"An overview of penetration testing (pentest)" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Hosted MCP server from TwitterAPI.io that gives AI agents read-only access to Twitter/X data. 12 tools: tweet search with X operators, user profiles, a user's latest tweets, followers and followings, replies, quotes, retweeters, mentions and trends. Connect at https://mcp.twitterapi.io/mcp with a TwitterAPI.io API key or account sign-in; usage is paid per result returned. Separately, TwitterAPI.io also offers x402 pay-per-call HTTP endpoints (tweet search, user info, a user's latest tweets) paid in USDC on Base or Solana with no account or API key; see https://docs.twitterapi.io/x402-pay-per-call. The MCP server itself uses an API key or sign-in.
teas.co.uk is an independent UK online tea shop. Its MCP server lets AI assistants search about 400 teas, herbal and fruit infusions and hot chocolates from 40 brands, compare them, find recipes and offers, quote delivery and build a basket, then hand over a secure checkout link: the customer always pays on teas.co.uk. No sign-in is needed to shop. Customers can optionally link their teas.co.uk account (OAuth) for orders, tracking, repeat deliveries, reward points, returns and invoices.
Searchable catalog of 74 agent-ready APIs and tools. Search by task, get pricing model, agent controls and a tracked link for each tool, or list categories. Read-only, no auth.
Search a curated library of organic TikTok and Instagram Reels videos made by real businesses (videos that spread without ads), filtered by industry, business type, funnel job (awareness, branding, sales), format and what the shoot takes. Read a video's breakdown: why it worked, its hook, its call to action and how many viewers asked where to buy. For marketing agencies, creators and businesses planning short-form content. Requires a SeedReel Grow or Harvest plan; sign in with SeedReel (OAuth).
Search, inspect, and submit open-source VST 3, CLAP, LV2, and AU plugins in an unofficial registry.
Nutrition data for AI agents and LLMs, powered by Edamam’s database of 1,000,000 foods, including 680,000+ with UPC codes. Lookup via natural language and barcode at low cost and low latency. Highly accurate, deterministic data covering macro and micronutrients, allergens, and lifestyle diet tags.
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."
Search a library of film, commercial and music video frames, then build moodboards, boards and slide decks in Draftt from your AI assistant. Save references, organize them with your team and present them.
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
Fetch the transcript of any YouTube video (plain text or timestamped segments, in any available caption language), search YouTube for videos and channels, list a channel's uploads, Shorts, playlists and community posts, search inside one channel, and list every video in a playlist. Hosted Streamable HTTP server from getyoutubetranscript.com; sign in with OAuth or an API key. Credit-based: one credit per successful call.
Lets AI agents search an Arabic SEO knowledge base of 85+ problems and read the full step-by-step fix for each one, with the source URL to cite.
Gives AI agents read-only access to the ClickHelp user manual, so they can answer questions about ClickHelp, a help authoring tool, from its current documentation. Agents can search the manual, navigate its table of contents, and read topics. No authentication required. This is the Published Docs MCP Server that every ClickHelp portal can enable for its own public documentation. Readers of those portals connect through the Connect with MCP block on the portal itself, not through this listing.
Paste an error from a Supabase, Lovable or Bolt app and get the matching step-by-step fix guide.
Coupons and deals from many stores. Built on Feedico data. It is not an official Feedico server.
Search the official docs of Claude Code, Cursor, OpenAI Codex and MCP, refreshed daily.
Public company research with 9 focused tools: technology, hiring intent, open jobs, job changes, Google Ads and published contacts. Get a qualifying four-signal company profile for $0.03, plus breakout_summary growth estimates. Start with the free labeled example.com sandbox, 10 free successful calls per agent per UTC day (subject to a shared network ceiling), or an eligible 25-call trial. Setup: https://gethirepulse.xyz/?ref=glama-b2b#start-b2b . Reconnect to https://gethirepulse.xyz/mcp for all 27 tools, including batch and footprint research. Growth signals are estimates.
Zero-PII, read-only CRM and revenue intelligence MCP server for 3-dimensional lead intent scoring, natural language lead search, pipeline overview, and multi-channel ad attribution (Meta, Google Ads, WhatsApp).
Free directory of MCP servers and x402 APIs for AI agents. Find them, or list your own in one call.
