Neuromcp — 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": "neuromcp",
"source": {
"kind": "package",
"origin": "neuromcp"
},
"server": {
"name": "neuromcp"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 99,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 1.2,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SUP-010",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"rawWeight": 3,
"confidenceMult": 0.4,
"diminishingFactor": 1,
"appliedPenalty": 1.2
},
{
"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": "source",
"label": "publisher verification (provenance) — cryptographic build provenance ties the artifact to its source",
"appliedPenalty": 0
},
{
"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 (46 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 (bin/doctor.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/doctor.mjs:21`): 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": "bin/doctor.mjs"
},
"evidence": "rt { spawn } from 'node:child_process'; import { readFileSync, writeFileSync, existsSync } from 'node:fs'; import { crea",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/doctor.mjs",
"line": 21,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/enable-consolidation.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/enable-consolidation.mjs:25`): 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": "bin/enable-consolidation.mjs"
},
"evidence": "ecFileSync } from 'node:child_process'; import { fileURLToPath } from 'node:url'; const __dirname = dirname(fileURLToPa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/enable-consolidation.mjs",
"line": 25,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/enable-daemon.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/enable-daemon.mjs: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": "bin/enable-daemon.mjs"
},
"evidence": "ecFileSync } from 'node:child_process'; import { fileURLToPath } from 'node:url'; import { resolveStableNodeBin } from '",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/enable-daemon.mjs",
"line": 38,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/enable-zombie-cleanup.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/enable-zombie-cleanup.mjs: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": "bin/enable-zombie-cleanup.mjs"
},
"evidence": "ecFileSync } from 'node:child_process'; import { fileURLToPath } from 'node:url'; const __dirname = dirname(fileURLToPa",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/enable-zombie-cleanup.mjs",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/init-wiki.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/init-wiki.mjs:22`): 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": "bin/init-wiki.mjs"
},
"evidence": "ecFileSync } from 'node:child_process'; import { fileURLToPath } from 'node:url'; import { seedObsidianVault } from './o",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/init-wiki.mjs",
"line": 22,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/init.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/init.mjs:41`): 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": "bin/init.mjs"
},
"evidence": "ecFileSync } from 'node:child_process'; import { fileURLToPath, pathToFileURL } from 'node:url'; const __dirname = dirn",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/init.mjs",
"line": 41,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (bin/neuromcp-connect.mjs)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`bin/neuromcp-connect.mjs:31`): 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": "bin/neuromcp-connect.mjs"
},
"evidence": ", execFile } from 'node:child_process'; import { platform } from 'node:os'; import { pathToFileURL } from 'node:url'; c",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "bin/neuromcp-connect.mjs",
"line": 31,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (dist/chunk-IAJG7PHQ.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`dist/chunk-IAJG7PHQ.js:35`): 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": "dist/chunk-IAJG7PHQ.js"
},
"evidence": "import { spawn } from \"child_process\"; async function extractEntitiesViaLLM(content, options = {}) { const { timeoutM",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "dist/chunk-IAJG7PHQ.js",
"line": 35,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (templates/hooks/neuromcp-auto-capture.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`templates/hooks/neuromcp-auto-capture.js:20`): 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": "templates/hooks/neuromcp-auto-capture.js"
},
"evidence": "ecFileSync } = require('child_process'); const HOME = process.env.HOME || process.env.USERPROFILE || '/tmp'; const DB_P",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "templates/hooks/neuromcp-auto-capture.js",
