Skip to main content
Glama
48,569 servers. Updated

"Coolify - An Open-source Self-hosting Platform" matching MCP connectors:

GET /v1/connectors – MCP directory API reference

Matching Connector Tools:

  • AEO and SEO research engine for your brand. Studies what gets ranked and cited on a topic, then builds content plans around what your brand can add. Tracks how AI engines mention and cite your brand against competitors, and ranks what to work on next. Requires a Hi, Moose account. Some tools need the desktop app open on a host computer.

    https://mcp.himoose.com/mcp
  • FlickDirect Inc’s free, read-only movie MCP server. It provides movie and TV facts, cast, available country-specific dates and ratings, production trivia, brief quote excerpts, site-wide news and reviews, CinemaCon reporting, interviews and eligible stored transcripts. Cinema United association and year-round exhibition reporting use articles; CinemaCon remains its separate annual convention. FlickDirect’s independent guide is https://flickdirect.com/cinema-united/; the official association site is https://cinemaunited.org/. Find published podcast shows and episodes, including bounded FlickRadio archive matching. Recent uploads from three verified FlickDirect channels retain healthy-feed results when another feed times out, with incomplete coverage explicitly reported. Streaming, soundtrack/player and published Amazon and Apple destinations remain supported. Retailer listings and daily deals are no longer supported. Longer-title recovery preserves original title words and requested year/media filters. The tools are search_flickdirect_content and get_flickdirect_movie_details. Cached search_fdmd and get_fdmd_movie calls remain compatible at the unchanged endpoint. Results retain canonical source links and distinguish missing matches, unavailable sources and ambiguity. Fetch time does not prove upstream currentness. No full articles, reviews, transcripts, scripts or photographs. Playback and tool selection depend on the AI host. Private request diagnostics expire within seven days. No FlickDirect account or API key is required.

  • US homeowner and property data for AI assistants. Find homes by solar, permits, roof, storms, value or location with the owner of record and household phones and emails; look up an address, phone, email, name or business; run lists of up to 1,000 rows. Results open as a spreadsheet you can copy or download. Free account with 100 lookups.

  • Deterministic AEO/GEO checks and a source-cited rulebook for AI search, for your agent.

    https://mcp.aeogeo.site/mcp
  • 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.

    https://seoquestionsbank.com/mcp
  • Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.

    https://mcp.jmrp.io/libgen
  • 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.

  • Search, inspect, and submit open-source VST 3, CLAP, LV2, and AU plugins in an unofficial registry.

  • Coupons and deals from many stores. Built on Feedico data. It is not an official Feedico server.

    https://coupossum.com/mcp
  • 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.

  • 239k open jobs from 3,519 company career sites on 71 hiring platforms (Workday, Greenhouse, Lever, Ashby and more), with duplicates merged and links to the original posting. Read-only. Free tier without a key: 200 tool calls a day per IP. Send a JobSweep API key as Authorization: Bearer <key> for a paid plan's limits (https://jobsweep.works/pricing).

    https://jobsweep.works/mcp
  • 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".

    https://mcp.ctlogs.dev/mcp
  • Explore 1,000,000+ active job postings worldwide — in the United States, Europe and other international markets. This public search connection offers five read-only tools: discover supported countries and work filters, find employers, search active jobs, read full postings and inspect market totals. Search and original application links are free. Find full-time roles or remote, part-time, contract and flexible opportunities for extra income. Use declared weekly hours and schedule filters; unknown hours are not invented, and remote does not automatically mean worldwide work eligibility. Check the full posting before applying. Try: “Show supported countries and filters, then find remote part-time jobs with at most 20 declared hours per week”, “Find employers hiring PHP developers in my eligible countries”, or “Open the full posting and original application link for this job”. The Glama discovery profile is deliberately limited to jobs:read. It cannot access a CV, modify a tracker, spend AI credits, send applications or buy anything. The wider roTEAMnet platform also offers confirmed-fact CV preparation, fit analysis, document export and application tracking through separately authorized private tools and the website. A verified free account includes 15 one-time AI credits for those optional workflows. Connect using OAuth. Permissions are scoped and revocable. Interface: English, German, French, Romanian, Dutch, Italian and Spanish. Setup and examples: https://roteamnet.com/en/ai-agent?utm_source=glama&utm_medium=connector_directory&utm_campaign=connector_launch#first-result

    https://roteamnet.com/api/mcp
  • 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.