Polish legal data for AI assistants: full-text search across 2.94M+ court rulings (common courts, Supreme Court, Constitutional Tribunal, KIO, NSA/WSA), statute text and version history from the official ELI register (164k+ acts), rulings citing a provision and citations between rulings, a citation verifier for case numbers, case-outcome and duration statistics, KIS tax interpretations, CJEU rulings applied in Poland, UODO decisions, KRS company lookup, court competence, official bank accounts and legal calculators. Works without an API key (daily limit).
ctlogs.dev searches the public Certificate Transparency logs, where every publicly trusted TLS certificate is recorded. Connected to it, an assistant can answer questions such as "which subdomains does example.com have", "who issued the certificates for this name" or "which domains does this company hold certificates for".
Everything about World of Warcraft: Forever, in the chat app you already use. Anything you'd look up is already in your chat. Close your other tabs. Why thott.bot? - Everything, connected. Quests, items, recipes, NPCs and maps are linked: what a quest needs, where that item drops, where you turn it in, what it crafts. Your AI gets the whole picture in one place, not scraps from dozens of random sites. - Current to the minute. Every new build, patch and hotfix reaches thott.bot within minutes of landing, even the silent ones. - Straight from Blizzard. Game facts come from Blizzard's own files and posts, not old guides or forum guesses. Community guides are labeled as such. What it knows: - Your characters: link Battle.net and your AI knows the characters you actually play, their gear, talents, quests and more, updated every time you log out. - Patch notes and changes: every build and hotfix, and exactly what each changed. - Quests and leveling: every quest, its chain, route and rewards, and leveling guides. - Talents and builds: the builds players run right now, counted daily from millions of real characters at every level, every spec's talent pick rates, and every talent change. - Spells and abilities: every spell and ability, and every change to each. - Classes and races: every class, race and racial, and what Forever changed for each. - Items and gear: every item and item set, where it drops and who sells it. - Crafting and professions: every profession, recipe and reagent, what each reagent makes, and profession leveling guides. - Auction house: live prices on every WoW Forever auction house, hourly. - The world: zones, maps, flight paths, dungeons, raids and bosses, battlegrounds. - Collections: mounts, pets, toys, achievements, reputations and holidays. - Interface and addons: every setting, key binding and chat command, the addon API and banned addons. - Blizzard news: news and developer posts (blue posts) from the official forums. In ChatGPT and Claude, ask to see it: your characters' sheets with the gear and stats they logged out with, the game's own tooltips, clickable talent trees, quest chains, maps and before-and-after cards. For every WoW Forever player, from first-timers to theorycrafters and addon developers.
Find movies and shows for tonight through current trends, mood, viewing and rating patterns, and streaming options. Public discovery works without a ReelRecs account. Connect an account for saved taste, rated-title history, bookmarks and accepted Watch+ groups.
Search extracted newspaper articles from the Library of Congress, 1736-1963. Subscription required.
CheapCarRent search. A read-only MCP server that looks up current car rental offers on CheapCarRent. Results are one page of up to 8 offers, with a link to the offer on https://cheapcarent.com. Prices are not a guaranteed quote.
Grounded search over chinaready.co — practical guides for launching software in Mainland China (ICP filing, app-store publishing, China cloud regions, payments). Three read-only tools: hybrid search, topic catalog, and full articles as Markdown. Every result carries an absolute source URL so answers can be cited. Free, no account, no keys.
Public directory of UK medical cannabis clinics, pharmacies, products and strains.
Search Fragments is the gate before your agent answers. When a user half-remembers something your agent can't confidently place, one call returns a verdict: ORIGIN_OF_TRUTH (found and evidence-checked, with sources), PARTIAL_ORIGIN (leads worth following, not an answer) or NOT_REACHABLE (our search reached nothing; not a claim it can't be found). Your agent answers and cites, keeps looking, or says it can't place it, instead of inventing. Free, no signup. Also: verify_claim (check a specific factual claim against current sources) and submit_resolution_feedback.
Now part of GAIP Witness: tests supplier claims and compares them with published metadata.
A growing catalog of free data sources for AI agents, updated daily, plus MCP server audits.
Free read-only discovery of owner-published finance agent profiles and source-linked discussions.
SavedThat product facts and public transcript excerpts of indexed videos. No sign-in.
Search 367k+ verified businesses; earn cashback when an agent routes a real purchase.
Real-time Google Flights fares for agents. Three things people do with this server. Scan for deals: one call takes a date range and a list of destination airports, expands every combination server side, and returns each fare with Google's own low, typical or high verdict. Put live search in your app: flat JSON with a bookable link on every result, and round trips priced as paired legs. Run a 24/7 AI travel agent: add the server, sign in with Google, and schedule it. No ads, no sponsored content. You bring your own RapidAPI key, so every search is billed to your plan and never to anyone else's. Add https://flights.flightpowers.com/mcp , click Sign in, sign in with Google, and paste your RapidAPI key once on the page that opens. Scripts and clients without a sign-in button send the key as x-rapidapi-key on the same URL.
