io.github.Nutshell2000/agent-data-tools-ai

up checked 2026-11-11T04:38:22.060Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided title

Agent Data Tools: AI

Publisher-provided description

34 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.

Summary by lookupd

Gives agents hosted LLM chat, web-grounded answers, summaries, translation, embeddings, moderation, speech, image generation and…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http agent-data-tools-ai https://agent-data-tools.revmesh2074.workers.dev/mcp/ai

Codex, remote (streamable-http)

codex mcp add agent-data-tools-ai --url https://agent-data-tools.revmesh2074.workers.dev/mcp/ai

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "agent-data-tools-ai": {
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/ai"
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (showing 30 of 34)

Publisher-provided text

• 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 and adjustable temper
• 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 prompt, up to 1,024 outp
• 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 retrieval, clustering
• transcribe Transcribe speech from an audio file at a public URL using Whisper large-v3-turbo. Returns the transcript text, detected language, duration and word count. Acce
• 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), with Deepgram Aura-2. P
• 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, thumbnails, mockups, a
• 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 specific about the image.
• 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 and tool outputs (fo
• 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 ends and checked, so a
• 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 not present. Use to tur
• 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 those sources only,
• 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 only (supported, contra
• 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 English (40 voices) or
• 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). Send documents as a JSO
• 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, sexual content, child
• 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, in English (40 voices)
• 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, transcripts, meeting not
• 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. Use to classify reviews
• 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 target is an ISO code su
• 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 /v1/embeddings. Use
• 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 optional steps setting (1
• 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 Llama 4 Scout, up to
• 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 70B Instruct or OpenAI
• 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 prompt, get the answer,
• 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 prompt, get the answer,
• 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 prompt, get the answer
• 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, get the answer, up to 1
• 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 the answer, up to 1,0
• 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 prompt, get the answer, u
• 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, support messages, so

Changes

Newest first, as lookupd saw them

• 2026-11-11: version 1.133.0 → 1.135.0
• 2026-11-11: version 1.132.0 → 1.133.0
• 2026-11-11: version 1.131.0 → 1.132.0
• 2026-11-11: version 1.128.0 → 1.131.0
• 2026-11-11: version 1.126.0 → 1.128.0
• 2026-11-11: version 1.122.0 → 1.123.0

Details

• Version: 1.135.0
• Transports: streamable-http
• Uptime (7 days): 100%
• Median latency: 897 ms
• First indexed: 2026-11-01T09:13:00.526Z
• Last seen in registry: 2026-11-11T15:17:16.366Z
• Repository: https://github.com/Nutshell2000/agent-data-tools
• Website: https://agent-data-tools.revmesh2074.workers.dev/

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.Nutshell2000/agent-data-tools-ai.svg)](https://lookupd.com/servers/io.github.Nutshell2000/agent-data-tools-ai)

• 62033 servers
• Last crawl: 2026-11-11T15:38:39.561Z
• API base: https://api.lookupd.com
• MCP URL: https://api.lookupd.com/mcp