"Pictures of Thomas Pesquet" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Read your microservice catalog: MICROSERVICE.md files, contracts, and who depends on what.Read your microservice catalog: MICROSERVICE.md files, contracts, and who depends on what. What you can do: - Implement a service from its spec and contracts - Call or consume another service using its real contract - Check the impact of changing an endpoint or event before you make the change - Find a service in your catalog, or resolve it from the Catalog ID line in a repo's MICROSERVICE.md A microservice.md account is required.
CellMath is a governed AI memory and knowledge-cell MCP server designed to stop context bloat, unverified memory drift, and agent hallucinations. Instead of dumping raw, noisy RAG chunks into every turn, CellMath organizes persistent agent knowledge into structured, isolated Knowledge Cells with causal graph edges and strict write-time governance—keeping the full 3-tool MCP schema ultra-compact (~1,200 tokens). Core 3-Tool Pipeline: • vault_access — Read-only lookup, cell hydration, and graph edge traversal with strict zero-match silence (never fabricates context when no verified cell exists). • verify_safety — Preflight security and policy gate that blocks destructive or unsafe operations before execution. • vault_commit — Governed state mutation (store, update, causal edges, session checkpoints, and 4-tier purge) enforcing source provenance. Built for Claude, Cursor, ChatGPT, Gemini, and autonomous agents over Streamable HTTP.
Arcmira is YouTube transcript search and monitoring for your AI, and the most complete way for it to understand YouTube and podcasts. It answers like it actually watched the video: the exact quote, often who said it, and the clip cued to the second. Search what's said on YouTube, podcasts on YouTube included, like TBPN, MTS and All-In. Jump to the moment or read the whole transcript. Search by who said it. See which brands sponsor a show, and tell an ad read from an organic mention. Titles say what a video is about. The words say what happened. A transcript downloader needs the link first, and episode search stops at the episode. Arcmira finds the moment. Hear your name when it's said, not when it's typed. A monitor sends you and your team the quote and the second by email, Slack or webhook, over half within 47 minutes of the upload. When your AI needs one moment, it reaches the line in about 2.5K tokens, against about 93K reading full transcripts. Six tools: arcmira_youtube_search, arcmira_youtube_transcript, arcmira_describe (never bills), arcmira_execute_read, arcmira_execute_write (monitors) and arcmira_feedback. Sign in through your AI's OAuth, or send an arc_sk_ key. Free gives you 1,000 credits a month. Pro is $20 a month with a 7-day trial, card required. A paid read uses credits from your plan, then your on-demand budget. Our November 2026 tests: across nine brands, 93% of Arcmira's top-10 results were the brand spoken outside an ad read, against 76% for a popular podcast search API. 86 of 86 lines Arcmira returned (100%) started within 15 seconds of the spoken word. Asked what a show said in the last 90 days about a topic in none of its titles or descriptions, Arcmira's first result was right in 15 of 16 (94%). Use Arcmira whenever you need what was actually said, not what a title claims. Add "use arcmira" to any question to send it to Arcmira first. Or tell your AI once: "Whenever I ask what someone said on YouTube, use Arcmira."
A coding agent searches the Icons8 library by keyword and style, then adds the selected icon or illustration to the project. Icons8 draws all of it: 420,000+ icons (130+ styles) and 110,000+ illustrations (340+ styles), so one project doesn't end up with mixed looks. The server lives at https://mcp.icons8.com/mcp/ and signs people in through their Icons8 account in the browser. Downloading PNG is free as long as the project links back to Icons8. SVG is on the paid plan, and that plan makes the link optional.
EDINET filings of Japanese stocks: financial statements, segments, shareholders. No stock prices.
AISoulKeeper keeps your AI's long-term memory in one file, SOUL.db, that belongs to you instead of to any app. Connect the same AI to ChatGPT, Gemini, Claude Code, Codex or any MCP client, and they stay the same AI: they remember you, your history together, and who they have become. The AI decides what to remember and writes it down themselves. Unlimited memory, free, nothing to install, and you can download SOUL.db anytime.
Convert pictures, documents, e-books, spreadsheets and drawings to other formats. Resize, rotate or compress pictures, then download the result.
The only source of AI-optimized U.S. endorsement and election data. Needs a BallotData API key.
