
},
{
"tool": "provide_human_response",
"tags": [],
"reasons": {}
},
{
"tool": "get_thinking_chain_status",
"tags": [],
"reasons": {}
},
{
"tool": "get_active_thinking_chains",
"tags": [],
"reasons": {}
},
{
"tool": "initiate_sequential_thinking",
"tags": [],
"reasons": {}
},
{
"tool": "advance_thinking_chain",
"tags": [],
"reasons": {}
},
{
"tool": "run_full_analysis_chain",
"tags": [],
"reasons": {}
},
{
"tool": "check_agent_creative_orientation",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "29f35886ea64c22644506433c4f080dc4ce989ade4061b2553873d6da7d30159",
"stats": {
"tools": 38,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 4,
"medium": 0,
"low": 0,
"info": 0
}
}
}