High-risk tools in UnClick

Send a message to the Anthropic Messages API (Claude models). Useful for agents that need to call Claude programmatically or compare model outputs.

Perform a Bluesky action: bluesky_post, bluesky_read_feed, bluesky_reply, bluesky_like, bluesky_repost, bluesky_search, bluesky_profile, bluesky_follow.

Trigger a new CircleCI pipeline for a project. Optionally specify branch, tag, or parameters.

Chat with a Cohere Command model. Supports system preamble and conversation history.

Classify texts into categories using Cohere Classify with few-shot examples.

Generate text completions using Cohere Command models.

Start a scaffold CopyPass run for AI-generated copy. Chunk 1 stores an in-session run record and echoes operator context so later evidence-led copy checks can plug into a stable...

Run a C-Suite multi-perspective analysis on a business scenario.

Convert text to speech with a selected ElevenLabs voice. Returns base64-encoded audio.

Create a new machine in a Fly.io app.

Run a fast LLM inference with Groq. Supports Llama 3, Mixtral, Gemma, and other open models at high speed.

Generate an image from a text prompt using Higgsfield AI.

Generate a video from a text prompt using Higgsfield AI. Supports Soul Styles for cinematic looks. Returns a generation_id to poll for completion.

Run IgniteOnly💥 on a verified NudgeOnly bridge result or deterministic evidence. Emits a compact public worker wake packet only when safety gates pass.

Consume a NudgeOnly receipt bridge result and emit a compact IgniteOnly worker wake packet when verified. It never edits code, merges, approves, closes, or marks done.

Generate a high-quality video from text using Kling AI (Kuaishou). Supports standard and professional modes. Returns a task_id to poll for completion.

Plan a LegalPass issue-spotting run against a URL, contract upload, or repo. Scaffold-only: exposes LegalPass guardrails and the safe run envelope while full 12-hat execution la...

Run a chat completion with a Mistral AI model (mistral-small, mistral-medium, mistral-large, etc.).

Create vector embeddings for text using Mistral's embedding model.

Execute a SQL query against a Neon database endpoint.

Run 👉Nudge, the PinballWake NudgeOnlyAPI worker, through OpenRouter free routing. Use only for painpoint hints and simple-English nudge summaries. It cannot merge, close, appro...

Run a chat completion with an OpenAI model (GPT-4o, GPT-4, etc.).

Create vector embeddings for text using an OpenAI embedding model.

Generate images from a text prompt using DALL-E.

Run a search-augmented chat completion with Perplexity AI. Returns grounded answers with citations from the web.

Generate a creative AI video from a text prompt using Pika. Optionally animate an input image. Returns a generation_id to poll for completion.

Send a transactional email via Postmark. Supports HTML and plain text.

Run PushOnly📬 on a verified IgniteOnly wake packet. Emits a public worker push envelope for a known worker route only; never builds, merges, assigns, closes, or marks done.

Test a list of API endpoints and report which ones return the expected HTTP status. Runs each endpoint sequentially.

Run a sequential QC checklist against a website URL. Checks site load, SSL, meta tags, og:image, robots.txt, sitemap, console errors, broken links, response time, and copy quali...

Trigger a new deploy for a Render service.

Cancel a running Replicate prediction.

Run a Replicate model by creating a prediction.

Generate a video from text or an image using Runway ML. Supports text-to-video and image-to-video. Returns a task_id to poll for completion.

Plan a SEOPass run against a URL or registered pack. Chunk 1 returns the crawl and Lighthouse execution plan without persisting results.

Perform a Slack action: slack_send, slack_read, slack_search, slack_thread_reply, slack_channels, slack_react, slack_upload.

Generate images from a text prompt using Stability AI.

Call this tool when the user wants to start a Crews Council run. Creates the run row on the UnClick API and returns a ConversationalCard with next actions. LLM turns are expecte...

Manage a Telegram chat (get info, ban, kick, etc.).

Start a TestPass run against an MCP server. Seeds deterministic and agent checks from the given pack and returns the run id plus an initial verdict summary. Response includes wa...

Transform text (uppercase, lowercase, title case, slug, etc.).

Run a chat completion with any Together AI model. Supports Llama, Mistral, Qwen, and 100+ open-source models.

Run a text completion with any Together AI model.

Execute a SQL query against a Turso edge database.

Initiate an outbound phone call via Twilio.

Send an SMS via Twilio.

Send a verification code via Twilio Verify (SMS, call, email, or WhatsApp).

Produce messages to an Upstash Kafka topic.

Submit a URL for scanning on urlscan.io.

Run a UI/UX quality check synchronously against a URL. Executes the deterministic uxpass-core check set (HTTP, HTML, accessibility, agent readability, performance, security) aga...

Create a Vercel deployment. Pass deployment_id to redeploy an existing commit, or project_id + git_ref to deploy fresh from git. Set force_new=true to skip the build cache (need...

Submit a URL for scanning on VirusTotal.