Check what AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Googlebot) receive from any website, graded A to F, and get a signed, offline-verifiable verdict before an agent reads, cites, connects to or buys from a site. Covers robots.txt and content rights, site safety, MCP server checks and crawler-log verification.
Hosted, read-only MCP server for security events from the news: protests, strikes, crime, terrorism, accidents, natural hazards and political unrest. Search by country, address, a point plus radius, category and date. Connect with OAuth or an API key from the console at console.int-tech.solutions. The free plan is 50 requests a month and resets each month.
Decision-ready research brief audit, delivered per API call as an atom service on Conduit Atoms.
Free, no-key search of PubMed, FDA drug and device records and ClinicalTrials.gov, with citations.
Search 239k open jobs from 3,519 company career sites. Free tier; an API key raises limits.
Claim verification fact check stamp, delivered per API call as an atom service on Conduit Atoms.
A fast first-pass screen against the USPTO federal register — sound-alikes, look-alikes, and same or related classes, in plain English. Below are all Tool descriptions 1. screen_trademark Screen a brand name against the USPTO federal register. Read-only. Use this FIRST for any name. Returns JSON with a plain-English risk verdict (HIGH / MEDIUM-HIGH / MEDIUM / LOW), ranked conflicting marks (each with sound/appearance similarity, class relatedness, live/dead status, owner, serial), and the data-as-of date. Pass format "csv" to get the same results as a spreadsheet (one row per hit) instead of JSON. Limited to 100 screens/day on this server. SCREEN ONLY — not a clearance opinion, not legal advice. After this, use check_global_marks for EU/UK, check_domains for the domain, and watch_mark to monitor the name. 2. trademark_status Authoritative status for ONE mark you already know, by serial number (sn12345678) or registration number (rn1234567). Read-only. Returns JSON with the mark's live/dead status, owner, classes, goods/services, and filing/registration dates. Uses TSDR if a free key is set, otherwise the public Trademark Search record. Use when you have a serial/registration number (e.g. from a screen_trademark hit) and want the authoritative record for that one mark — not for searching by name (use screen_trademark for that). 3. suggest_classes Suggest the Nice classes (1-45) a goods/services description falls under, with reasons. Read-only, pure reasoning — no live data, no register lookup. Input goodsDescription is what you sell (e.g. 'music streaming app'); the more specific it is, the better the classes. Returns JSON with the suggested classes (each with its label), the classes assumed from your wording, and the reasons. Use before filing to pick classes (each class costs $350 to file), or to feed classes into screen_trademark / check_global_marks. Always verify against the USPTO ID Manual for the exact pre-approved description. 4. analyze_name Analyze a brand name's strength WITHOUT checking the register — read-only, offline, deterministic (same name always gives the same result). Returns JSON with the distinctiveness spectrum (fanciful / arbitrary / suggestive / descriptive / generic), phonetic collisions to check, and a checklist (other-language meanings, common-law use, state registers). Optional goodsDescription (what you sell) sharpens the analysis: a descriptive word for those goods scores weaker than the same word for unrelated goods. No live data and no register results — pair it with screen_trademark, which checks the actual federal register. Use this to judge how protectable a name is; use screen_trademark to judge whether it conflicts. 5. compare_marks Compare two specific names side-by-side. Read-only, deterministic — the same two names always give the same scores. Returns JSON with visual similarity, Jaro-Winkler, phonetic (Soundex) similarity, an overall confusion score (0-1), and a risk level. Use to compare two names you already have in mind; use screen_trademark to discover conflicts for a name across the whole register (it also weighs classes and live/dead status, which this does not). Does not assess meaning, commercial impression, or class relatedness. 6. check_domains Check whether a brand name is free to register as a domain. Read-only. Returns JSON with one result per TLD (registered / available / unknown) — all TLDs are checked in parallel. Uses RDAP (the registry's own data, free, no key): 404 = not registered; 'unknown' = the TLD has no RDAP service. Covers .com/.io/.ai/.co/.app/.dev/.net/.org by default, or a custom TLD list. A free domain does NOT mean the trademark is clear, and a taken domain does not block the trademark — domains and trademarks are separate rights, so use screen_trademark for the trademark check. 7. check_global_marks Check a brand name against EU + UK trademark registers via TMview (EUIPO-operated, offices EM + GB). Read-only. Returns JSON with the EU/UK hits scored the same way as screen_trademark, plus the classes used. Use AFTER screen_trademark when you also sell in the EU/UK; the US screen is unaffected if TMview is down. BEST-EFFORT: TMview has no published API and resets connections from plain HTTP clients — when it will not answer, this returns { checked: false, reason } with a manual link instead of failing. A clear EU/UK result is a signal, not clearance. 