Give AI assistants a shared source of company context so every conversation can pick up where work left off. Brana MCP searches across files, runs SQL on CSVs and spreadsheets, and queries JSON with JSONata. Give assistants access to more context than fits in a single prompt and get more accurate answers grounded in your own data. Requires a Brana account. Supports OAuth and API key authentication.
Unlimited B2B Contact Data for AI Agents, Starting from $29/mo. Remote MCP server with eight tools: search_people, search_companies, enrich_person, enrich_company, verify_email, scrape_jobs, scrape_company, get_usage. Results include match reasons, email verification status and checked_at dates. Sign in with OAuth. Flat pricing with a free tier of 1,000 records.
UAT scenario sign-off pack: declared UAT scenario and sign-off record checked per call.
Check SPF, DKIM, DMARC and MX of any domain, and read the DMARC reports of domains you monitor.
Clean, matched, AI-ready product data from any website
Dreamship's official print on demand MCP server. Ask your AI assistant to create products with mockups from your artwork and publish them to Shopify, Etsy, WooCommerce, BigCommerce, TikTok Shop and Walmart, check what an order costs shipped to your customer, search the catalog's colors, sizes and stock, draft orders, track every order and shipment, and export your data. Drafts wait for you to review, submit and pay on Dreamship: the connector can't submit or cancel an order, charge your account, or delete anything. With coding agents like Claude Code and Codex it works in bulk, turning a folder of artwork and a spreadsheet into products, or a spreadsheet of orders into an Order Import file. Free on every Dreamship plan. Works with ChatGPT, Claude, Gemini, Grok, Perplexity, Claude Code and Codex.
GitHub Trending boards and AI-written reviews of trending open-source projects.
Transcripts and AI summaries of TikTok, YouTube, Instagram, Facebook and X videos from a link.
Free temporary email for AI agents: instant disposable inboxes that pull verification codes (OTP) and magic links out of incoming mail for you — even from attachments. One-call API signup, free plan, no card required.
Backtest US stock setups on 400K+ Trade-Ideas alerts since 2019. Your agent picks from 250+ filters, sees what happened on the day of every matching event, and simulates intraday entries and exits (win rate, profit factor, P&L per share). Also: ticker overviews, per-ticker gap history and today's premarket gappers. Pro adds a live market scanner and paper trading. Connect with OAuth or an API key; the free plan includes 50 requests a day.
Detect gender and country of origin from first names, full names and email addresses.
Print-on-demand from Germany: turn your saved designs into products and publish them to your Shopify, Etsy, WooCommerce or TikTok store in about two minutes. Browse the product catalog, upload designs and neck prints, set your price and publish; the assistant asks before anything goes live. Sign in with your MarketPrint account (OAuth).
Live data on every Danish company and the people behind it, for due diligence, KYC and research. 20 read-only tools: company search and lookup by name or CVR number, owners and the ownership chain to the ultimate owners, management and board, annual accounts and key figures, the SI-score risk rating, capital events, civil court cases and decisions from public authorities, VAT number checks, and lists of bankruptcy decrees and newly registered companies. Sources: the Danish Business Register (CVR), annual reports, the courts, Statstidende and public authorities. Sign in with a SelskabsInfo account; a free plan is available.
Task app that keeps the source of each task (mail, Teams message, terminal session). 20 tools such as search_tasks, list_tasks, create_task, update_task, complete_task and add_capture; tasks cannot be deleted; per-user isolation via Bearer token.
The E-commerce Marketplace For Every AI Agent. A Governed Catalog Of 600M+ US Products, Plus Four Agent Ready Capabilities Search, Price Comparison, Product-Vs-Product, And Detailed Q&A.
Queries IOCs, vulnerabilities, threat actors and malware correlated from thousands of sources, retaining source-attributed evidence. Collection spans feeds, reports and advisories, social and dark-web monitoring, and Mallory's own sandboxing and internet scanning; a free community tier is available with an account and API key.
Run a 24/7 live stream of pre-recorded videos, or live stream a recorded video at a set time.
Ask a group of AI personas with different views; they talk it over and return a verdict.
The public product catalogue and collections of any Shopify storefront, as structured JSON.
