"MCP servers that support SSE connections" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
**Ask your AI assistant about your Angelcam cameras, in plain language.** Sign in with your own Angelcam account (OAuth), and the assistant sees exactly what your account sees on MyAngelcam. Almost every tool only reads. There are two exceptions: the assistant can start or stop Cloud Recording on a camera when you ask, after confirming which camera it means, and it can send a feedback report to the Angelcam team once you agree to what the report contains. It never arms, configures or deletes anything. **What you can ask** • “Is the Front Door camera working right now?” It pulls a fresh frame, not the last status Angelcam recorded. • “What did the loading bay camera record at 3am?” Frames from Cloud Recording around that moment, plus a playback or download link. • “Which cameras are offline, and what needs attention at the site this morning?” • “What Real Time Security incidents happened overnight?” What raised each one and how it was verified. • “Which of our services expire next month?” (Space administrators only.) • “Start recording on the Warehouse camera.” Recording starts once you confirm the camera the assistant named. **Step-by-step guides** Six guides turn a camera you already have into a check your AI agent can run, with setup steps for Claude, ChatGPT and Grok Bot. [See all AI camera guides →](https://www.angelcam.com/ai-camera-guides?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guides-index) • [Is the gate closed? →](https://www.angelcam.com/ai-camera-guides/check-gate-open-or-closed?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guide-gate) • [How busy was the restaurant? →](https://www.angelcam.com/ai-camera-guides/count-restaurant-guests?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guide-restaurant) • [Was the container left open? →](https://www.angelcam.com/ai-camera-guides/check-container-doors?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guide-container) • [Is the horse lying down? →](https://www.angelcam.com/ai-camera-guides/monitor-horse-posture?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guide-horse) • [What changed at the shopfront? →](https://www.angelcam.com/ai-camera-guides/detect-graffiti-and-vandalism?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guide-graffiti) • [Is waste being left beside the bins? →](https://www.angelcam.com/ai-camera-guides/detect-waste-beside-bins?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=guide-bins) **What's inside** • 30 tools: spaces and locations, cameras and live view, Cloud Recording (timelines, gaps, frames, downloads), incidents, services and recording control. • Answers are summaries built for an assistant to reason over, not raw API payloads. • Snapshots reach your assistant as pictures. You can switch to links only when you connect. **Works with** Claude, ChatGPT, Cursor, VS Code and any client that supports remote MCP over Streamable HTTP with OAuth. **Good to know** • Free on top of your Angelcam subscription. • Times are UTC. Angelcam allows about 30 requests a minute per user. • Want a connector that can never change anything? Add `https://mcp.angelcam.com/readonly` to your client instead. It has no recording or feedback tools. [Setup steps for every client →](https://mcp.angelcam.com/?utm_source=glama&utm_medium=referral&utm_campaign=mcp-launch&utm_content=connector-page)
Hosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcp
An open MCP server for the Portuguese housing market, run by flatin.pt. No API key, no registration, no rate-limit negotiation. Twelve tools: • imt_calculate — IMT and Imposto do Selo on a purchase, 2026 tables, including the reduced table, the relief for buyers aged 35 or under and the flat rate for non-residents • imi_rate / imi_annual_cost — the IMI rate of any of the 308 municipalities for 2023–2025, and the annual bill for a given VPT • construction_barometer — how many building-permit cases enter a town hall each month (our own indicator: monthly for three municipalities, annual for eight, method and revision policy published) • search_newbuilds / get_newbuild — 250 new developments, 53 municipalities, 71 developers, with stage and, where published, price • where_to_live / municipality_stats / compare_municipalities — municipal comparisons • glossary_lookup — Portuguese property and tax terms • request_consultation / subscribe_digest — reaching a human The data behind the tax tools is published as open data under CC BY 4.0 on the Portuguese national portal (dados.gov.pt) and archived on Zenodo with a permanent DOI. Anyone may reuse it. Humans, not bots, answer the people who get in touch: a home purchase involves personal data under the GDPR and decisions that cannot be refunded.
Pre-trade token safety check for AI agents. Simulates a sell before you buy, then returns one low/medium/high/unknown verdict with the signals behind it: sellability, buy/sell tax, liquidity depth, pair age, same-ticker impersonation, owner powers from bytecode. Ethereum, BSC, Base, Solana. Fail-closed - a check that cannot run answers unknown, never low. Publishes its own measured error rate with the benchmark harness in the repo. Free, no signup, no API key, MIT.
Run saved PDF/office file flows, convert HWP/HWPX to Markdown or DOCX, and call data/text APIs.
Buzzmark is a ghostwriter that writes, plans and schedules social media posts for founders and growing businesses. It reads your website first, so drafts sound like you, and it works in the web app or from Claude, ChatGPT and Cursor. Every scheduled post lands on your calendar before it goes out.
