Coder — 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": "coder-mcp",
"source": {
"kind": "package",
"origin": "coder-mcp"
},
"server": {
"name": "coder-mcp"
}
},
"grade": "B",
"score": {
"score": 84,
"threatScore": 91,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 9.45,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"kind": "threat",
"ruleId": "MTC-SRC-007",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 0.5,
"appliedPenalty": 3.15
},
{
"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 create, modify or delete files",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"file-write",
"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 (30 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-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": "\"Usage of eval() function detected\", \"Avoid eval() - use safer alternatives like ast.l",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "coder_mcp/analysis/visitors/python_visitor.py",
"line": 227,
"nonRuntime": false
}
},
{
"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": "on\"] proc = subprocess.run(cmd, capture_output=True, text=True, timeout=30) if proc.returncode",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/dependency_analyzer.py",
"line": 630,
"nonRuntime": false
}
},
{
"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": "ized commands, \" \"avoid shell=True\" ), ) def _create_path_traversal_pattern(self) -> Vulnerabil",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/detectors/security/injection.py",
"line": 87,
"nonRuntime": false
}
},
{
"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": "ty result = subprocess.run( # nosec B603 [pytest_path, \"--cov=coder_mcp\", \"--cov-report=jso",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/metrics/coverage_reader.py",
"line": 110,
"nonRuntime": false
}
},
{
"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": "\"Usage of exec() function detected\", \"Avoid exec() - use safer alternatives\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "coder_mcp/analysis/visitors/python_visitor.py",
"line": 240,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"edit_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"edit_file\" can write, overwrite or delete files (keyword \"edit_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "edit_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-002",
"title": "Tool \"write_file\" can modify the filesystem",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "Tool \"write_file\" can write, overwrite or delete files (keyword \"write_file\" in tool name). Verify it is scoped to a safe directory.",
"remediation": "Constrain file operations to an explicit, non-sensitive root; reject path traversal.",
"location": {
"kind": "tool",
"name": "write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"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": "ry: __import__(requirement) except ImportError: self._add_missin",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "coder_mcp/core/providers/registry.py",
"line": 244,
"nonRuntime": false
}
},
{
"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": "cached_result = pickle.loads(cached_data) # nosec B301 if isinstance(cached_result, list) a",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "coder_mcp/context/search/cache.py",
"line": 96,
"nonRuntime": false
}
},
{
"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": "mbedding: List[float] = pickle.loads(cached) # nosec B301 self.embedding_cache.set(cache_key, embedding)",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "coder_mcp/search/cache.py",
"line": 33,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"edit_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"edit_file\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "edit_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-005",
"title": "Mutating tool \"write_file\" declares no destructiveHint",
"category": "hygiene",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"write_file\" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.",
"remediation": "Declare accurate annotations, and gate destructive tools on user confirmation regardless.",
"location": {
"kind": "tool",
"name": "write_file"
},
"data": {
"tags": [
"file-write"
]
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"read_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"read_file\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "read_file",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"write_file\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"write_file\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "write_file",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"list_files\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"list_files\" takes a path parameter \"path\" with no constraint. Without a canonicalize-and-contain check (not visible statically), this permits ../ traversal outside the intended root.",
"remediation": "Resolve and verify the path stays within an allowed root; reject traversal sequences.",
"location": {
"kind": "tool",
"name": "list_files",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "analyze_code",
"tags": [],
"reasons": {}
},
{
"tool": "smart_analyze",
"tags": [],
"reasons": {}
},
{
"tool": "detect_code_smells",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_dependencies",
"tags": [],
"reasons": {}
},
{
"tool": "get_related_files",
"tags": [],
"reasons": {}
},
{
"tool": "initialize_context",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_project",
"tags": [],
"reasons": {}
},
{
"tool": "update_context",
"tags": [],
"reasons": {}
},
{
"tool": "add_note",
"tags": [],
"reasons": {}
},
{
"tool": "search_context",
"tags": [],
"reasons": {}
},
{
"tool": "edit_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"edit_file\" in tool name"
]
}
},
{
"tool": "smart_edit",
"tags": [],
"reasons": {}
},
{
"tool": "start_edit_session",
"tags": [],
"reasons": {}
},
{
"tool": "session_apply_edit",
"tags": [],
"reasons": {}
},
{
"tool": "session_undo",
"tags": [],
"reasons": {}
},
{
"tool": "session_redo",
"tags": [],
"reasons": {}
},
{
"tool": "get_edit_suggestions",
"tags": [],
"reasons": {}
},
{
"tool": "preview_edit",
"tags": [],
"reasons": {}
},
{
"tool": "list_edit_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "close_edit_session",
"tags": [],
"reasons": {}
},
{
"tool": "read_file",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"read_file\""
]
}
},
{
"tool": "write_file",
"tags": [
"file-write"
],
"reasons": {
"file-write": [
"keyword \"write_file\" in tool name"
]
}
},
{
"tool": "list_files",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"list_files\""
]
}
},
{
"tool": "search_files",
"tags": [],
"reasons": {}
},
{
"tool": "health_check",
"tags": [],
"reasons": {}
},
{
"tool": "get_metrics",
"tags": [],
"reasons": {}
},
{
"tool": "advanced_search",
"tags": [],
"reasons": {}
},
{
"tool": "scaffold_feature",
"tags": [],
"reasons": {}
},
{
"tool": "apply_best_practices",
"tags": [],
"reasons": {}
},
{
"tool": "generate_improvement_roadmap",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "30ffef54c11de280081204b6aaf2fdcd099a25994ce4fee5b0cda755e73277b9",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 5,
"medium": 5,
"low": 5,
"info": 0
}
}
}