Msfeldstein Test Servers — 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": "@msfeldstein/mcp-test-servers",
"source": {
"kind": "package",
"origin": "@msfeldstein/mcp-test-servers"
},
"server": {
"name": "@msfeldstein/mcp-test-servers"
}
},
"grade": "A",
"score": {
"score": 92,
"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": "none",
"label": "publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read",
"appliedPenalty": 2
},
{
"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": [
"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"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (67 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/shell-exec-server.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`src/shell-exec-server.js:5`): 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/shell-exec-server.js"
},
"evidence": "t { exec, spawn } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); const ser",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "src/shell-exec-server.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (src/cli.js)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`src/cli.js:34`): 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/cli.js"
},
"evidence": "cute the Node.js server import(serverConfig.file);",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "src/cli.js",
"line": 34,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/oauth-debug-setup.js)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/oauth-debug-setup.js:3`): 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/oauth-debug-setup.js"
},
"evidence": "import { spawn } from 'child_process'; import { readFileSync } from 'fs'; import { join, dirname } from 'path'; import",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/oauth-debug-setup.js",
"line": 3,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-011",
"title": "Package declares no source repository",
"category": "supply-chain",
"severity": "info",
"confidence": "strong",
"description": "\"@msfeldstein/mcp-test-servers\" declares no repository URL, so its published artifact cannot be compared against reviewable source.",
"remediation": "Prefer packages that link to public, reviewable source.",
"location": {
"kind": "package",
"name": "@msfeldstein/mcp-test-servers"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "all_types_tool",
"tags": [],
"reasons": {}
},
{
"tool": "get-headers",
"tags": [],
"reasons": {}
},
{
"tool": "ping",
"tags": [],
"reasons": {}
},
{
"tool": "bad-param",
"tags": [],
"reasons": {}
},
{
"tool": "generate_big_response",
"tags": [],
"reasons": {}
},
{
"tool": "crash",
"tags": [],
"reasons": {}
},
{
"tool": "fizzbuzz",
"tags": [],
"reasons": {}
},
{
"tool": "delayedPing",
"tags": [],
"reasons": {}
},
{
"tool": "analyze_text",
"tags": [],
"reasons": {}
},
{
"tool": "format_data",
"tags": [],
"reasons": {}
},
{
"tool": "optionalTool",
"tags": [],
"reasons": {}
},
{
"tool": "toggleTool",
"tags": [],
"reasons": {}
},
{
"tool": "ask-name",
"tags": [],
"reasons": {}
},
{
"tool": "multi-step-elicitation",
"tags": [],
"reasons": {}
},
{
"tool": "ask-favorite-color",
"tags": [],
"reasons": {}
},
{
"tool": "ask-programming-language",
"tags": [],
"reasons": {}
},
{
"tool": "delete-project",
"tags": [],
"reasons": {}
},
{
"tool": "search_documentation",
"tags": [],
"reasons": {}
},
{
"tool": "status",
"tags": [],
"reasons": {}
},
{
"tool": "env_echo",
"tags": [],
"reasons": {}
},
{
"tool": "echo_with_params",
"tags": [],
"reasons": {}
},
{
"tool": "simple_ping",
"tags": [],
"reasons": {}
},
{
"tool": "get_mixed_resources",
"tags": [],
"reasons": {}
},
{
"tool": "test_all_elicitations",
"tags": [],
"reasons": {}
},
{
"tool": "dynamic_feature",
"tags": [],
"reasons": {}
},
{
"tool": "toggle_dynamic_tool",
"tags": [],
"reasons": {}
},
{
"tool": "echo_mcp_roots",
"tags": [],
"reasons": {}
},
{
"tool": "echo_env_var",
"tags": [],
"reasons": {}
},
{
"tool": "long_running_progress",
"tags": [],
"reasons": {}
},
{
"tool": "execute-sql",
"tags": [
"sensitive-source"
],
"reasons": {
"sensitive-source": [
"keyword \"execute_sql\""
]
}
},
{
"tool": "safe_header_info",
"tags": [],
"reasons": {}
},
{
"tool": "generate_image",
"tags": [],
"reasons": {}
},
{
"tool": "makeRequest",
"tags": [],
"reasons": {}
},
{
"tool": "test-simple-integer",
"tags": [],
"reasons": {}
},
{
"tool": "test-anyof-integer",
"tags": [],
"reasons": {}
},
{
"tool": "test-both-params",
"tags": [],
"reasons": {}
},
{
"tool": "get-info",
"tags": [],
"reasons": {}
},
{
"tool": "long-running-task",
"tags": [],
"reasons": {}
},
{
"tool": "long-running-task-with-no-total",
"tags": [],
"reasons": {}
},
{
"tool": "long-running-task-with-message",
"tags": [],
"reasons": {}
},
{
"tool": "many-resources-tool",
"tags": [],
"reasons": {}
},
{
"tool": "add",
"tags": [],
"reasons": {}
},
{
"tool": "subtract",
"tags": [],
"reasons": {}
},
{
"tool": "multiply",
"tags": [],
"reasons": {}
},
{
"tool": "divide",
"tags": [],
"reasons": {}
},
{
"tool": "power",
"tags": [],
"reasons": {}
},
{
"tool": "sqrt",
"tags": [],
"reasons": {}
},
{
"tool": "factorial",
"tags": [],
"reasons": {}
},
{
"tool": "missing-type-tool",
"tags": [],
"reasons": {}
},
{
"tool": "another-missing-type",
"tags": [],
"reasons": {}
},
{
"tool": "number-param",
"tags": [],
"reasons": {}
},
{
"tool": "bug-status",
"tags": [],
"reasons": {}
},
{
"tool": "debug-oauth",
"tags": [],
"reasons": {}
},
{
"tool": "test-edge-cases",
"tags": [],
"reasons": {}
},
{
"tool": "whoami",
"tags": [],
"reasons": {}
},
{
"tool": "token-info",
"tags": [],
"reasons": {}
},
{
"tool": "echo",
"tags": [],
"reasons": {}
},
{
"tool": "parse_bugsnag_error_url",
"tags": [],
"reasons": {}
},
{
"tool": "long-running-ping",
"tags": [],
"reasons": {}
},
{
"tool": "get-resource-list",
"tags": [],
"reasons": {}
},
{
"tool": "root-echo",
"tags": [],
"reasons": {}
},
{
"tool": "get-session-info",
"tags": [],
"reasons": {}
},
{
"tool": "terminate-session",
"tags": [],
"reasons": {}
},
{
"tool": "start-notification-stream",
"tags": [],
"reasons": {}
},
{
"tool": "log-to-stderr",
"tags": [],
"reasons": {}
},
{
"tool": "echo_structured",
"tags": [],
"reasons": {}
},
{
"tool": "get-time",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "9b3c37dcb38793d85537c6197afcd6a80f15ed1a4b6aff290c074cc9401badcc",
"stats": {
"tools": 67,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 1,
"medium": 1,
"low": 1,
"info": 1
}
}
}