"The number 555" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Skavio LLC hosts 20 OAuth-protected Streamable HTTP tools for PDF, searchable OCR, invoice/receipt fields, audio and document workflows. Paid jobs debit company-scoped prepaid Skavio credits (1 USD = 1,000 credits), with quotes, max_credits caps and idempotent settlement. Only the company administrator can fund its wallet. Linked Agent Tools companies can buy Stripe card packs of USD 5-500 or use USDC at https://getskavio.com/agent-tools/dashboard.html. Processing OAuth and Agent Tools credentials are separate; never assume automatic wallet sharing. Four independent blockchain proof/DNS tools still require x402 native USDC. MCP endpoint: https://getskavio.com/processing/mcp ; Docs: https://getskavio.com/processing/docs/mcp/ ; Support: support@getskavio.com. No paid external card-to-MCP job E2E verified yet.
Sealgraf checks agent purchases against the owner's limits and seals a receipt anyone can check.
Read and edit shared mind maps from Claude, Cursor or any MCP client. Your AI assistant can search a map, add and rewrite nodes, link ideas and tidy the layout. Your team sees each change live on the canvas and can undo any edit from the map's history.
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.
Bring professional data and tools to the AI you already use. QVeris helps AI assistants, products, and workflows find services, review supported scope, call them, and audit usage.
Live data on millions of companies worldwide, read from their own websites, job boards and public registers: what they do, where they operate, their tech stack, funding rounds and investors, and how fast they grow. Find companies by industry, country, size, founding year, funding stage, investor or technology; get lookalikes of any company with the reasons; research one company in depth; search verified job postings and pay statistics. Read-only, OAuth sign-in; compact lists are free up to 50 a day, full profiles and statistics are paid from Alion credits.
Tokfluence's hosted MCP server connects Claude, ChatGPT, Cursor or any MCP client to the Tokfluence TikTok creator index. Give your agent a brief and it plans the search, pages through keyword and structured results, reads creators' latest posts as evidence, ranks the pool, and saves the list to your Tokfluence dashboard. For niches the index doesn't cover yet, it can start a crawl (it asks you first and shows the credit cost) or hand the brief to Ultra Search for a judged list with a tier, fit and reason for each creator. It's a remote server with nothing to install: sign in with OAuth, or use an API key. Free accounts include 50 API credits; paid plans add more. Creators whose bio states an age under 18 are always excluded.
Ask your assistant for an app and it lands on your phone: offline, data on the phone.
Manage over-the-air (OTA) updates for React Native, Expo, Capacitor and Cordova apps.
Shared Markdown memory that every AI assistant can read and write. Hosted in the EU.
Search job postings and track the jobs you like, dismiss and apply to in Joeb.
The integration hub for your CRM, field service and accounting apps. One plugin, two separate parts: integrations between two of your systems, and AI agents inside one of them. It connects the CRM, field service, accounting and online store systems small businesses run on. Don't see your system? Request it, right in the chat. Part 1. Integrations between two systems Set up in the chat, then they keep two of your systems in sync by themselves, so a new customer, a won deal or a paid invoice shows up where your team works without copying it by hand. - See which systems connect and what two systems can sync, no account needed - Choose the records that travel, one way or both ways, and the moment they travel: when paid, won, accepted or overdue - Ready rules, such as a won deal that becomes a draft invoice - Which fields go across, and how each system connects - Set it up in the chat, or get a link that opens the setup prefilled - For CRM Connector customers: your integrations, what failed and why, sync now, pause or resume Part 2. AI Agents inside one system An AI agent works with the records of one of your systems. Request your system right in the chat: we arrange the setup and enable it for your account, then you sign in to it. - AI Analyst: it reads your customer data, such as contacts, deals and invoices, and finds the same customer in your other connected systems - AI Agent: it also changes records when you ask, each change shown first, risky ones approved by you in CRM Connector - Automations: fixed rules inside that one system (when this happens, only if, then do that), made in the chat, approved once by you in CRM Connector, then run by the platform by itself - A change log with undo where the system allows it - Nothing in AI Agents syncs between two systems: that is an integration You stay in control: - You choose per system and per record type what the assistant may see or change - Changing records is a separate permission on the consent page, off unless you allow it - An automation never runs before you approve it, and you can pause or remove it at any time - It never deletes a record and never records a payment - It sets up, runs or pauses an integration only when you ask and confirm, and never deletes one - Disconnect at any time in CRM Connector under Settings, AI Assistants
Manage jobs, applicants, stages, and AI-ranked matches in Emploist, the applicant tracking system.
Your AI makes the file, you get a public link. Host PDFs, images and files from any MCP client.
Ship over-the-air updates for Capacitor apps: publish releases after your approval, control staged rollouts, read rollout health, and revert.
Know where your business stands and what needs attention next. Review available inquiry and paid-work records, goals and recorded spending from your connected workspace. See what needs attention and which conclusions the data cannot yet support. Create non-money goals on explicit request. Revenue targets and increased spending limits require owner approval. Requires a Samuelz account with the relevant Business OS modules. Data coverage depends on connected sources; missing data stays unknown. OAuth access remains bound to one workspace and its current permissions. By Glöggl GmbH.
One MCP for your whole revenue stack plus contact enrichment at cost. Build your own back-office apps on the same data. Credentials stay in a vault.
