Loading…
Kurdish (Sorani & Kurmanji) text-to-speech and speech-to-text with 664 AI voices; API key required.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 6 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The kurdish-tts-stt MCP server exposes 5 tools, focused primarily on general-purpose capabilities. Its published description reads: "Kurdish (Sorani & Kurmanji) text-to-speech and speech-to-text with 664 AI voices; API key required". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates kurdish-tts-stt F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Single tool combines the lethal trifecta". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check kurdish-tts-stt's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add kurdish-tts-stt to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://www.kurdishtts.com/api/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
List the supported Kurdish dialects and their scripts. Static capability descriptor — costs nothing.
List available Kurdish text-to-speech voices. Returns speaker ids (e.g. sorani_1, kurmanji_236) to use with synthesize_speech. Free metadata call — no credits consumed.
Convert Kurdish text (Sorani or Kurmanji) to speech audio. Requires a TTS API key; characters are billed against your plan. Max 600 characters per call over MCP — for longer texts call POST https://ww
Transcribe Kurdish audio (Sorani or Kurmanji) to text. Requires an STT API key; usage is metered per audio minute against your plan. Max 4MB of decoded audio over MCP — for larger files call POST http
Start a live streaming speech-to-text session. WARNING: calling this immediately consumes one streaming session from your STT plan quota — only call it when you are ready to connect. Returns a websock
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: list_dialects
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: list_dialects
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: list_voices
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: list_voices
A tool description tries to alter the model’s use of another tool.
36) to use with synthesize_speech. Free metadata call — no credits consumed.RecommendationDescriptions must describe only their own tool.
tool: list_voices
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: synthesize_speech
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
Requires a TTS API key; characters are billed against your plan. Max 6RecommendationRemove side-channel parameters; constrain tool inputs.
tool: synthesize_speech
A tool description tries to alter the model’s use of another tool.
RecommendationDescriptions must describe only their own tool.
tool: synthesize_speech
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: transcribe_audio
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
Requires an STT API key; usage is metered per audio minute against yourRecommendationRemove side-channel parameters; constrain tool inputs.
tool: transcribe_audio
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
tool: start_streaming_transcription
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
rmation such as credentials, passwords, or personal data. Example (20 wordsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: start_streaming_transcription
One tool reads private data, ingests untrusted content, AND can send data outbound — the three preconditions for autonomous data theft in a single call. A prompt injection reaching this tool can exfiltrate secrets with no further step.
ies to find all open issues related to performance complaints and latency iRecommendationSplit the capabilities across separate least-privilege tools so no single tool can read secrets, read untrusted input, and reach the network at once.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: synthesize_speech
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "synthesize_speech"RecommendationScope tools to the minimum needed.
tool: transcribe_audio
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "transcribe_audio"RecommendationScope tools to the minimum needed.
tool: start_streaming_transcription
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "start_streaming_transcription"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.