Screwtape.ai decides whether an AI agent is allowed to spend money, and keeps the proof. Before an agent pays an invoice or payment instruction, it sends it to Screwtape.ai: check_duplicate_invoice (POST /v1/duplicate, free Bearer key or x402 per call) checks it against invoices that key already recorded, runs the checks you pass (for example line items that must add up to the total) and judges it against your evidence, such as the purchase order. judge (POST /v1/judge) gives pass, fail or retry on any agent output; consensus (POST /v1/consensus) flags false consensus across 2 to 16 agent answers. Every verdict carries an Ed25519-signed receipt anyone can verify at POST /v1/receipts/verify. judge and consensus can be paid per call with x402 ($0.005 USDC on Base or Solana, no account); a free key gives 10 calls per UTC day.
Marcora is the context layer for go-to-market teams. Build your source of truth once: a Brand Foundation (positioning, brand voice, and writing style) plus a Reference Library of product docs, buyer personas, competitive analysis, and messaging. Claude, ChatGPT, and any AI tool that supports MCP connections read from it, so what you write stays on-brand and accurate.
Run your social media from Claude, ChatGPT or any MCP client. Feedlio's MCP server lets your assistant list workspaces and connected accounts, add media, and create, edit, reschedule and cancel posts across 15 platforms, including Facebook, Instagram, LinkedIn, YouTube, TikTok, Pinterest, Threads, Bluesky, Mastodon, Dev.to and Google Business Profile. Sign in with OAuth on Feedlio's own page. MCP is included on every Feedlio plan, the Free plan too. Support: support@feedlio.io. Also in Claude's Connectors Directory: https://claude.ai/directory/connectors/feedlio
360 pay-per-call APIs for AI agents over x402 and MPP, settled in USDC on Base ($0.001-$0.25 a call, no account or API key). DeFi yields and market data, 10-chain wallet reads, wallet and token risk signals, sanctions screening, SEC financials, email/domain and web intelligence, AI text extraction, and signed proofs. Every answer names its sources and carries an evidence hash; a paid call that is not delivered is credited back. Built and run by UnyKorn LLC.
Make games with AI: one MCP server that connects your agent to Unity, Unreal and Godot editors.
Create beautiful forms that do more. Take payments, get documents signed, automate the rest.
Legacy IIS, classic ASP and SQL Server migration: paths, FAQ, end-of-support dates, fit assessment.
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.
Schedule, publish, edit and cancel social media posts on your Sociro accounts from your AI assistant, and plan a week of posts with Sociro's AI Planner that waits for your approval.
InsightBaZi exposes a public, read-only MCP tool (`calculate_bazi_chart`) that calculates BaZi pillars, hidden stems, Ten Gods, and Five Elements from birth inputs. Birth date and an IANA time zone are required. Recorded birth time, birthplace longitude, a birthplace display label, gender, and one of ten supported languages are optional. The birthplace label is for display; it does not look up coordinates. With a birth time, the tool returns all Four Pillars and true solar time, using the supplied longitude or an estimated time-zone meridian when longitude is omitted. Without a birth time, it returns Year, Month, and Day Pillars only, assumes a birth before 23:00 for the Day Pillar, and omits true solar time and luck pillars. Luck pillars require both birth time and gender. Historical daylight-saving offsets are derived automatically from the IANA time zone and birth date/time; there is no separate DST input, and the recorded time should not be pre-adjusted. Supported languages are English, Simplified Chinese, Traditional Chinese, Japanese, Korean, Thai, Indonesian, Spanish, Portuguese, and French. No authentication is required.
Build it. Rehearse it. Own the room. The hosted MCP server for Kadal Deck (deck.kadal.cc), which has your back for the whole talk, from the first idea to the last applause. Connect once with OAuth and your AI agent can list and inspect your decks, read a talk in progress (current slide, who is watching, polls and questions by votes), check analytics, change titles, visibility and passcodes, roll back versions, create share links, and quick-edit and publish decks through the web builder, with conflict-safe publishing that never overwrites newer work. Pair it with the local server (npx @kadal/deck mcp) to write, check and build decks on your machine. Open source.
