Coder — the complete, unedited output of the deterministic mcptrustchecker engine v1.5.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.5.0",
"methodologyVersion": "mcptrustchecker-1.4"
},
"target": {
"id": "coder-mcp",
"source": {
"kind": "package",
"origin": "coder-mcp"
},
"server": {
"name": "coder-mcp"
}
},
"grade": "B",
"score": {
"score": 88,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 11.66,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.25,
"appliedPenalty": 1.58
},
{
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.1,
"appliedPenalty": 0.63
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "high",
"reasons": [
"can execute shell commands or code"
],
"tags": [
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": false,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (coder_mcp/analysis/visitors/python_visitor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/analysis/visitors/python_visitor.py:227`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. 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": "coder_mcp/analysis/visitors/python_visitor.py"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "coder_mcp/analysis/visitors/python_visitor.py",
"line": 227
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (coder_mcp/analysis/dependency_analyzer.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/analysis/dependency_analyzer.py:630`): 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": "coder_mcp/analysis/dependency_analyzer.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/dependency_analyzer.py",
"line": 630
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (coder_mcp/analysis/detectors/security/injection.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/analysis/detectors/security/injection.py:87`): 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": "coder_mcp/analysis/detectors/security/injection.py"
},
"evidence": "shell=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/detectors/security/injection.py",
"line": 87
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (coder_mcp/analysis/metrics/coverage_reader.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/analysis/metrics/coverage_reader.py:110`): 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": "coder_mcp/analysis/metrics/coverage_reader.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/metrics/coverage_reader.py",
"line": 110
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (coder_mcp/analysis/visitors/python_visitor.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/analysis/visitors/python_visitor.py:240`): 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": "coder_mcp/analysis/visitors/python_visitor.py"
},
"evidence": "exec(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/visitors/python_visitor.py",
"line": 240
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (coder_mcp/core/providers/registry.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`coder_mcp/core/providers/registry.py:244`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. 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": "coder_mcp/core/providers/registry.py"
},
"evidence": "__import__(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "coder_mcp/core/providers/registry.py",
"line": 244
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (coder_mcp/analysis/detectors/security/insecure_functions.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/analysis/detectors/security/insecure_functions.py:118`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "coder_mcp/analysis/detectors/security/insecure_functions.py"
},
"evidence": "yaml.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "coder_mcp/analysis/detectors/security/insecure_functions.py",
"line": 118
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (coder_mcp/context/search/cache.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/context/search/cache.py:96`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "coder_mcp/context/search/cache.py"
},
"evidence": "pickle.loads(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "coder_mcp/context/search/cache.py",
"line": 96
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (coder_mcp/search/cache.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/search/cache.py:33`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "coder_mcp/search/cache.py"
},
"evidence": "pickle.loads(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "coder_mcp/search/cache.py",
"line": 33
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (coder_mcp/storage/vector_stores/hnsw_store.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`coder_mcp/storage/vector_stores/hnsw_store.py:405`): Deserializing untrusted data with these APIs can execute arbitrary code (a well-known RCE gadget class). 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": "coder_mcp/storage/vector_stores/hnsw_store.py"
},
"evidence": "pickle.load(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "coder_mcp/storage/vector_stores/hnsw_store.py",
"line": 405
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "5ebfd57cc5f64dd6c057ca056bc5e6cac188bb2047ba33701420edb2bf308a39",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 5,
"low": 0,
"info": 0
}
}
}