Footnote — 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": "footnote-mcp",
"source": {
"kind": "package",
"origin": "footnote-mcp"
},
"server": {
"name": "footnote-mcp"
}
},
"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": [
"ingests untrusted external content (a prompt-injection entry point)",
"reads sensitive or local data",
"has a read → egress path (a data-exfiltration surface)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"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 (45 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 (src/footnote_mcp/tools_data/sandbox.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/footnote_mcp/tools_data/sandbox.py:253`): 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/footnote_mcp/tools_data/sandbox.py"
},
"evidence": "safe_builtins} try: exec(compile(code, \"<recipe>\", \"exec\"), namespace) extract = namespace.get(\"extract\") if",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-001",
"file": "src/footnote_mcp/tools_data/sandbox.py",
"line": 253,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (src/footnote_mcp/tools_data/sandbox.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/footnote_mcp/tools_data/sandbox.py:253`): 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/footnote_mcp/tools_data/sandbox.py"
},
"evidence": "safe_builtins} try: exec(compile(code, \"<recipe>\", \"exec\"), namespace) extract = namespace.get(\"extract\") if",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/footnote_mcp/tools_data/sandbox.py",
"line": 253,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"web_read\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_read\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_read",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"web_extract_tables\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_extract_tables\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_extract_tables",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"web_parse_file\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_parse_file\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_parse_file",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"web_fetch_json\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_fetch_json\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_fetch_json",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"web_archive_fetch\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_archive_fetch\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_archive_fetch",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"web_fetch_authenticated\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_fetch_authenticated\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_fetch_authenticated",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"start_url\" on \"web_crawl\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"web_crawl\" takes a URL/host parameter \"start_url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "web_crawl",
"field": "inputSchema.properties.start_url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "start_url"
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (src/footnote_mcp/tools_data/health.py)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/footnote_mcp/tools_data/health.py:56`): 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": "src/footnote_mcp/tools_data/health.py"
},
"evidence": "try: __import__(module_name) checks[module_name] = {\"ok\": True} except Exception",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/footnote_mcp/tools_data/health.py",
"line": 56,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_scraper.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_scraper.py:109`): 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": "tests/test_scraper.py"
},
"evidence": "None res = scraper.fetch(\"https://x.com\", http_fn=http_fn) assert res[\"tier\"] == \"http\" assert res[\"blocked",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_scraper.py",
"line": 109,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint in packaging/dev tooling (tests/test_tools_extra.py)",
"category": "exfiltration",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_tools_extra.py:23`): 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": "tests/test_tools_extra.py"
},
"evidence": "tools_extra.web_archive_fetch(\"http://x.com\") assert result[\"archived\"] is True assert result[\"snapshot_url\"].s",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "tests/test_tools_extra.py",
"line": 23,
"nonRuntime": true
}
},
{
"ruleId": "MTC-CAP-008",
"title": "Unconstrained path parameter \"path\" on \"export_dataset\"",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "Tool \"export_dataset\" 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": "export_dataset",
"field": "inputSchema.properties.path"
},
"data": {
"param": "path"
}
},
{
"ruleId": "MTC-SUP-012",
"title": "Package has no license",
"category": "hygiene",
"severity": "info",
"confidence": "strong",
"description": "\"footnote-mcp\" has no declared license. This is a legal/reuse concern, not a security finding.",
"location": {
"kind": "package",
"name": "footnote-mcp"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "web_search",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"web_search\""
]
}
},
{
"tool": "web_deep_search",
"tags": [],
"reasons": {}
},
{
"tool": "web_read",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "web_extract_tables",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "web_detect_downloads",
"tags": [],
"reasons": {}
},
{
"tool": "web_parse_file",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"download\""
]
}
},
{
"tool": "web_fetch_json",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "check_date_completeness",
"tags": [],
"reasons": {}
},
{
"tool": "classify_source",
"tags": [],
"reasons": {}
},
{
"tool": "generate_search_queries",
"tags": [],
"reasons": {}
},
{
"tool": "resolve_units",
"tags": [],
"reasons": {}
},
{
"tool": "validate_unit_rows",
"tags": [],
"reasons": {}
},
{
"tool": "evidence_entailment",
"tags": [],
"reasons": {}
},
{
"tool": "tool_spec_propose",
"tags": [],
"reasons": {}
},
{
"tool": "tool_code_generate",
"tags": [],
"reasons": {}
},
{
"tool": "tool_code_validate",
"tags": [],
"reasons": {}
},
{
"tool": "tool_code_run_sandboxed",
"tags": [],
"reasons": {}
},
{
"tool": "tool_promote",
"tags": [],
"reasons": {}
},
{
"tool": "source_cache_get",
"tags": [],
"reasons": {}
},
{
"tool": "source_cache_put",
"tags": [],
"reasons": {}
},
{
"tool": "build_research_debug_report",
"tags": [],
"reasons": {}
},
{
"tool": "startup_health_check",
"tags": [],
"reasons": {}
},
{
"tool": "web_navigate",
"tags": [],
"reasons": {}
},
{
"tool": "web_snapshot",
"tags": [],
"reasons": {}
},
{
"tool": "web_click",
"tags": [],
"reasons": {}
},
{
"tool": "web_type",
"tags": [],
"reasons": {}
},
{
"tool": "web_extract",
"tags": [],
"reasons": {}
},
{
"tool": "web_scroll",
"tags": [],
"reasons": {}
},
{
"tool": "browser_extract_tables",
"tags": [],
"reasons": {}
},
{
"tool": "browser_set_date_range",
"tags": [],
"reasons": {}
},
{
"tool": "browser_extract_tables_for_date_range",
"tags": [],
"reasons": {}
},
{
"tool": "web_archive_fetch",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "papers_search",
"tags": [],
"reasons": {}
},
{
"tool": "encyclopedia_search",
"tags": [],
"reasons": {}
},
{
"tool": "github_search",
"tags": [],
"reasons": {}
},
{
"tool": "archive_search",
"tags": [],
"reasons": {}
},
{
"tool": "web_search_recent",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"web_search\""
]
}
},
{
"tool": "corroborate_claim",
"tags": [],
"reasons": {}
},
{
"tool": "locate_claim_span",
"tags": [],
"reasons": {}
},
{
"tool": "recipe_registry",
"tags": [],
"reasons": {}
},
{
"tool": "web_fetch_authenticated",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "web_crawl",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"crawl\""
]
}
},
{
"tool": "export_dataset",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"export_data\""
]
}
},
{
"tool": "reconcile_time_series",
"tags": [],
"reasons": {}
},
{
"tool": "web_screenshot",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "e0105517949dbfed17ae027d85e994bbcd0a5685d3c661641bbbbd6a1f1a2a97",
"stats": {
"tools": 45,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 2,
"medium": 8,
"low": 3,
"info": 1
}
}
}