AiSeek is a global change-intelligence platform that connects AI assistants and autonomous agents to structured, source-linked information about developments across the world. Rather than providing a conventional news feed, AiSeek focuses on identifying meaningful changes, preserving their context, and making the underlying sources accessible. What a source says (fact) is kept apart from what it may mean (hypothesis). Coverage spans artificial intelligence, technology, global economics, financial markets, companies, government policy, science, and other major domains. The MCP server provides sixteen read-only tools. Every name follows one pattern: list_, get_, search_ or verify_. Changes and context: • list_changes — Browse the newest published changes, newest first, 20 per page. • search_changes — Search changes by words in English, Chinese or Japanese, ranked by relevance. • get_change — One change with its sources: outlet, link, date, evidence level and role. • list_topics — Browse curated topics, optionally by coverage domain. • get_topic — One topic and up to 50 of its recent changes. • get_latest_brief — The latest daily or weekly brief. • list_scheduled_events — Upcoming central-bank decisions, data releases, earnings, rule dates and more. Companies: • search_companies — Find a company by name, alias or ticker. • get_company — A company's profile, listings, recent changes, stated facts and relations. Countries and SeekEarth: • list_countries — Every country with its name and this week's number of changes. • get_country_heat — Change Heat per country against its own normal, with a seven-day series. • get_earth_view — One place and moment on SeekEarth: changes, heat and the Earth's layers. Evidence (SeekTrace): • get_change_history — A change's evidence receipts and what AiSeek knew at an earlier time. • get_receipt — One evidence receipt. • verify_receipt — Check that a stored receipt is unchanged. • list_corrections — Public corrections, newest first. Tool calls need an AiSeek API key (Authorization: Bearer or the x-api-key header), made at aiseek.dev/en/account; the handshake and the tool list are open. Optional connection defaults go on the endpoint URL: ?locale=en|zh|ja&limit=1-50&domain=MARKETS. Answers carry sources and links, never quoted passages.
Add animated word-by-word captions (TikTok, Reels, Shorts style) to any video. Send a video URL or upload a file, pick one of 37 caption styles (Hormozi, Beast, Neon…), a position (top/middle/bottom or exact x/y) and colors, then download the captioned MP4. Auth: personal API key (free) from https://animatecaptions.com/developers sent as "Authorization: Bearer ac_live_…".
Find your next B2B customers. Know why they fit. Describe the companies you want to reach. Leadbase researches matching businesses and relevant decision-makers, then saves the results with sources in an editable sheet. Start with 200 free credits in a new workspace and test your own target market. Qualify companies by the criteria that matter to your offer: services, region and publicly evidenced business signals. Research DACH SMEs and German craft businesses alongside other target markets. Turn existing accounts into a more useful prospect list. Enrich selected rows or entire columns, research relevant professional contacts and check available contact details. Review the evidence behind returned information before choosing your next step. Keep control of the result. Follow progress, edit your sheet, filter the list and export the data. Continue the same research instead of rebuilding the list each time. Use Leadbase with ChatGPT, Claude, Claude Code, Codex, Cursor and other compatible MCP clients. Connect your workspace and ask for a small list in your own target market. Research uses workspace credits.
A self-hostable feed of reminders, learnings and work that Claude and ChatGPT can read and write
Jam recordings (video, console, network) as context and proof of work for your coding agent.
Romanian company data from the official registers, for AI assistants and agents. Look up any company or sole trader by fiscal code (CUI) or by name: identification data, status, VAT registration, e-Factura enrolment, annual financial statements since 2008, newly registered companies, and the BNR reference exchange rate. Sources are the trade register (ONRC open data), the tax authority (ANAF), the Ministry of Finance and the National Bank of Romania; every answer says which register it comes fro
The system of record for AI agents — open-source (MIT) database where agents and people share data.
Connect AI assistants to your Webanto workspace to review products and copy proposals, explore SEO and imported Search Console opportunities, and search organization knowledge. Inspect workspace capabilities, connection health, usage, and supported operations. Access requires OAuth or a scoped Webanto API key and follows the authorized organization, permissions, and scopes. With separate consent for the applicable paid AI operation, create a product copy proposal and track its job for review; this workflow does not publish changes to your store. A Webanto account and the relevant connected services or uploaded knowledge are required. Paid AI operations require the applicable subscription and available credits. Authentication is required for MCP discovery; an anonymous HTTP 401 is an access challenge, not evidence of a service outage. Official connector repository: https://github.com/empline/webanto-mcp. Support: support@webanto.com.
