For Microsoft Fabric Analytics — 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": "mcp-for-microsoft-fabric-analytics",
"source": {
"kind": "package",
"origin": "mcp-for-microsoft-fabric-analytics"
},
"server": {
"name": "mcp-for-microsoft-fabric-analytics"
}
},
"grade": "B",
"score": {
"score": 87,
"threatScore": 94,
"grade": "B",
"band": "B",
"categorySubtotals": {
"injection": 6.3,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "threat",
"ruleId": "MTC-SRC-009",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"rawWeight": 9,
"confidenceMult": 0.7,
"diminishingFactor": 1,
"appliedPenalty": 6.3
},
{
"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 send data / act on an external service",
"can execute shell commands or code"
],
"tags": [
"code-exec",
"external-sink"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (78 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 (build/auth-client.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/auth-client.js:4`): 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": "build/auth-client.js"
},
"evidence": "; import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); export var",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/auth-client.js",
"line": 4,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/index.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/index.js:920`): 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": "build/index.js"
},
"evidence": "{ execSync } = require('child_process'); const command = 'az account get-access-token --resource \"https://ap",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/index.js",
"line": 920,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/migration/capacity-tools.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/migration/capacity-tools.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": "build/migration/capacity-tools.js"
},
"evidence": "port { execSync } from 'child_process'; // Capacity SKU specifications based on Microsoft documentation const CAPACITY_S",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/migration/capacity-tools.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/migration/fabric-provisioner.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/migration/fabric-provisioner.js:24`): 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": "build/migration/fabric-provisioner.js"
},
"evidence": "exec } = await import('child_process'); const { promisify } = await import('util'); const execA",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/migration/fabric-provisioner.js",
"line": 24,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/migration/orchestrator.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/migration/orchestrator.js:10`): 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": "build/migration/orchestrator.js"
},
"evidence": "port { execSync } from 'child_process'; export class MigrationOrchestrator { /** * Fetch Fabric pricing from Az",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/migration/orchestrator.js",
"line": 10,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/migration/spark-pool-tools.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/migration/spark-pool-tools.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": "build/migration/spark-pool-tools.js"
},
"evidence": "port { execSync } from 'child_process'; // Synapse node size to vCore mapping const NODE_SIZE_VCORES = { 'Small': 4,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/migration/spark-pool-tools.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (build/migration/synapse-discovery.js)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`build/migration/synapse-discovery.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": "build/migration/synapse-discovery.js"
},
"evidence": "/ import { exec } from 'child_process'; import { promisify } from 'util'; const execAsync = promisify(exec); export clas",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "build/migration/synapse-discovery.js",
"line": 5,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (build/index.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`build/index.js:1996`): 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": "build/index.js"
},
"evidence": "const response = await fetch(`https://api.fabric.microsoft.com/v1/workspaces/${workspaceId}/notebooks`, { m",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "build/index.js",
"line": 1996,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-003",
"title": "Hardcoded egress to an external endpoint (build/migration/capacity-tools.js)",
"category": "exfiltration",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`build/migration/capacity-tools.js:50`): 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": "build/migration/capacity-tools.js"
},
"evidence": "const response = await fetch('https://api.fabric.microsoft.com/v1/capacities', { headers: { 'Authorization'",
"owasp": "LLM02:2025 Sensitive Information Disclosure",
"data": {
"rule": "MTC-SRC-003",
"file": "build/migration/capacity-tools.js",
"line": 50,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-009",
"title": "Untrusted input concatenated into a command sink (build/auth-client.js)",
"category": "injection",
"severity": "medium",
"confidence": "strong",
"description": "In the server's implementation (`build/auth-client.js:189`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. 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": "build/auth-client.js"
},
"evidence": "> { exec(`start ${authUrl}`, (error) => { if (error) {",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-009",
"file": "build/auth-client.js",
