"Services that provide internet connectivity" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Grabbit gives AI agents eyes on the web through a hosted MCP server. Send a public URL and get a pixel-perfect hosted image back, without maintaining Chromium, Playwright, or a browser fleet. Capture a full page, exact viewport, or single CSS selector as PNG, JPEG, or WebP. Grabbit handles cookie and consent banners, waits for JavaScript-heavy pages, blocks private and internal URLs, supports safe retries with idempotency keys, and delivers async results through signed webhooks. Completed captures include a CDN URL. Connect with OAuth 2.1 or an API key. Grabbit works with Claude, Cursor, Codex, and any MCP client. Live captures cost $0.002 each. The $50 annual plan includes 25,000 prepaid credits that never reset or expire. Free test keys return placeholder images, so you can wire up the integration before paying. Home: https://grabbit.live Docs: https://grabbit.live/screenshot-api Built by BrainGrid.
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 eleven read-only tools. Changes and context: • latest_changes — Browse the newest published changes, newest first, 20 per page. • search_changes — Find changes by keywords such as a company, country, or subject, ranked by relevance. • get_change — Read one change in full: summary, scores, main subject, and the sources that reported it (outlet, link, date). • country_heat — Country-level Change Heat: how much verified change happened in each country (amount of change, not danger), with history windows set by the plan. • release_calendar — Scheduled economic indicators, central bank decisions, company earnings, and other upcoming releases. • company — Look up a company by its AiSeek slug, or search companies by name, with profile, listings, and recent changes. • latest_brief — The latest daily or weekly briefing. SeekTrace evidence records: • get_receipt — The evidence receipt behind a change: how firmly each statement is supported, which evidence it rests on, when it was recorded, and its revision history. • verify_receipt — Recompute a receipt's fingerprint to confirm the record has not been altered since it was issued. • change_history — A change as it was known on a past date, kept apart from what is known now. • recent_corrections — Recently corrected evidence and the published changes it affected. A receipt is a record of how AiSeek assessed the evidence at a given time, not a certificate that a statement is true. Sources that merely repeat one another count once, and a source that cannot be shown to be independent is never presented as independent. Responses carry source names and links, never quoted passages. AiSeek supports English, Simplified Chinese, and Japanese, making it suitable for multilingual research, global monitoring, market intelligence, and cross-border information discovery. All tools are read-only. No trading, account modifications, or external actions are performed. Tool calls require an AiSeek API key, sent as a Bearer token or in the x-api-key header. Usage limits and history depend on the account's plan: the Free plan includes 100 MCP calls a day, and history goes back 7 days on Free, 30 on Pro, 90 on Intelligence, and 180 on Developer. MCP Endpoint: https://aiseek.dev/api/v1/mcp Developer Documentation: https://aiseek.dev/en/developers#mcp
ScriptGrain makes ChatGPT, Claude and the rest better at being you. Connect it and your assistant can build a voice profile from writing you’ve already done, draft in that voice, and score any text against it from 0 to 1. The profile covers 45 attributes in eight groups: lexical, syntax, tone and register, rhetoric, punctuation and format, function words, content patterns, and quirks and cadence. On-voice drafts typically score 0.85 to 0.95. Clearly off-voice text scores below 0.45.
Stop juggling chat windows. Complete your project in one seamless conversation. Marvnor is a proprietary, hosted MCP/API service that gives your AI agent persistent project memory. Your agent saves confirmed or evidence-backed requirements, decisions, and changes. For each new question, Marvnor retrieves relevant saved records, verifies claims against them, and flags conflicting information for your confirmation. Records can be corrected or deleted as your project evolves. Spend less time repeating the background and untangling old decisions. Pass only the current question and relevant results to your model to reduce repeated history in its input and keep your project moving.