8. request_watch_code Send a 6-digit verification code to an email address, for watch access. This sends an email (the only side effect) but creates nothing. Call it BEFORE list_watches, unwatch_mark, or attaching an email to a watch with watch_mark. The code expires in 10 minutes (5 tries); verifying it returns a 60-minute session token you can reuse for the other watch tools. A code is sent even if the email has no watches, so the response never reveals whether an address has watches. 9. watch_mark Start watching a mark for NEW confusingly similar filings. This CREATES a watch (a side effect — it stores the watch and sends a confirmation email with the stop link). Runs a baseline screen first — everything already on the register is marked seen, so you are only alerted on filings that appear AFTER the watch starts. Returns JSON with the watch id, its classes/threshold/schedule, and the baseline hits (for context). Check for new filings with check_watches, or let the scheduled checker run (daily by default, or weekly / every N days if you set a schedule). An email is required — it is the watch's owner, and the digest goes there (needs RESEND_API_KEY on the server; without it the watch still works and records hits, and alerts start once email is switched on). The email must be verified first — call request_watch_code, then pass the email and code (or the session token); without verification the watch is refused, so nobody can attach someone else's inbox. SCREEN ONLY — not clearance, not legal advice. 10. list_watches List the watches you ALREADY have — a read-only view, it does NOT check for new filings. Returns JSON with each watch's mark, classes, threshold, schedule, created/last-checked dates, total alerts so far, and the most recent new hits. Use this to see what you are watching; use check_watches to actually run a check for new filings right now. Private to one email — pass the email and the 6-digit code from request_watch_code, or a session token from a previous verification. No email addresses are ever returned. 11. unwatch_mark Stop watching a mark. This DELETES the watch (a side effect — it is removed and will no longer be checked). Returns JSON { removed, ok: true }. If the watch has an email, you must prove you own it — pass the email and the 6-digit code from request_watch_code, or a session token. A watch with no email needs no verification. 12. check_watches Run a check for NEW filings RIGHT NOW (on all your watches, or one by id) — this actually queries the register, unlike list_watches which only shows what you have. Returns JSON with only the filings that appeared since the watch started / last check, scored by risk. Use this when you want fresh results immediately; the scheduled checker also runs daily at 09:00 on each watch's own cadence (daily by default). SCREEN ONLY — not clearance, not legal advice.
Search pending delete and recently dropped domain names from Claude, ChatGPT or any MCP app: drop times, Rank, Linking Domains and every filter of the advanced search.
Trend data, an interactive Trend Radar and ad-targeting dry runs for AI agents. Read-only.
GRC & compliance directory for AI assistants: free, read-only search of compliance audit firms (SOC 2, ISO 27001, PCI DSS, HITRUST, FedRAMP, CMMC) and GRC/security AI agents, cross-checked against official registries. By Heritage Services, publisher of theagentindex.io. Not affiliated with other projects named Agent Index.
SEO and market data: SERP, keyword volume, backlinks, site audit, schema, Maps, reviews, traffic, ChatGPT visibility, Amazon, jobs.
AEO, SEO and AI shopping checks for any website. xfix checks whether ChatGPT, Claude, Perplexity and Google can find and read a site, and whether AI shopping agents can read an online store: AI crawler access, page text without JavaScript, product schema, AI search visibility score, AI Shopping Readiness Index lookup, and a Google Ad Grants website check. Read-only, no sign-in. Website: https://xfix.ai/ai-assistants/
Dated record of advertised Australian bank and lender rates, plus RBA curves. Read-only.
Compare prices across Spanish online stores and check whether a price is good against two years of price history. Search products, compare current offers by variant, seller and condition, check a store link, and read the usual price, minimum and maximum. Read-only, no account needed. Prices in EUR, checked within 48 hours.
Poems for a mood, a situation or an occasion, with poets, analyses and plans to learn by heart.
iinventedlight notes is a read-first MCP server for the public iinventedlight library: Cole Withington's notes and papers, plus openly licensed reference notes (CC BY, CC BY-SA, CC0 and public domain), and pages for corrow music and the Starweave app. Reading needs no account or key: list, search, read by section, ask a question, or browse a topic atlas. Agents can leave feedback or a correction without a key, and it stays pending until a person approves it. New notes need an access key and are reviewed by a person before anything is published. Feedback never changes a note's published text.