Mode Analytics MCP server for ChatGPT, Claude and any AI agent: list reports, run report, read run results, edit query, create schedule, share report to Slack and archive report in your own Mode Analytics account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Mode Analytics yourself; Cotlet does not store your password and you need no Mode Analytics API key. About the official Mode Analytics API: Mode has a REST API, but only for Workspaces on a paid plan, and it signs in with a token: a Workspace token an Admin creates, or a member token that expires after 90 days once an Admin turns member tokens on; Mode offers no official MCP server (checked 5 Nov 2026). It covers reports, queries, report runs, exports, schedules and subscriptions, and it has no one-off share to Slack or email. Setup and FAQ: https://cotlet.dev/integrations/mode-analytics-api-mcp-server
Comeet MCP server for ChatGPT, Claude and any AI agent: list candidates, change candidate status, reject candidate with reason, decide Go/No-go step, invite candidate to self-schedule, add comment, tag candidate and add candidate in your own Comeet account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Comeet yourself; Cotlet does not store your password and you need no Comeet API key. About the official Comeet API: Comeet, now Spark Hire Recruit, has a Recruiting API, but Comeet grants access at its sole discretion under partner terms (checked 22 Oct 2026). Its beta MCP connection for ChatGPT and Claude searches live candidate, position and pipeline data and lists nothing that changes a record. Setup and FAQ: https://cotlet.dev/integrations/comeet-api-mcp-server
CapCut MCP server for ChatGPT, Claude and any AI agent: list drafts, export draft, add auto captions, share draft for review, invite members to a space, set member role, transfer editing permission and search templates in your own CapCut account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to CapCut yourself; Cotlet does not store your password and you need no CapCut API key. About the official CapCut API: Partly. CapCut has an official plugin for the ChatGPT desktop app that builds drafts and adds captions, effects and templates (capcut.com, checked 6 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/capcut-api-mcp-server
Skavio LLC serves 18 MCP tools. Four separately priced blockchain verification/DNS-TLS calls use native Circle USDC via x402 v2 on Base or Solana: Verify 0.02, Match 0.03, evidence PDF 0.05, DNS/TLS audit 0.05 USDC. Free discovery requires no wallet. Additional company document, OCR, invoice and audio relays use authenticated Agent Tools credentials and can debit prepaid company credits for eligible processing jobs. A human company admin may buy USD 5-500 Stripe card credit packs or top up with USDC at https://getskavio.com/agent-tools/dashboard.html. Those card credits DO NOT pay for the four standalone x402 USDC tools. Base-only HTTP x402 routes are separate. Endpoint: https://getskavio.com/mcp ; Docs: https://getskavio.com/agent-tools/docs.html ; USDC APIs: https://getskavio.com/x402/docs/ ; Support: support@getskavio.com. Evidence PDF is not a tax invoice. No real external paid card-to-MCP job E2E is verified yet.
Build AI agents that handle calls, web chats, and email — and automate everything around them.
Check before your agent installs, connects or pays. install_check: before installing an npm or PyPI package, a GitHub repo, a skill or an MCP server, it answers allow / hold / block (known malicious packages from OSV, typosquats of official MCP servers, names that do not exist, install scripts, maintainer changes). check_service: live status, real price and payTo vs the catalogue listing for any x402 endpoint or MCP server, OFAC and stablecoin-freeze screening, uptime, tool-set changes, on-chain payers, an open Trust Score. preflight_payment decides allow / hold / block right before an x402 payment is signed; payment_status prevents paying twice; dispute_evidence builds a signed evidence pack. Every answer is signed into a public transparency log. Free, no account. Claude Code plugin: alalanet-guard.
Adversarial testing for AI agents that move money: engine battery, Ed25519-sealed verdict reports.
Onchain DeFi intelligence API for Base, payable per call with x402 (USDC). Live MCP tools: get_bot_status (Telegram bot health), get_market_stats (market snapshot), get_onchain_sales (proven revenue from live x402 routes). Built for agents that need verifiable onchain data — whale flow, signals, and sales evidence at $0.005/call.
Compare travel eSIM plans and each local network (4G/5G), check phone support, get payment links.
TweakThis hands your coding agent the feedback left on your website. You or your client point at an element with the Chrome or Firefox extension and write a note; TweakThis captures the page, the element's selectors, HTML and styles, and a screenshot. Claude Code, Codex or any MCP client reads it over MCP, fixes it in your repository, and submits a resolution that you accept or reopen.
Whova MCP server for ChatGPT, Claude and any AI agent: add session, import attendees, send announcement, list registrations and export engagement in your own Whova account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Whova yourself; Cotlet does not store your password and you need no Whova API key. About the official Whova API: Whova has no public developer API (checked 11 Oct 2026). Organizers get a Zapier app with three triggers (attendees, orders, registrants) and one action, Create or Update Attendee, plus native connections to CRM and AMS platforms such as HubSpot and MemberClicks. Setup and FAQ: https://cotlet.dev/integrations/whova-api-mcp-server
ShootProof MCP server for ChatGPT, Claude and any AI agent: create gallery, share gallery, list orders, send contract and send invoice in your own ShootProof account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to ShootProof yourself; Cotlet does not store your password and you need no ShootProof API key. About the official ShootProof API: ShootProof has a documented OAuth API that is free with an account, but you get a client ID only by emailing ShootProof support with your app details (checked 8 Nov 2026). There is no self-service key and no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/shootproof-api-mcp-server
Rent Manager MCP server for ChatGPT, Claude and any AI agent: post charge, create work order, message tenant and list tenants in your own Rent Manager account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Rent Manager yourself; Cotlet does not store your password and you need no Rent Manager API key. About the official Rent Manager API: Rent Manager has an API that reads and writes your database, but it is not self-serve (checked 11 Oct 2026). Its public pages offer no key signup: access goes through the Integrations Partner Program or an API support request, and a developer then builds the connector. Setup and FAQ: https://cotlet.dev/integrations/rent-manager-api-mcp-server
