Agent Data Tools: AI
io.github.Nutshell2000/agent-data-tools-ai
Tools
Exactly what the server advertised in the scan completed . Effects and capabilities are classified by Squatch from each tool's metadata. Squatch never runs tools. Compared with the previous scan: 3 new, 1 changed.
- Effect: Read 29
- Effect: Write 8
Showing 37 of 37 tools
| Details | ||
|---|---|---|
| ai_chat Send a prompt, get an answer from Meta's Llama 4 Scout (17B active, 16 experts), with an optional system prompt, up to 1,024 output tokens … | Effect: Write | |
| ai_chat_large Send a prompt, get an answer from a larger open model: Llama 3.3 70B Instruct (default) or OpenAI gpt-oss-120b, with an optional system pro… | Effect: Write | |
| ai_embeddings Text embeddings API: a 1,024-dimension vector for up to 4,000 characters of text in 100+ languages (BAAI BGE-M3), also OpenAI-compatible at… | Effect: Write | |
| ai_speech Turn up to 300 characters of text into natural, human-sounding speech as an MP3 (base64), in English (40 voices) or Spanish (10 voices), wi… | Effect: Write | |
| ai_tts Text to speech API: turn up to 300 characters of text into natural, human-sounding speech as an MP3 (base64) with Deepgram Aura-2 voices, i… | Effect: Write | |
| image Text-to-image generation with FLUX.1 schnell. Send a prompt, get a 1024x1024 JPEG back as base64 in a few seconds. Use for illustrations, t… | Effect: Write | |
| text_to_speech Text to speech for a paragraph or a page: turn up to 2,000 characters of text into natural, human-sounding speech as one MP3 (base64), in E… | Effect: Write | |
| text_to_speech_liteNew Low-cost text to speech for longer English text: up to 2,000 characters as one MP3 (base64) with Deepgram Aura-1, 12 voices. Half the price… | Effect: Write | |
| ai_answer Answer a question from the live web in one call: a Brave web search, the top result pages read, and an answer written by Llama 4 Scout from… | Effect: Read | |
| ai_classify Zero-shot classification: give text and 2-20 candidate labels, get the best label, a short reason and a ranking. Use for routing tickets, t… | Effect: Read | |
| ai_embed A 1,024-dimension embedding vector for up to 4,000 characters of text in 100+ languages, from BAAI's BGE-M3. Use for semantic search, RAG r… | Effect: Read | |
| ai_extract_json Pull named fields out of unstructured text (emails, invoices, listings, bios) and get them back as a JSON object, with null for anything no… | Effect: Read | |
| ai_fact_check Check a claim against the live web in one call: a Brave search, the top pages read, and a verdict from Llama 4 Scout using those sources on… | Effect: Read | |
| ai_keywords The most important keywords and key phrases of a text, most relevant first. Use for tagging, SEO, search indexing and topic detection. Pric… | Effect: Read | |
| ai_model_deepseek_r1 Chat with DeepSeek's R1 reasoning model distilled into Qwen 32B (MIT) through one paid HTTP call: send a prompt and an optional system prom… | Effect: Read | |
| ai_model_gpt_oss_120b Chat with OpenAI's open-weight gpt-oss-120b reasoning model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system p… | Effect: Read | |
| ai_model_gpt_oss_20b Chat with OpenAI's open-weight gpt-oss-20b reasoning model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system pr… | Effect: Read | |
| ai_model_mistral_small Chat with Mistral AI's Mistral Small 3.1 24B model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, ge… | Effect: Read | |
| ai_model_qwen_coder Chat with Alibaba's Qwen2.5 Coder 32B code model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get … | Effect: Read | |
| ai_model_qwen3_30b Chat with Alibaba's Qwen3 30B-A3B mixture-of-experts model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system pr… | Effect: Read | |
| ai_moderation Classify a text as safe or unsafe with Meta's Llama Guard 3 and name the hazard categories it falls into (violent and non-violent crimes, s… | Effect: Read | |
| ai_outline A structured Markdown outline (headings and bullet points) of a text you send, or a suggested outline for a topic. Use to plan articles, re… | Effect: Read | |
| ai_rerank Order up to 50 documents by how well each answers a query, with a relevance score from 0 to 1 (BAAI bge-reranker-base, a cross-encoder). Se… | Effect: Read | |
| ai_rewrite Rewrite text to be more formal, casual, simpler, shorter, friendlier, more professional or more persuasive, keeping the meaning and languag… | Effect: Read | |
| ai_sentiment Positive or negative sentiment of English text with a confidence score, from a DistilBERT model fine-tuned on SST-2. Use to triage reviews,… | Effect: Read | |
| ai_sentiment_analysis Sentiment analysis of text: positive or negative with a confidence score, from a DistilBERT model fine-tuned on SST-2, for English text. Us… | Effect: Read | |
| ai_summarize Summarize text with an LLM: send up to 12,000 characters and get a short summary plus bullet key points. Use for long emails, articles, tra… | Effect: Read | |
| ai_summarize_text Summarize up to 12,000 characters of text you send into a few sentences plus bullet key points. Use for long emails, documents, transcripts… | Effect: Read | |
| ai_translate Translate text into another language with OpenAI's open-weight gpt-oss-20b, detecting the source language. Long text is split at sentence e… | Effect: Read | |
| ai_translate_text Translate text between languages with an open LLM (gpt-oss-20b; M2M100 for less common languages): the source language is detected, the tar… | Effect: Read | |
| describe Vision model for an image at a public URL: get a detailed description including any visible text, or pass a question to ask something speci… | Effect: Read | |
| image_generate Generate an image from a text prompt with FLUX.1 schnell: send a prompt, get a 1024x1024 JPEG back as base64 in a few seconds, with an opti… | Effect: Read | |
| llm_chat LLM chat completion and text generation: send a prompt (or an OpenAI messages array with tools and JSON mode) and get an answer from Meta's… | Effect: Read | |
| llm_inference LLM inference with a large open model: send a prompt (optional system prompt, up to 1,024 output tokens) and get an answer from Llama 3.3 7… | Effect: Read | |
| transcribeChanged Transcribe speech from an audio file at a public URL, or uploaded in a POST body, using Whisper large-v3-turbo. Returns the transcript text… | Effect: Read | |
| transcribe_longNew Transcribe a podcast, meeting, interview or lecture: up to 60 minutes of MP3 or WAV (25 MB) by URL or uploaded in a POST body, 90+ language… | Effect: Read | |
| transcribe_summaryNew Summarize a voice note, meeting, call or podcast in one call: transcribes up to 60 minutes (MP3/WAV up to 25 MB; M4A, OGG or WebM up to 5 M… | Effect: Read |