Request information without the back-and-forth
Toolstile is a managed MCP gateway that connects remote MCP servers behind one endpoint, with per-agent permissions, shared accounts and activity logs. Connect at https://mcp.toolstile.com/mcp over Streamable HTTP with OAuth; sign in at https://toolstile.com, select a workspace and connect your upstream servers. Available tools, resources and prompts depend on that workspace and the agent's granted access.
Ask about your own Meta (Facebook and Instagram) ad account right in Claude, ChatGPT or Cursor. Run1Ads checks your ads, Pixel and store every hour and tells you the one fix that matters today, ranked by buyers lost, with exact steps. It advises only and never changes your ads. Free for a limited time.
tri-train is a training platform for triathletes that syncs activities from Strava and Garmin and exposes them to Claude through a remote MCP server. Ask Claude how your last block went, why your run pace dropped, or whether you are fresh enough for Sunday's race, and it answers from your real data: activities with laps and grade-adjusted pace, weekly load and the performance management chart (CTL/ATL/TSB), sleep, HRV and resting heart rate, and your race calendar with predictions. Claude can also act: create and adjust planned workouts with structured intervals, push them to your Garmin watch, add races and write notes. Every change is journaled and can be undone. Read and write access are separate OAuth scopes, and the server enforces them on every call. Built and hosted in Switzerland by a triathlete; data stays on our own servers (Swiss revDSG / GDPR).
Singapore SLA land lots by lot number or coordinates, with URA Master Plan 2025 land use and GPR.
AgentiSend is a transactional email API: send through verified domains with a message log, budgets, a preflight and refusals that name the fix; built so AI agents can send on your behalf. The hosted MCP server at https://api.agentisend.com/mcp exposes 82 tools (44 on tools/list; the rest via list_more_tools). A send is one message or a batch of up to 500 items with per-item results. preflight_email runs every gate a real send runs, sends nothing, and costs nothing. Every 4xx returns code, message, and fix. There is no tool for unsolicited mail. Auth is a bearer API key or OAuth 2.1 with dynamic client registration. Starter prompts: "Send this receipt to the customer." "Preflight this send and tell me what would stop it." "What can I spend today?"
Turn a customer request into a complete HPE server configuration that loads straight into HPE's OCA configurator, without leaving Claude or ChatGPT. For HPE partners in Europe and the UK. Sign up at https://www.oyster.tech/join/connector for free credits; setup guide at https://www.oyster.tech/connectors.
Drafts posts in your brand's voice and publishes to Facebook, Instagram, X, Threads, Bluesky, LinkedIn profile, TikTok and Pinterest, only after you approve each one. TikTok videos are made in the Rebbel dashboard.
Mexican law for your AI: current federal and 32-state statutes with full articles and source links, Supreme Court (SCJN) and federal case law, the Diario Oficial de la Federación updated every 20 minutes, procedural deadlines with the official court calendar, filing guides and court bulletins. Free OAuth connection: 500 welcome calls plus 20 per day.
RedirX turns a site's old and new URL lists into a redirect map, working through the AI agent you already use. Connect the remote MCP server and sign in with OAuth. Your agent imports the two URL inventories, and RedirX proposes a destination for each old URL. Every proposal stays in review until you confirm it: confirm the clear matches, settle the ambiguous ones, and RedirX uses your confirmed examples to revisit what is still unresolved. Only approved mappings are exported, as Apache, Nginx, WordPress Redirection, Vercel, Cloudflare Pages, Shopify, CSV or JSON. Once the redirects are installed, verify_redirects checks the live site over HTTP. Nothing is published to your site automatically. RedirX produces the redirect file; you decide what ships. Works with Claude Code, Claude Desktop, Codex, Cursor and VS Code. Agents without an MCP client can follow the skill file at redirx.dev/skill.md. Pricing: the first migration is free for up to 500 old URLs, no card required. After that, $0.02 per old URL ($10 minimum), or monthly plans at $79 (5,000 old URLs) and $199 (15,000).
Live news search: what was published in the last hours and days on any topic, in 45 languages, with duplicate coverage grouped and every story checked for relevance. One read-only tool, search_news; sign in with OAuth (a free account with 50 search credits is created when you connect).
Ask your AI assistant about your own website's SEO and get answers from your real data, not generic advice. One connector, all your channels: Google Search Console (rankings, clicks, indexing), Google Analytics (traffic and sources), Google Ads (campaigns and search terms), Google Business Profile (local visibility and reviews), Google Trends, keyword research, backlinks and link prospects, competitor rankings, site crawls, and AI visibility (does ChatGPT mention your site?). Ask things like: which keywords am I one push away from page 1 for? Why did traffic drop last month? Which competitor is outranking me, and where? Are my ads and SEO fighting over the same keywords? Then let it act. On a paid plan, your assistant can prepare SEO fixes, content campaigns, and article drafts. Nothing touches your site until you approve it in SEOmatic, and every change shows before-and-after results. Connect via OAuth: log in, pick your site, done. No API key needed.
Design and edit Bloom canvases from AI agents with browser OAuth. Inspect pages and frames, edit frames, and work through review comments under existing project permissions. Bloom Labs, Inc. is a Y Combinator company from the P25 batch.