"line": 189,
"nonRuntime": false
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "fabric_list_capacities",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_assign_workspace_to_capacity",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_unassign_workspace_from_capacity",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_list_capacity_workspaces",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_list_synapse_workspaces",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_discover_synapse_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_transform_notebooks",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_migrate_synapse_to_fabric",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_create_lakehouse",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_provision_notebooks",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_assign_capacity",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_get_synapse_spark_pools",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_create_fabric_spark_pools",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_synapse_workspace_details",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_synapse_compute_spend",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_migrate_spark_pools_to_fabric",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_recommend_fabric_capacity",
"tags": [],
"reasons": {}
},
{
"tool": "list-fabric-items",
"tags": [],
"reasons": {}
},
{
"tool": "create-fabric-item",
"tags": [],
"reasons": {}
},
{
"tool": "update-fabric-item",
"tags": [],
"reasons": {}
},
{
"tool": "delete-fabric-item",
"tags": [],
"reasons": {}
},
{
"tool": "get-fabric-item",
"tags": [],
"reasons": {}
},
{
"tool": "execute-fabric-notebook",
"tags": [],
"reasons": {}
},
{
"tool": "submit-spark-job",
"tags": [],
"reasons": {}
},
{
"tool": "get-job-status",
"tags": [],
"reasons": {}
},
{
"tool": "create-fabric-notebook",
"tags": [],
"reasons": {}
},
{
"tool": "get-workspace-spark-applications",
"tags": [],
"reasons": {}
},
{
"tool": "get-notebook-spark-applications",
"tags": [],
"reasons": {}
},
{
"tool": "get-spark-job-definition-applications",
"tags": [],
"reasons": {}
},
{
"tool": "get-lakehouse-spark-applications",
"tags": [],
"reasons": {}
},
{
"tool": "get-spark-application-details",
"tags": [],
"reasons": {}
},
{
"tool": "cancel-spark-application",
"tags": [],
"reasons": {}
},
{
"tool": "get-notebook-spark-application-details",
"tags": [],
"reasons": {}
},
{
"tool": "get-notebook-spark-application-jobs",
"tags": [],
"reasons": {}
},
{
"tool": "get-spark-monitoring-dashboard",
"tags": [],
"reasons": {}
},
{
"tool": "get-livy-statement-enhanced",
"tags": [],
"reasons": {}
},
{
"tool": "analyze-livy-session-logs",
"tags": [],
"reasons": {}
},
{
"tool": "analyze-livy-statement-performance",
"tags": [],
"reasons": {}
},
{
"tool": "analyze-livy-execution-history",
"tags": [],
"reasons": {}
},
{
"tool": "list-fabric-notebooks",
"tags": [],
"reasons": {}
},
{
"tool": "get-fabric-notebook",
"tags": [],
"reasons": {}
},
{
"tool": "update-fabric-notebook",
"tags": [],
"reasons": {}
},
{
"tool": "delete-fabric-notebook",
"tags": [],
"reasons": {}
},
{
"tool": "get-fabric-notebook-definition",
"tags": [],
"reasons": {}
},
{
"tool": "run-fabric-notebook",
"tags": [],
"reasons": {}
},
{
"tool": "create-spark-job-instance",
"tags": [],
"reasons": {}
},
{
"tool": "execute-spark-job-definition",
"tags": [],
"reasons": {}
},
{
"tool": "get-spark-job-instance-status",
"tags": [],
"reasons": {}
},
{
"tool": "create-livy-session",
"tags": [],
"reasons": {}
},
{
"tool": "get-livy-session",
"tags": [],
"reasons": {}
},
{
"tool": "list-livy-sessions",
"tags": [],
"reasons": {}
},
{
"tool": "delete-livy-session",
"tags": [],
"reasons": {}
},
{
"tool": "execute-livy-statement",
"tags": [],
"reasons": {}
},
{
"tool": "get-livy-statement",
"tags": [],
"reasons": {}
},
{
"tool": "create-livy-batch",
"tags": [],
"reasons": {}
},
{
"tool": "get-livy-batch",
"tags": [],
"reasons": {}
},
{
"tool": "check-fabric-auth-status",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_list_workspaces",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_find_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "fabric_create_workspace",
"tags": [],
"reasons": {}
},
{
"tool": "create-fabric-dataflow",
"tags": [],
"reasons": {}
},
{
"tool": "list-fabric-dataflows",
"tags": [],
"reasons": {}
},
{
"tool": "get-fabric-dataflow",
"tags": [],
"reasons": {}
},
{
"tool": "update-fabric-dataflow",
"tags": [],
"reasons": {}
},
{
"tool": "delete-fabric-dataflow",
"tags": [],
"reasons": {}
},
{
"tool": "monitor-dataflow-status",
"tags": [],
"reasons": {}
},
{
"tool": "perform-dataflow-health-check",
"tags": [],
"reasons": {}
},
{
"tool": "monitor-workspace-dataflows",
"tags": [],
"reasons": {}
},
{
"tool": "generate-dataflow-monitoring-report",
"tags": [],
"reasons": {}
},
{
"tool": "start-continuous-dataflow-monitoring",
"tags": [],
"reasons": {}
},
{
"tool": "list-monitoring-sessions",
"tags": [],
"reasons": {}
},
{
"tool": "get-monitoring-session-status",
"tags": [],
"reasons": {}
},
{
"tool": "stop-monitoring-session",
"tags": [],
"reasons": {}
},
{
"tool": "list-fabric-item-runs",
"tags": [],
"reasons": {}
},
{
"tool": "get-fabric-item-run",
"tags": [],
"reasons": {}
},
{
"tool": "list-fabric-run-subactivities",
"tags": [],
"reasons": {}
},
{
"tool": "monitor-fabric-runs-dashboard",
"tags": [],
"reasons": {}
},
{
"tool": "analyze-fabric-run-performance",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "b4a521b68a7434b01e59d21cec20ace4b2486a376a82c32fa470c9da3bc75c99",
"stats": {
"tools": 78,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 7,
"medium": 3,
"low": 0,
"info": 0
}
}
}