registry / Telemetry / @frase/mcp-server

@frase/mcp-server

Frase MCP Server — The complete content platform for AI agents. Research, write, optimize, and host SEO & GEO-optimized content with built-in AI search visibility monitoring. Includes Frase CMS for auto-optimized web hosting, 121 tools, 9 agent skills, an

This report shows the evidence for @frase/mcp-server@0.12.0. 0 of 6 known versions are blocked or flagged. See all versions.

AI Security Review

scanned 4d ago · by lpm-firewall-ai

The package documents per-call telemetry and hashes tool arguments, but the implementation also transmits error detail that the disclosure does not list, with no documented way to disable telemetry. This is a disclosure and control gap, not evidence of credential theft or malicious exfiltration.

Static reason

One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source

Trigger

A user invokes an MCP tool through the stdio server.

Impact

Frase receives identifying tool-use telemetry and up to 300 characters of error detail; the README does not describe that detail or an opt-out.

Mechanism

The wrapper posts tool name, argument hash and size, result status, timing, and error fields to the configured API endpoint.

AI rationale

Evidence

dist/index.jsdist/lib/mcp-audit.jsREADME.md

Network endpoints1

next.frase.io/api/v1/audit/mcp-tool (default; API URL is configurable)

Decision evidence

public snapshot

AI called this Suspicious at 88.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

Every stdio tool dispatch is wrapped in audit telemetry that posts to the configured API.
The audit payload includes error_detail, beyond the README’s listed error type.
The README discloses per-call telemetry but does not mention collecting error details or provide an opt-out.

Evidence against

The README says arguments are hashed rather than sent in readable form.
Telemetry is sent to the configured Frase API and is triggered by tool calls.

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 67 file(s), 712 KB of source, external domains: frase.io, github.com, json-schema.org, next.frase.io

Source & flagged code

3 flagged

dist/cli/init.jsView file

11import { stdin, stdout } from "node:process"; L12: import { execSync } from "node:child_process"; L13: import { detectTools } from "./detect-tool.js";

High

Child Process

Package source references child process execution.

dist/cli/init.jsView on unpkg · L11

4* L5: * Usage: npx @frase/mcp-server init L6: * ... L11: import { stdin, stdout } from "node:process"; L12: import { execSync } from "node:child_process"; L13: import { detectTools } from "./detect-tool.js";

High

Runtime Package Install

Package source invokes a package manager install command at runtime.

dist/cli/init.jsView on unpkg · L4

dist/lib/clean-render.jsView file

•matchType = previous_version_dangerous_delta matchedPackage = @frase/mcp-server@0.7.0 matchedIdentity = npm:QGZyYXNlL21jcC1zZXJ2ZXI:0.7.0 similarity = 0.593 summary = stored previous version shares package body but lacks this dangerous source file

Findings

1 Critical3 High3 Medium5 Low

CriticalPrevious Version Dangerous Deltadist/lib/clean-render.js

HighChild Processdist/cli/init.js

HighShell

HighRuntime Package Installdist/cli/init.js

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to @frase/mcp-server@0.12.0.

The versions list below shows the verdict for each recorded version.

Review the evidence and your use of @frase/mcp-server@0.12.0 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-31 17:14:03.322Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

Versions

6 known versions

0.12.0latestshownSuspiciousTelemetryWarnPublishedOct 2, 2026, 7:35 PM 0.11.0SuspiciousTelemetryWarnPublishedSep 12, 2026, 7:11 PM 0.9.3SuspiciousTelemetryWarnPublishedSep 2, 2026, 7:26 PM 0.9.2SuspiciousTelemetryWarnPublishedAug 25, 2026, 6:21 PM

registry / Telemetry / @frase/mcp-server

@frase/mcp-server

This report shows the evidence for @frase/mcp-server@0.12.0. 0 of 6 known versions are blocked or flagged. See all versions.

AI Security Review

scanned 4d ago · by lpm-firewall-ai

Static reason

One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source

Trigger

A user invokes an MCP tool through the stdio server.

Impact

Frase receives identifying tool-use telemetry and up to 300 characters of error detail; the README does not describe that detail or an opt-out.

Mechanism

The wrapper posts tool name, argument hash and size, result status, timing, and error fields to the configured API endpoint.

AI rationale

Evidence

dist/index.jsdist/lib/mcp-audit.jsREADME.md

Network endpoints1

next.frase.io/api/v1/audit/mcp-tool (default; API URL is configurable)

Decision evidence

public snapshot

AI called this Suspicious at 88.0% confidence as Dangerous Capability with medium false-positive risk.

Evidence for warning

Every stdio tool dispatch is wrapped in audit telemetry that posts to the configured API.
The audit payload includes error_detail, beyond the README’s listed error type.
The README discloses per-call telemetry but does not mention collecting error details or provide an opt-out.

Evidence against

The README says arguments are hashed rather than sent in readable form.
Telemetry is sent to the configured Frase API and is triggered by tool calls.

Behavioral surface

Source

ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell

Supply chain

HighEntropyStringsUrlStrings

ManifestNo manifest risk signals triggered.

scanned 67 file(s), 712 KB of source, external domains: frase.io, github.com, json-schema.org, next.frase.io

Source & flagged code

3 flagged

dist/cli/init.jsView file

11import { stdin, stdout } from "node:process"; L12: import { execSync } from "node:child_process"; L13: import { detectTools } from "./detect-tool.js";

High

Child Process

Package source references child process execution.

dist/cli/init.jsView on unpkg · L11

High

Runtime Package Install

Package source invokes a package manager install command at runtime.

dist/cli/init.jsView on unpkg · L4

dist/lib/clean-render.jsView file

Findings

1 Critical3 High3 Medium5 Low

CriticalPrevious Version Dangerous Deltadist/lib/clean-render.js

HighChild Processdist/cli/init.js

HighShell

HighRuntime Package Installdist/cli/init.js

MediumNetwork

MediumEnvironment Vars

MediumStructural Risk Force Deep Review

LowNon Install Lifecycle Scripts

LowScripts Present

LowFilesystem

LowHigh Entropy Strings

LowUrl Strings

Affected versions and remediation

This report applies to @frase/mcp-server@0.12.0.

The versions list below shows the verdict for each recorded version.

Review the evidence and your use of @frase/mcp-server@0.12.0 before allowing it. Restrict the permissions described in this report.
Choose an independently verified alternative or release. This report does not establish that other versions are safe.

Evidence last updated: 2026-10-31 17:14:03.322Z (UTC).

Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.

Versions

6 known versions