"line": 20,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-005",
"title": "Dynamic module load from a non-literal (bin/query.mjs)",
"category": "permissions",
"severity": "medium",
"confidence": "heuristic",
"description": "In the server's implementation (`bin/query.mjs:88`): 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": "bin/query.mjs"
},
"evidence": "ait Promise.all([ import(distPath), import(join(__dirname, '..', 'dist', 'config.js')), import(join(__",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-005",
"file": "bin/query.mjs",
"line": 88,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in packaging/dev tooling (scripts/consolidate-sessions.py)",
"category": "permissions",
"severity": "low",
"confidence": "heuristic",
"description": "In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/consolidate-sessions.py:208`): 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/consolidate-sessions.py"
},
"evidence": "\"\" try: r = subprocess.run( [\"claude\", \"-p\", \"--no-session-persistence\", \"--model\",",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "scripts/consolidate-sessions.py",
"line": 208,
"nonRuntime": true
}
},
{
"ruleId": "MTC-SUP-010",
"title": "Package runs install-time scripts (postinstall)",
"category": "supply-chain",
"severity": "low",
"confidence": "heuristic",
"description": "\"neuromcp\" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.",
"remediation": "Review the scripts; install with --ignore-scripts where possible and vet what they do.",
"location": {
"kind": "package",
"name": "neuromcp"
},
"evidence": "node scripts/download-model.mjs || true",
"owasp": "LLM03:2025 Supply Chain",
"references": [
"https://github.com/ossf/package-analysis",
"https://owasp.org/www-project-top-10-ci-cd-security-risks/"
],
"data": {
"scripts": [
"postinstall"
]
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "store_memory",
"tags": [],
"reasons": {}
},
{
"tool": "search_memory",
"tags": [],
"reasons": {}
},
{
"tool": "recall_answer",
"tags": [],
"reasons": {}
},
{
"tool": "recall_memory",
"tags": [],
"reasons": {}
},
{
"tool": "forget_memory",
"tags": [],
"reasons": {}
},
{
"tool": "consolidate",
"tags": [],
"reasons": {}
},
{
"tool": "memory_stats",
"tags": [],
"reasons": {}
},
{
"tool": "export_memories",
"tags": [],
"reasons": {}
},
{
"tool": "import_memories",
"tags": [],
"reasons": {}
},
{
"tool": "backfill_embeddings",
"tags": [],
"reasons": {}
},
{
"tool": "search_all",
"tags": [],
"reasons": {}
},
{
"tool": "create_entity",
"tags": [],
"reasons": {}
},
{
"tool": "create_relation",
"tags": [],
"reasons": {}
},
{
"tool": "query_graph",
"tags": [],
"reasons": {}
},
{
"tool": "search_claims",
"tags": [],
"reasons": {}
},
{
"tool": "compute_centrality",
"tags": [],
"reasons": {}
},
{
"tool": "update_importance",
"tags": [],
"reasons": {}
},
{
"tool": "start_episode",
"tags": [],
"reasons": {}
},
{
"tool": "end_episode",
"tags": [],
"reasons": {}
},
{
"tool": "list_episodes",
"tags": [],
"reasons": {}
},
{
"tool": "get_episode",
"tags": [],
"reasons": {}
},
{
"tool": "cluster_memories",
"tags": [],
"reasons": {}
},
{
"tool": "list_clusters",
"tags": [],
"reasons": {}
},
{
"tool": "get_cluster_memories",
"tags": [],
"reasons": {}
},
{
"tool": "summarize_cluster",
"tags": [],
"reasons": {}
},
{
"tool": "summarize_episode",
"tags": [],
"reasons": {}
},
{
"tool": "memory_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "register_agent",
"tags": [],
"reasons": {}
},
{
"tool": "find_expert",
"tags": [],
"reasons": {}
},
{
"tool": "agent_conflicts",
"tags": [],
"reasons": {}
},
{
"tool": "review_queue",
"tags": [],
"reasons": {}
},
{
"tool": "review_memory",
"tags": [],
"reasons": {}
},
{
"tool": "init_reviews",
"tags": [],
"reasons": {}
},
{
"tool": "compress_memories",
"tags": [],
"reasons": {}
},
{
"tool": "find_transferable",
"tags": [],
"reasons": {}
},
{
"tool": "transfer_memories",
"tags": [],
"reasons": {}
},
{
"tool": "store_verbatim",
"tags": [],
"reasons": {}
},
{
"tool": "search_verbatim",
"tags": [],
"reasons": {}
},
{
"tool": "verbatim_stats",
"tags": [],
"reasons": {}
},
{
"tool": "log_retrieval",
"tags": [],
"reasons": {}
},
{
"tool": "cite_memories",
"tags": [],
"reasons": {}
},
{
"tool": "usefulness_stats",
"tags": [],
"reasons": {}
},
{
"tool": "generate_reflection",
"tags": [],
"reasons": {}
},
{
"tool": "wiki_ingest",
"tags": [],
"reasons": {}
},
{
"tool": "wiki_lint",
"tags": [],
"reasons": {}
},
{
"tool": "wiki_briefing",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "49ea1d6c23a5f1fe94427aa88357b4fca0375f3ec884df8b379a49011cf59b89",
"stats": {
"tools": 46,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 9,
"medium": 1,
"low": 2,
"info": 0
}
}
}