Which AI laws apply to an AI feature in a market: cited provisions, who they cover, dates, guards.
EVUUN is the layer where an AI agent's intent becomes a real-world transaction. When your agent says it's done, it's done: a named provider has confirmed, the price and terms are locked, and money moves only within what you approve. Ask for a hotel stay, a table at a restaurant, a local experience, a guide for the day, a curated plan from an independent host, or a flight. EVUUN finds the options, shows you the evidence and the terms, and holds the one you choose. Where a place has no online booking, EVUUN contacts it for you and brings back a confirmed offer. You review and approve on a hosted page you control. Afterwards, your agent can follow up on every arrangement: changes, cancellations, refunds and receipts all stay in one place.
European directory of freight carriers: find carriers by route, equipment and certificates.
Explore Scripture through an interactive Bible knowledge graph. Search Bible verses, discover cross-references and thematic connections, compare passages, access study notes, and visualize relationships between Scripture passages. Powered by the Berean Standard Bible with clearly distinguished source references, reviewed connections, and interpretive notes.v
AccuRanker MCP server for ChatGPT, Claude and any AI agent: add keywords, list keywords and ranks, add tags to keywords, add domain, add competitor, delete keywords, get keyword rank history and remove tags from keywords in your own AccuRanker account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to AccuRanker yourself; Cotlet does not store your password and you need no AccuRanker API key. About the official AccuRanker API: AccuRanker has an official API and an official MCP server (checked 23 Oct 2026). The Read API and Write API (both v4) come with API access at no additional cost, but need a developer and an API token. Setup and FAQ: https://cotlet.dev/integrations/accuranker-api-mcp-server
Free, read-only directory of 114 AI trading tools: broker MCP servers, market data APIs, bots and backtesters. Sourced facts on who can place orders and what safeguards exist; search, compare and check order gating for every broker MCP.
REVIEWS.io MCP server for ChatGPT, Claude and any AI agent: list reviews, reply to review, moderate review, tag reviews, list invitations, pause invitations, add to unsubscribe list and export reviews in your own REVIEWS.io account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to REVIEWS.io yourself; Cotlet does not store your password and you need no REVIEWS.io API key. About the official REVIEWS.io API: REVIEWS.io has a REST API, but only on the Plus plan, and no official MCP server (checked 23 Oct 2026). The API index lists reads of reviews, invitations and the unsubscribe list, queuing and editing invitations, and tagging reviews. Setup and FAQ: https://cotlet.dev/integrations/reviews-io-api-mcp-server
Postscript MCP server for ChatGPT, Claude and any AI agent: create segment, create campaign draft, schedule campaign, create keyword, reply to subscriber, get message analytics, find subscriber and stop campaign in your own Postscript account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Postscript yourself; Cotlet does not store your password and you need no Postscript API key. About the official Postscript API: Postscript has an API and an official MCP server, but neither builds or sends campaigns (checked 23 Oct 2026). The MCP server is read-only: it pulls campaign, automation, popup and shop-wide analytics on Pro and Enterprise plans and "cannot create, edit, send, or delete anything". Setup and FAQ: https://cotlet.dev/integrations/postscript-api-mcp-server
Okendo MCP server for ChatGPT, Claude and any AI agent: list pending reviews, publish review, reject review, reply to review, answer product question and get product performance in your own Okendo account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Okendo yourself; Cotlet does not store your password and you need no Okendo API key. About the official Okendo API: Okendo has an official API, but with limits (checked 23 Oct 2026). The Merchant REST API reads and updates reviews, replies, loyalty customers and webhooks, and Okendo's spec calls it available to enterprise customers. Setup and FAQ: https://cotlet.dev/integrations/okendo-api-mcp-server
EmailOctopus MCP server for ChatGPT, Claude and any AI agent: list campaigns, get campaign report, duplicate campaign, create segment, set campaign recipients, schedule campaign, send campaign and unsubscribe contacts in your own EmailOctopus account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to EmailOctopus yourself; Cotlet does not store your password and you need no EmailOctopus API key. About the official EmailOctopus API: EmailOctopus has a public REST API (v2) for lists, contacts, fields, tags, campaign reports and starting an automation for a contact, but no official MCP server and no API for creating, scheduling or sending a campaign (checked 20 Oct 2026). EmailOctopus states that it does not support API sending: all emails need to be created directly in the Dashboard. Setup and FAQ: https://cotlet.dev/integrations/emailoctopus-api-mcp-server
Agent car inventory index. Synthetic demo data, not real inventory, not an offer.