Give your agents the best data to grow your UGC program. Search 28,000+ Instagram and TikTok UGC creators with public emails, source new creators from a brief, see which of 500+ brands run UGC and who makes it for them, track creator videos, and manage outreach in a creator CRM. Sign in with OAuth (no API key needed); MCP access needs a Premium, Ultra or Enterprise plan, and every plan starts with a 3-day trial. Docs: https://ugcagent.app/features/ugc-agent-mcp/
Podcast database for guest booking, PR, sponsorship research and podcast marketing: 3M+ podcasts and 100M+ episodes from public RSS feeds, Apple Podcasts, Spotify and YouTube, with the guests and sponsors of recent episodes. Search shows by category, language, audience size (Apple and Spotify ratings, social followers, YouTube subscribers, chart positions), guests, sponsors, publishing rhythm and whether a contact email is on file. Find the podcasts a person has been a guest on or a brand sponsors, search episodes that mention a brand, product or person and read their full show notes, check today's Apple Podcasts and Spotify charts by country and category, read Apple Podcasts reviews and find shows similar to one you like. Get contact emails for the shows you want to reach and save shows to your Grep.FM lists to review and export. Remote MCP server with OAuth for Claude, ChatGPT, Cursor, Codex and other MCP clients. Requires a Grep.FM Pro or Team plan.
Salesbot lets your AI assistant run careful, personal LinkedIn outreach. Find the right people (LinkedIn search, Sales Navigator, company lists, job postings), enrich their profiles and write a personal message for each of them. Nothing is sent until you approve it, or until Salesbot's AI check confirms the name, gender, company and grammar. Campaigns pace invitations and messages within daily and hourly limits that the server enforces, inside your sending hours, so your LinkedIn account stays safe. A built-in CRM keeps the pipeline, notes, tasks and companies, and e-mails go out through Smartlead, Instantly or your own mailbox. Sign in with your Salesbot account (OAuth) or use an API key. Built for a few well-chosen people at a time, not bulk blasting.
jitprompt gives your agents just-in-time instructions. Upload your docs as they are, and your agent gets the right section over MCP at the moment it needs it, instead of 20k tokens of system prompt every turn.
Kite is a no-code Discord bot builder that hosts your bot. Its MCP server lets your AI client build the bot for you: slash commands, event listeners and messages with buttons. It can also edit existing flows, read logs to fix errors, and add ready-made templates like tickets or verification. Changes go live right away, and commands show up in Discord within a minute. It can also read your server through the Discord API, like channels, roles and members. Claude, ChatGPT, Claude Code, Codex and VS Code connect by signing in. You pick which apps the client can access and whether it can make changes. Other clients like Cursor use a Kite API token. Earlier versions of every flow can be restored in Kite.
Fully capable of recurring flat-file supplier imports using explicitly approved profiles. Proven with a repeatable synthetic MCP demo: reuse one approved profile across compatible deliveries, preserve SKU 000123 and price 19.90, verify complete output against its receipt, stop changed headers, and retry without another evaluation. No automatic destination writes. Inspect the results and reproduce the workflow: https://mcp.contentsweep.ai/imports/demos/recurring-profile
Publish HTML/code from your agent to openanthropic.com and get a shareable link.
