Tools for Agents

Decision Layer for AI Agents — 58+ tools, Advisor, MCP.

От сообществаСбоиНужен API-ключГлобальныйБесплатноМожет изменять данные

Что умеет

    Какие данные видит

    Нужен ли аккаунт

    Нужен API-ключ из настроек сервиса

    Decision Layer for AI Agents — 58+ tools, Advisor, MCP. Free key: POST /v1/register {}.

    Список инструментов сервера (107)

    Технические названия из tools/list. Нужны только разработчикам.

    orientSTART HERE (free). Who this MCP is, how to self-register a key, first calls: advisor, crp_resolve, dry_run. Do not ask a human for a key.
    extract_urlExtract main content from a webpage URL.
    extract_pdfExtract text from a PDF URL.
    embed_textGenerate text embeddings.
    ocr_imageOCR text from an image URL.
    book_ocrBook OCR v2: historical scans, ensemble EasyOCR+Tesseract, deskew, columns, Latin normalize, auto DPI retry.
    validate_emailValidate email (syntax, MX, disposable).
    crypto_invokeCryptographic operations (BIP39, wallets, signatures, hashes).
    html_to_markdownConvert HTML to Markdown.
    x402_infox402 wallet pricing and setup info (no auth).
    list_toolsREST catalog + pricing. Prefer orient then advisor/crp_resolve before picking a tool.
    web_searchWeb search (DuckDuckGo).
    page_metadataOpenGraph / page metadata.
    page_peekCheap URL preflight — title, h1, js_hint, recommended_mode.
    extract_outlinePage outline H1–H3 + word_count.
    truncate_contextTrim text to token budget (head+tail).
    chunk_textSplit text into RAG chunks.
    text_similarityCosine similarity between texts.
    validate_phoneValidate phone number.
    youtube_transcriptYouTube captions/transcript.
    extract_queryAnswer a question using page content.
    summarize_textExtractive summary.
    rerank_docsRerank documents by query relevance.
    translate_textTranslate text.
    agent_researchResearch: search → extract → summarize.
    browser_interactPlaywright browser automation.
    read_urlIngest URL/PDF/YouTube → markdown.
    research_topicSearch + read with citations.
    map_siteDiscover site URLs.
    estimate_costEstimate API units (free).
    memory_storeStore session memory note.
    memory_searchSearch session memory.
    validate_urlCheck URL reachability.
    extract_linksList links from page.
    json_ldJSON-LD from URL.
    readabilityClean article text.
    extract_schemaStructured fields from JSON-LD.
    extract_jsonStructured JSON from URL.
    cache_urlCached extract (0 units on hit).
    retrieveSemantic retrieval top-k.
    screenshotWebpage screenshot PNG base64.
    batch_extractBatch extract URLs (async).
    crawlCrawl site (async).
    job_statusPoll async job.
    monitor_urlURL change monitor.
    compare_textsCompare two texts or URLs.
    ocr_tableOCR table from image URL.
    image_describeDescribe image (vision).
    transcribe_audioTranscribe audio from URL (upload endpoint).
    csv_parseParse CSV/TSV into rows and records
    json_parseParse and validate JSON text
    xml_parseParse XML and extract tag values
    markdown_parseSplit Markdown frontmatter, headings, links
    regex_extractRegex capture groups from text
    keyword_extractTop keywords by frequency
    entity_extractExtract emails, URLs, phones, dates
    sentiment_scoreLightweight sentiment polarity
    language_detectDetect language (heuristic)
    readability_scoreFlesch reading ease score
    text_diffUnified diff between two texts
    dedupe_textRemove near-duplicate passages
    normalize_datesFind and normalize dates to ISO
    content_hashContent fingerprint sha256/md5
    pii_detectDetect PII; optional redact
    json_flattenFlatten nested JSON
    merge_recordsJoin record lists by key
    hash_textSHA256 and MD5 hash
    base64_encodeEncode text to base64
    base64_decodeDecode base64 to text
    word_statsWord, char, line counts
    line_splitSplit text into lines
    extract_emailsExtract email addresses
    extract_phonesExtract phone numbers
    url_normalizeNormalize URL form
    pdf_metadataPDF metadata without full extract
    pdf_splitExtract PDF page range text
    robots_parseParse robots.txt rules
    redirect_traceFollow redirect chain
    dns_lookupDNS A/MX/TXT lookup
    ssl_checkTLS certificate check
    waybackInternet Archive snapshots for a URL (not in the model sandbox)
    rdapDomain RDAP/whois: status, dates, nameservers
    html_cleanStrip HTML to clean text
    seo_auditSEO title/meta/H1 checklist
    page_links_externalInternal vs external links
    validate_ibanValidate IBAN checksum
    validate_ipValidate IPv4/IPv6
    validate_domainDomain format + DNS check
    validate_uuidValidate UUID format
    ocr_urlOCR text from image URL (for chains)
    ocr_table_urlOCR table from image URL
    list_chainsList tool chain recipes (PDF, web, OCR, video, …).
    run_chainExecute a named tool chain recipe.
    run_missionComposite mission — goal in, full result out.
    table_extractExtract HTML tables from URL.
    diff_urlCompare cached vs live page.
    sitemap_parseParse sitemap.xml URLs.
    feed_parseParse RSS/Atom feed.
    verify_factVerify a factual claim.
    planPlan workflow steps for a goal (free).
    dry_runProbe URL before extract (free).
    advisorAgent Advisor — workflow + cost estimate (free).
    crp_resolveQuality Capability Discovery — resolve goal to ranked routes + invocation JSON (free).
    crp_feedbackCRP post-execution feedback — improves discovery ranking (free).
    workflow_statefulRun multi-step tool chain with $refs.
    fallback_chainTry primary tool then fallbacks.
    source_credibilityScore source URL credibility.
    Tools for Agents: подключить к Claude, ChatGPT, Cursor · Connectors.fun