  • Open tech roles in Egypt, Saudi Arabia and the UAE, from each company's careers page.

    https://techny.dev/mcp
  • Free read-only discovery of owner-published finance agent profiles and source-linked discussions.

  • Find European public tenders and EU funding calls inside your AI assistant. Search by topic, country, procurement category and deadline. Examine opportunity details and source notices, then follow structured bid qualification workflows. For bid managers, business development teams and funding consultants. Free during beta; sign in with your email. --- Europos viešieji pirkimai ir ES finansavimo kvietimai jūsų DI asistente (Claude, ChatGPT ir kt.). Ieškokite pagal veiklos sritį, šalį, pirkimo kategoriją ir terminą. Peržiūrėkite galimybių duomenis bei pirminius skelbimus ir naudokitės darbo eigomis, padedančiomis įvertinti, ar verta dalyvauti. Pirkimų pasiūlymų rengėjams, verslo plėtros komandoms ir finansavimo konsultantams. Beta laikotarpiu nemokama; prisijunkite el. paštu.

    https://mcp.victano.com/mcp
  • Search ~656k Polish court rulings and ~165k acts, read provision text, find leading rulings for an article by citation authority, check whether a cited case number exists, and get outcome statistics. Works without an API key (rate-limited).

    https://api.prawnet.pl/mcp
  • Search 367k+ verified businesses; earn cashback when an agent routes a real purchase.

  • One key and one prepaid balance for 3,051 pay-per-call tools from 99 providers for AI agents: search, maps, shopping, market data, web pages, images and more. Agents find tools by job, see the price before running, and pay per call. Failed calls are free. Sign in with OAuth, no API key to copy. Sign-up is open to everyone.

    https://mcp.1toolring.com/mcp
  • 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."

    https://mcp.arcmira.com/mcp
  • Find and check companies across Africa: registries, sanctions lists and company websites, with every answer linked to its source. Anything that spends credits is proposed first and waits for your approval.

  • Free MCP tool for AI agents to search French public tenders and procurement opportunities using official BOAMP open data. Find notices by keyword, access source references, and verify tender details and deadlines.

  • 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.

    https://crawlcheck.io/mcp
  • 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.

    https://mcp.int-tech.solutions
  • Decision-ready research brief audit, delivered per API call as an atom service on Conduit Atoms.

  • Get every open job from official Greenhouse, Lever, Ashby, Workable boards, by Magnova

  • Search ~1.4M open jobs from 24k company career boards: Greenhouse, Lever, Ashby, Workday and more

    https://ats-jobs.mcpize.run/mcp
  • Search open jobs from company career sites by the country you can apply from, remote or onsite.

    https://workfinds.app/mcp
  • Search open tech jobs from company career pages by role, level, country, workplace and pay.

    https://lazee.dev/mcp
  • Search 239k open jobs from 3,519 company career sites. Free tier; an API key raises limits.

    https://jobsweep.works/mcp
  • Claim verification fact check stamp, delivered per API call as an atom service on Conduit Atoms.

  • 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.

    https://mcp.reelrecs.com/mcp
  • 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.

    https://trademarkscreen.com/mcp
  • Trend data, an interactive Trend Radar and ad-targeting dry runs for AI agents. Read-only.

    https://api.trendsagi.com/mcp
  • Search and compare public hosting-provider facts with sources and explicit unknowns. Three anonymous, read-only tools find published providers, inspect recorded services, price ranges, review availability and eligible uptime, and compare providers in the same hosting category. Public facts cover Free and paid providers with alphabetical discovery. Public beta. Setup and evidence limits: https://hostveritas.net/ai/hosting-research

    https://hostveritas.net/mcp
  • Search and compare public hosting-provider facts with sources and explicit unknowns.

    https://hostveritas.net/mcp
  • 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/

    https://mcp.xfix.ai/mcp
  • Startup MRR lookups: search, history, leaderboards. Each figure labelled verified or self-reported.

    https://showmrr.com/api/mcp
  • Poems for a mood, a situation or an occasion, with poets, analyses and plans to learn by heart.

    https://poemship.com/mcp
  • 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.