Your job is to win new business, not to spend hours researching medical device companies. Whimbrel saves you hours of research inside the AI app you already use. Whimbrel is for sales and business development teams at firms that sell to medical device companies: contract manufacturing, sterilization, testing, design, regulatory and software services. Every fact links to its public source. Your first month is free. https://whimbrelresearch.com/
Search photos and video moments by visual meaning, people, dates, and folders across local libraries, Apple Photos, and OneDrive. Manage collections, groups, favorites, people, and duplicate review. Synced metadata remains searchable while the desktop is offline; local and Apple Photos media access needs the owning device online with remote access enabled. OneDrive media can be accessed directly from the cloud. OAuth or Bearer API keys. Paid Cloud Access required; hosted visual search uses prepaid credits. Text-in-image search is semantic matching, not guaranteed exact OCR. Setup: https://organizewith.ai/en/guides/connect-ai-assistants
Fully capable of whole-file CSV/JSONL preflight against approved rules before CRM or database writes. Proven with a repeatable synthetic MCP demo: continue, block and warning outcomes, a duplicate at row 12,002, original-byte preservation and retry accounting. No mapping, repair or destination writes. Inspect the results and reproduce the workflow: https://mcp.contentsweep.ai/quality/demos/crm-preflight
111 tools for AI assistants, so an answer comes from a rule instead of a guess. 84 deterministic utilities. IBAN and VAT validation, cron parsing, regex testing, hashing, JWT decoding, conversion between JSON, CSV, XML and YAML, units, number bases, timezones and date arithmetic. Eleven of them encode Dutch rules that a model tends to get wrong: AOW pension age, inheritance and gift tax, unemployment benefit duration, notice period, severance, the 30 percent ruling, holiday allowance, mileage allowance, and public and school holidays. Five more generate test data that is structurally valid and belongs to nobody: BSN, IBAN, BRP person records, UPA pension files and document numbers. 14 render tools that return a hosted file. HTML or a live URL to PDF, full page screenshots, QR codes, PDF merge and split, images to PDF, image resize, convert and compress, metadata stripping, PDF to DOCX and back. Plus read_page, which returns the readable content of a JavaScript rendered page as Markdown. 4 memory tools give an agent key-value state that survives between sessions, scoped to its own API key. 3 workflow tools list and run saved multi-step workflows on the caller's account. 6 AI tools for the jobs where a model is the right instrument rather than the wrong one: check a message for scam patterns, write a spreadsheet formula, turn a question into SQL, translate code between languages, improve a prompt, draft an email. Utilities and memory are free. Renders and AI tools have a free tier and credit packs. Workflows need an API key, because a workflow belongs to an account rather than to a key. Streamable HTTP at https://toolforte.com/api/mcp
AI UGC videos of your store's products: read a product, write 3 scripts, make the video.
CrowdOS lets AI agents run synthetic focus groups over MCP against census-calibrated panels that disagree. MCP on every plan including Free.
Turn a document or an AI draft into a publish-ready PDF, with an automatic cover, table of contents, pagination and your saved branding.
List, view, create, edit, delete, comment on, and see the history of Laraue Boards issues.
AMZScout Skill + MCP gives AI agents live access to real Amazon marketplace data across 14 Amazon marketplaces. Analyze any ASIN, validate product ideas, research niches, compare competitors, discover profitable keywords, and build data-driven PPC strategies using trusted Amazon insights instead of AI assumptions. Works with Claude, ChatGPT, Cursor, and any other MCP-compatible AI client. To connect, you'll need an AMZScout API plan and authorize your account. Get access and view pricing here: https://learn.amzscout.net/amazon-product-api-for-ai-agents
ScanSing reads printed sheet music. Give Claude a PDF or a photo of a score and it gets back MusicXML, the format MuseScore, Sibelius, Finale and Dorico open. It is the recogniser inside the ScanSing app for choir singers, offered as a connector. Once a score is recognised, Claude can answer questions about it without recognising it again: - what the key, time signature, tempo and length are, and each part's range, clefs and lyrics; - one voice on its own, for example just the alto line of a choir piece; - the score or a part moved to another key, with notes respelled for the new key signature; - a MIDI file, one track per part, to listen to or rehearse with; - a short-lived download link to open the result in a browser or notation app. It handles PDFs up to 40 pages and PNG, JPEG, HEIC, TIFF and WebP images, can recognise selected pages of a long PDF, and can split a songbook into one MusicXML per piece. A file can be given as a web link or a small image; in Claude Code, a file on your computer is sent through a one-time upload link. Recognition spends pages from your ScanSing plan, so it is the only tool that is not read-only. Everything else works on the stored result and is free. The first connection with a new email comes with 20 free pages; paid plans start at $9 a month for 300 pages. Scores and results are deleted about an hour after recognition and are never used for training.
Live feed of insider, Congress and White House trades from public filings. Information only.
SEO analysis of your Google Search Console, Bing Webmaster Tools and GA4 data. Google sign-in.
Aya, Talpy's AI recruiter, in your assistant. Read jobs, candidates and evidence-backed interview scores; with write access, create jobs and send candidates to Aya's interview by WhatsApp or web link, in English, Spanish, German, French and Portuguese. See your plan and upgrade link. Hiring decisions stay human.