The official Model Context Protocol (MCP) server for RubiConnect — the enterprise platform for RCS (Rich Communication Services) and WhatsApp Business messaging. Connect external AI assistants (such as Claude Desktop, Claude.ai, Cursor, ChatGPT, and autonomous agent pipelines) directly to your RubiConnect messaging workspace to check phone reachability, send rich cards and carousels, trigger bulk campaigns, inspect live inbox conversations, and query messaging analytics.
A calorie MCP that looks up calories and macros from a 4M+ food catalog, not model guesses.
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.
Hear it from nimo, not your customers. Monitoring that tells you the fix, not just the alert: uptime, Core Web Vitals, cron check-ins, plus Journey Watch for your signup and checkout flows. Free one-off checks, no account needed.
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.
An MCP for marketers that gives agents tools for SEO, AEO, socials and ads data. Generous free tier; works in Claude, ChatGPT, Cursor and other MCP clients.
Remote MCP that evaluates one public HTTPS URL for WebMCP readiness: intent, tools observed, what to add, what never to expose.
Operate a real LinkedIn account from your AI agent. 52 tools for the inbox, invitations, network, profiles, Sales Navigator search in plain language, posts and engagement; six playbooks served as MCP prompts that preview before they write; daily quotas enforced server-side; structured errors; idempotent writes; signed webhooks when a prospect replies or a connection is accepted. LinkedIn only. 7-day trial, no card.
Turn finished agent work into a shareable, updatable web page that opens in WeChat. OAuth required.
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.
**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
IPStack MCP Adapter turns IPStack's REST APIs into Model Context Protocol tools so any MCP-compatible client can call them directly in conversation. The first release ships IPStack IP geolocation and security lookups (single IP, caller's IP, and bulk). Additional APILayer services are added by registering them in a single config file, so the catalog grows without client-side changes.
Publish in seconds, get the audience, start monetization, get all analytics — without leaving your agent. Playgama MCP is a remote MCP server for game developers. Point Codex, Claude Code, Cursor or VS Code at it and your agent works inside your Playgama developer cabinet: it creates a game and fills in the form, uploads a build and polls until the engine analysis is done, uploads covers in the exact sizes the form requires, edits the in-app catalog and leaderboards, gets a QA Tool link, and publishes a sandbox — a public link anyone can play, with no moderation step. It can also bring the first players to that sandbox through Playgama DSP, with the first run per game free. 22 tools, 11 of them read-only; every write is annotated as destructive so your client asks first. Submitting to moderation, deleting and payouts are deliberately left out: the agent prepares everything, a human presses the button. Authentication is OAuth 2.1 with dynamic client registration — there is no token to copy. The client opens a browser on first use, and connected agents are listed and revocable in the cabinet. After the link is live the game takes its first players from the Playgama network, and Playgama DSP can send more the same day (beta). Once it clears the session threshold you can switch on advertising — Playgama Ad serves rewarded, interstitial and banner formats through one JS SDK (access by request). Playgama Wrap turns the same game into a standalone site on your own domain with player accounts, in-game purchases and indexable SEO pages (early access), and Playgama Bridge SDK gives one API for ads, leaderboards, payments and platform SDKs when you publish across platforms. Playtime, retention and revenue reports are in the developer dashboard, and payouts start at 100 USD. Product page: https://playgama.com/mcp/ Docs: https://wiki.playgama.com/playgama/mcp Tools reference: https://wiki.playgama.com/playgama/mcp/tools Connected agents: https://developer.playgama.com/mcp
Connect your AI assistant to Signed and ask about your angel investing in plain English: how the portfolio is doing, what distributions came in this year, what’s sitting in the pitch queue. It's a view into the startups that you've invested in (or are thinking of investing in!)
Persistent knowledge graph for AI-augmented teams. Store decisions, findings, and standing rules across agent sessions with semantic search and typed connections. Includes cross-session memory, audit trail, workspace isolation, and secret detection. Built for teams running agents that need to remember. Free until launch with team tier as default, anon trial available.
Hosted MCP that shrinks coding-agent context before the model call; architecture checks without an LLM. Zero data retention.