    https://iinventedlight.com/mcp
  • 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.

    https://evuun.com/mcp
  • Web analytics expert for AI agents, built on your existing GA4 tracking: query traffic, sources, campaigns, pages, events and conversions, run funnels and user-path reports, rerun saved reports, and get tracking install snippets and setup audits. Works with d8a.tech Cloud and self-hosted deployments.

    https://app.d8a.tech/mcp
  • 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

  • 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

    https://mcp.myfaithfuel.app/mcp
  • 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

    https://cotlet.dev/mcp/v1/okendo
  • 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.

    https://moonshotlab1.com/mcp
  • LinkedIn MCP server for ChatGPT, Claude and any AI agent: create post, comment on post, send message, send connection invitation, search people, search companies, list connections and read conversations in your own LinkedIn account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to LinkedIn yourself; Cotlet does not store your password and you need no LinkedIn API key. About the official LinkedIn API: LinkedIn has an official API, but most of it needs an approved application (checked 6 Nov 2026). The open Share on LinkedIn permission lets an app post, comment and like on behalf of a member. Setup and FAQ: https://cotlet.dev/integrations/linkedin-api-mcp-server

  • Search open Spanish public-sector tenders, updated daily, and estimate an offer. Read-only.

    https://mcp.bidalto.com/mcp
  • UluP Nexus is a curated discovery platform for independent software, apps, and games. Its free, read-only MCP server lets AI assistants search manually reviewed projects by keywords, categories, language, and pricing. Discover indie creations beyond mainstream platforms, with no account or API key required.

    https://nexus.ulupstudio.com/mcp
  • Turn an English food description into an EFSA FoodEx2 code.

  • Discover architectural projects, buildings and architects worldwide, and find experienced architectural photographer for museums, cultural buildings and international commissions. Architecture Researcher provides project information, locations, published photographic credits, original source links and guidance on photographic attribution.

  • Read-only cited financial datasets, bounded research queries and source diagnostics.

  • SpyFu MCP server for ChatGPT, Claude and any AI agent: find backlink prospects, search business leads, create scheduled PDF report, get Site Audit issues, compare competitor keywords, list SEO keywords, add site to My Sites and get ad history in your own SpyFu account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to SpyFu yourself; Cotlet does not store your password and you need no SpyFu API key. About the official SpyFu API: SpyFu has an official REST API for research data and a remote MCP endpoint (checked 23 Oct 2026). The API is included with Pro-level plans and above, billed per row returned. Setup and FAQ: https://cotlet.dev/integrations/spyfu-api-mcp-server

    https://cotlet.dev/mcp/v1/spyfu
  • A remote MCP server and REST API for book data. Ask your AI assistant which order to read a series in, which series a book belongs to, or what an author has written, and get answers from a catalog of 60,000+ series and 15,000+ authors, each linked to its page. Five read-only tools; listing tools needs no key, calls need a free API key (Authorization: Bearer) from https://www.listofbooks.net/developers.

  • Mautic MCP server for ChatGPT, Claude and any AI agent: list contacts, merge contacts, change contact segments, set Do Not Contact, create segment, get email stats and activate or pause campaign in your own Mautic account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Mautic yourself; Cotlet does not store your password and you need no Mautic API key. About the official Mautic API: Mautic has a full REST API but no official MCP server (checked 23 Oct 2026). The API is off until an admin switches it on under Configuration > API Settings, and calls need OAuth2 or basic auth set up on that instance. Setup and FAQ: https://cotlet.dev/integrations/mautic-api-mcp-server

    https://cotlet.dev/mcp/v1/mautic
  • ManyChat MCP server for ChatGPT, Claude and any AI agent: list contacts, get contact profile, read inbox conversation, send inbox message, add tag to contact, set custom field, list broadcasts and send broadcast in your own ManyChat account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to ManyChat yourself; Cotlet does not store your password and you need no ManyChat API key. About the official ManyChat API: Yes, but only on the Pro plan or higher, and it is narrow (checked 5 Nov 2026). ManyChat has a REST API with a Page API and a Profile API that reads and sets contacts, tags and custom fields, sends content and triggers an automation for one contact. Setup and FAQ: https://cotlet.dev/integrations/manychat-api-mcp-server