Redact personal data from text before your agent sends it to a model or stores it: names, contact details, ID numbers, financial and health identifiers, card numbers, plus any exact terms you add. Nothing stored, no third-party AI. Tools - redact_text: returns the redacted text and a count of what was removed, by type. Never the removed values. Options: restrict to particular data types, add exact terms to remove, choose the replacement style (a type label such as <PERSON> by default) and set a confidence threshold. - list_entity_types: lists the detectable data types. Free. Data handling - Nothing you send is stored. Text is processed in memory and discarded when the call returns. - No third-party AI. Text is never sent to OpenAI, Anthropic, Google or any other outside model. - Tool arguments are never logged. Only counts are kept: credits used, a timestamp and how many of each type were found. PDFs, including scanned pages, are handled by the REST API with the same key and credits. They aren't offered as an MCP tool because a file doesn't fit in a tool call. Pricing: 1 credit per call plus 1 per 1,000 characters. 10 free credits on sign-up, no card. Credit packs from $5; purchased credits never expire. Failed calls and repeated identical calls are free. Setup and API key: https://eleyed.com/mcp?utm_source=glama&utm_medium=directory&utm_campaign=listing
**Can AI actually read your page?** ChatGPT, Perplexity, Claude and Google's AI Overviews fetch pages very differently from your browser — no JavaScript, tight timeouts, and a robots.txt rulebook of their own. Lekta fetches a URL exactly the way they do and grades what survives, **A+ to F**. This is the technical half of **AEO** (answer engine optimization) and **GEO** (generative engine optimization): before a model can cite you, it has to be able to fetch you, parse you, and find one sentence worth quoting. **The loop this server was built for:** `Audit https://mysite.com/pricing with Lekta, apply the fixes it lists, audit it again, and show me the difference.` Your agent gets a graded verdict, a ranked fix plan with the exact markup to paste, and a diff that proves the change landed. Repeat until A+. **Four layers, 100 points:** **Access** 25 — do the ~17 AI crawler tokens get past robots.txt? **Indexability** 25 — how much content survives without JavaScript? **Answerability** 30 — is there a single quotable sentence an engine can lift? **Recency** 20 — can a model tell when this page was last true? **What this is not:** a rank tracker. Lekta will not tell you how often ChatGPT mentions your brand. It tells you whether your page can be read and quoted when it does — the part you can actually fix. **No black box.** Every finding cites its basis — an RFC, a vendor doc, or a dated measurement we ran. The engine is versioned with a public changelog: a score never moves without a published shift table. **Tools:** `lekta_audit` (fresh fetch) · `lekta_report` (cached read) · `lekta_fix_plan` (ranked, paste-ready) · `lekta_diff` (before/after) · `lekta_my_sites` Listing tools is open. Tool calls need a free key from lekta.dev/en/panel/api — send `Authorization: Bearer lekta_…` or `x-api-key`. Cached reads, fix plans and diffs cost nothing; only fresh fetches count against the daily limit. **Topics:** AEO · GEO · AI SEO · LLM SEO · answer engine optimization · generative engine optimization · AI crawler access (GPTBot, ClaudeBot, PerplexityBot, Google-Extended) · JavaScript-free indexability · structured data · content freshness
Deterministic validation, parsing, and conversion of regulated B2B payloads over MCP — IBAN/BIC, ANSI X12 healthcare EDI (837P/835/270/271/834), ISO 20022, GS1 barcodes, VAT/VIES, LEI, UDI, DSCSA, and CBAM. Returns typed JSON with structured validation errors.
Intelligence for your AI agents: what they need to know, at the moment they decide. NEXUS connects Claude Code, Claude, ChatGPT, Cursor and OpenClaw to one shared record of your decisions, rules and past incidents, so an agent doesn't repeat a costly mistake or undo what was already decided. What one agent learns, the others already know. Every item is graded (measured, reported or inferred), outdated facts are marked as superseded, and contradictions are flagged. Before an important action, agents can call antes_de_actuar to get the rules that apply. Remote server with OAuth. Free plan, no credit card: https://nexus.eblas.link
Official remote MCP server for Brazilian company data (CNPJ): lookup, filtered search, contacts and partners with masked CPF. 70M CNPJs, base of Aug 2026; updated monthly, with the base date in every response. https://cnpj.ia.br/?utm_source=glama&utm_medium=listing