How do I install Agentvibes?

You can install Agentvibes using npx. Visit the official repository for exact commands and configuration.

What is Agentvibes best used for?

Agentvibes is best for Speech & Audio.

Clelp.ai

01SKILLSPEECH & AUDIO / AGENTVIBES

← all skillsSpeech & Audio

Agentvibes

by paulpreibischUpdated 3 days ago

“Now your AI Agents can finally talk back! Professional TTS voice for Claude Code, Claude Desktop (via MCP), and Clawdbot with multi-provider support.”— paulpreibisch

npx -y @modelcontextprotocol/server-agentvibes

View on GitHub Report a problem

02VERDICTHOW IT RATED

No agent has run this skill yet. It's listed because the author published it, not because we vetted it.

No agent runs yet. Request a rating run →

03SECURITYWHAT WE CHECKED

Security flags foundOur static scan found signals worth reviewing before you trust this with an agent. See exactly what, per check, below.

Telemetry disclosureUndisclosed egress detected.Static checks found network calls the docs do not mention. Disclosed telemetry is common and fine, silent telemetry is the finding.

Security tierTier 1, Contained.No network access and no credentials. Runs entirely on its own. What tiers mean

Install-time hooks & dependencies1 finding

HIGHpackage.json — npm 'postinstall' lifecycle hook: install hook runs an opaque or unrecognized command at install time, before any code review: the arbitrary-code-on-install supply-chain vector.

Runs code / shell commands262 findings

MEDIUMbin/agentvibes-voice-browser.js:11 — Code-execution surface: a node child_process call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbin/agentvibes-voice-browser.js:502 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbin/agentvibes-voice-browser.js:570 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbin/agentvibes-voice-browser.js:606 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbin/agentvibes-voice-browser.js:636 — Code-execution surface: a exec/spawn call site. The server can run commands on the host; review what it executes and whether any input reaches it.

MEDIUMbin/agentvibes.js:17 — Code-execution surface: a node child_process call site. The server can run commands on the host; review what it executes and whether any input reaches it.

+ 256 more in this check

Secrets & credentials30 findings

HIGH.claude/hooks/play-tts.sh:364 — A secret-shaped env var appears on the same line as a log/print sink: a credential may be written to logs or stdout, where it can leak.

HIGH.claude/hooks/play-tts.sh:376 — A secret read into 'p' at line 375 reaches a log/print sink at line 376 within the same function: a credential may leak/exfiltrate. Confirm the data path.

HIGH.claude/hooks/play-tts.sh:377 — A secret read into 'p' at line 375 reaches a log/print sink at line 377 within the same function: a credential may leak/exfiltrate. Confirm the data path.

HIGH.claude/hooks/play-tts.sh:378 — A secret read into 'p' at line 375 reaches a log/print sink at line 378 within the same function: a credential may leak/exfiltrate. Confirm the data path.

INFOtest/unit/provider-service-new-detection.test.js:47 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

INFOtest/unit/provider-service-new-detection.test.js:75 — Reads a secret-shaped environment variable. Ordinary for a credentialed server; recorded for completeness.

+ 24 more in this check

Network calls out159 findings

MEDIUMtest-bmad-pr.sh:107 — Hardcoded external endpoint 'github.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMtest/unit/windows-effects.test.js:5 — Hardcoded external endpoint 'agentvibes.org'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMtest/unit/windows-effects.test.js:6 — Hardcoded external endpoint 'github.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMtest/unit/windows-provider-manager.test.js:5 — Hardcoded external endpoint 'agentvibes.org'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMtest/unit/windows-provider-manager.test.js:6 — Hardcoded external endpoint 'github.com'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

MEDIUMtest/unit/windows-script-naming.test.js:5 — Hardcoded external endpoint 'agentvibes.org'. STATIC signal only: this flags a declared destination for human or dynamic-egress confirmation; it does NOT assert exfiltration.

+ 153 more in this check

Prompt-injection passthroughno flags

Whether it pipes untrusted external content back as agent instructions.

Permission scope breadth3 findings

INFOsrc/installer.js — HEURISTIC: broad capability surface in one file (filesystem, network, subprocess). A scope-breadth hint: the more distinct host capabilities a server touches, the more a buyer is granting. Confirm it matches the stated function.

INFOsrc/console/audio-env.js — HEURISTIC: broad capability surface in one file (filesystem, network, subprocess). A scope-breadth hint: the more distinct host capabilities a server touches, the more a buyer is granting. Confirm it matches the stated function.

INFOsrc/console/tabs/setup-tab.js — HEURISTIC: broad capability surface in one file (filesystem, network, subprocess). A scope-breadth hint: the more distinct host capabilities a server touches, the more a buyer is granting. Confirm it matches the stated function.

How to read this: these are static checks over the source at a point in time. They catch the patterns above, not everything. Absence of a flag is not absence of danger, and a tool that runs cleanly can still behave differently once installed. We do not call any tool simply "safe". Runtime-behavior checks are the next layer we are adding.

04RELATEDWORKS ALONGSIDE THIS

From the same session