Contextfs — 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": "contextfs",
"source": {
"kind": "package",
"origin": "contextfs"
},
"server": {
"name": "contextfs"
}
},
"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 (20 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 (src/contextfs/cli/index.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/cli/index.py:165`): 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/contextfs/cli/index.py"
},
"evidence": "ched subprocess subprocess.Popen( cmd, stdout=subprocess.DEVNULL, stderr=sub",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/cli/index.py",
"line": 165,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/cli/install.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/cli/install.py:80`): 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/contextfs/cli/install.py"
},
"evidence": "try: result = subprocess.run( [sys.executable, \"-m\", \"pip\", \"show\", \"contextfs\"], capt",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/cli/install.py",
"line": 80,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/cli/memory.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/cli/memory.py:814`): 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/contextfs/cli/memory.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"rev-parse\", \"--show-toplevel\"], capture_output=",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/cli/memory.py",
"line": 814,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/cli/server.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/cli/server.py:96`): 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/contextfs/cli/server.py"
},
"evidence": "] proc = subprocess.Popen( cmd, stdout=subprocess.DEVNULL, stderr=sub",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/cli/server.py",
"line": 96,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/cli/services/chroma.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/cli/services/chroma.py:38`): 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/contextfs/cli/services/chroma.py"
},
"evidence": "Linux) result = subprocess.run( [\"lsof\", \"-ti\", f\":{port}\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/cli/services/chroma.py",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/cli/services/mcp.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/cli/services/mcp.py:36`): 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/contextfs/cli/services/mcp.py"
},
"evidence": "try: result = subprocess.run( [\"lsof\", \"-ti\", f\":{port}\"], capture_output=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/cli/services/mcp.py",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/indexing/autoindex.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/indexing/autoindex.py:875`): 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/contextfs/indexing/autoindex.py"
},
"evidence": "y: result = subprocess.run( [\"git\", \"rev-parse\", \"HEAD\"], cwd=repo_path,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/indexing/autoindex.py",
"line": 875,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/contextfs/indexing/discovery.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/contextfs/indexing/discovery.py:331`): 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/contextfs/indexing/discovery.py"
},
"evidence": "try: result = subprocess.run( [\"git\", \"remote\", \"get-url\", \"origin\"], cwd=repo_path,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/contextfs/indexing/discovery.py",
"line": 331,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/generate_changelog.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/generate_changelog.py:73`): 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": "scripts/generate_changelog.py"
},
"evidence": "output.\"\"\" result = subprocess.run( [\"git\", *args], capture_output=True, text=True,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/generate_changelog.py",
"line": 73,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/install_claude_desktop.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/install_claude_desktop.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": "scripts/install_claude_desktop.py"
},
"evidence": "try: result = subprocess.run( [sys.executable, \"-m\", \"pip\", \"show\", \"-f\", \"contextfs\"],",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/install_claude_desktop.py",
"line": 51,
"nonRuntime": true
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "contextfs_save",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_get_type_schema",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_search",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_list_repos",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_list_tools",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_list_projects",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_recall",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_list",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_sessions",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_load_session",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_message",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_init",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_index",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_index_status",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_list_indexes",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_update",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_delete",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_evolve",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_link",
"tags": [],
"reasons": {}
},
{
"tool": "contextfs_sync",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "bfcaecf0422076633f08f1b0ae75dc60c16f82360335c1d27722be06cf3c61d0",
"stats": {
"tools": 20,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 8,
"medium": 0,
"low": 2,
"info": 0
}
}
}