"Supabase Platform Overview" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Execution platform for AI agents on Firecracker microVMs in the EU. Interactive Linux sandboxes with root, templates for Python, Node.js, Go, Rust and a headless browser, public HTTPS URLs. Background jobs that outlive the connection, batches of up to 1,000 jobs with dependencies, hard cost caps reserved up front, execution receipts with SHA-256, log digests that fit the context. IPv4, dual-stack or IPv6-only with its own public address, allowlists or no network. WASI runtime for small tasks. Idle sandboxes sleep and keep their files. Also REST API, Python SDK and LangChain.
Your AI assistant writes a design as HTML and Tailwind CSS, and RenderPixels renders it in a real browser and returns images at the exact size each platform needs: social posts, banners, logos, favicon sets and Open Graph images. Each render reports clipped text and missing fonts or images so the assistant can fix and re-render. OAuth sign-in, saved brand kits, 50 free renders per month.
Draft, find, update and sign contracts in fynk, the European contract management platform. Your AI assistant can search and summarize your documents, create contracts from templates or PDFs, fill in parties, signatories and dynamic fields, build templates, manage tags, teams and metadata, and send documents out for e-signature (SES, AES, QES). It acts with your own fynk permissions via OAuth. Requires an Essential, Business or Pro plan (14-day free trial) with MCP enabled by an account admin.
Query your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform.
Read-only security checklists: VPS hardening, Docker, secrets, Supabase, Stripe, auth, AI agents.
Work with connected business profiles and available Google Maps publication workflows. This listing retains the complete 25-tool Maps service and its existing full endpoint. For new tasks, start with Samuelz® Maps · Profile maintenance. Choose from Profile maintenance, Posts and drafts, Review replies, Image sources, Provenance and search terms at https://platform.samuelz.com/integrations?lang=en#maps. Each task view is a subset, not a replacement for the full service. Existing URLs and conversations keep working. Changing views grants no additional rights and does not migrate a running conversation. Prepared operations keep their identity and approval requirements; read their status before any recovery. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=maps. Sign in to Samuelz and select your authorized workspace. Active workspace membership and the relevant module permissions are required. Review requested permissions before authorizing. Existing human approvals and separate cost permissions continue to apply.
Review accounting data and available financial records within your authorized workspace. This listing retains the complete 18-tool Accounting service and its existing full endpoint. For new tasks, start with Samuelz® Accounting · Evidence checks. Choose from Evidence checks, Individual reminder, Cost allocation, Existing reminder run at https://platform.samuelz.com/integrations?lang=en#accounting. Each task view is a subset, not a replacement for the full service. Existing URLs and conversations keep working. Changing views grants no additional rights and does not migrate a running conversation. Prepared operations keep their identity and approval requirements; read their status before any recovery. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=accounting. Sign in to Samuelz and select your authorized workspace. Active workspace membership and the relevant module permissions are required. Review requested permissions before authorizing. Existing human approvals and separate cost permissions continue to apply.
Paste an error from a Supabase, Lovable or Bolt app and get the matching step-by-step fix guide.
Public chauffeur information, policies and anonymous price previews in the provider’s published service areas. On explicit customer request, prepare a binding unpaid offer using email OR E.164 phone, without an account. Customers review bound terms and explicitly confirm in Samuelz checkout. The same endpoint provides OAuth-protected booking status, payment review, history, and amendment/cancellation workflows. Booking data and actions require authorized customer access; changes and cancellations require the applicable object-bound consent. Tool discovery is public. Quotes do not guarantee availability, and MCP does not take payment. Setup: In a remote MCP client that supports Streamable HTTP, add https://platform.samuelz.com/api/v1/mcp/customer-booking. Public discovery and price previews need no account. Sign in with OAuth for authorized customer booking data and actions. Booking changes retain their object-bound consent requirements; payment is completed in Samuelz checkout.
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).
Work with communication cases, clarification requests and prepared replies through the existing workflow. This listing retains the complete 52-tool Communications service and its existing full endpoint. For new tasks, start with Samuelz® Communications · Replies. Choose from Replies, Triage, Reply preparation, New email, Delivery checks, Assignments and duty, Repair evidence, Letter preparation, Physical mail intake at https://platform.samuelz.com/integrations?lang=en#communications. Each task view is a subset, not a replacement for the full service. Existing URLs and conversations keep working. Changing views grants no additional rights and does not migrate a running conversation. Prepared operations keep their identity and approval requirements; read their status before any recovery. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=communications. Sign in to Samuelz and select your authorized workspace. Active workspace membership and the relevant module permissions are required. Review requested permissions before authorizing. Existing human approvals and separate cost permissions continue to apply.
Read-only Seenly tools: explain the platform, hand a signup link, fetch public profiles.
31Explore 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
Deploy durable AI agents with Omnara, an open-source managed-agent platform.
Ethora chat platform MCP: apps, users, rooms, AI agents, chat widgets. Hosted or stdio.
Double-entry books an agent keeps as the user: invoices, VAT returns, 174 country packs.
Review and follow operational workflows and available work orders in your connected workspace. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=operations. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Schedule and publish posts to TikTok, Instagram, YouTube, LinkedIn and more from any AI agent. Connect your social accounts once, then let Claude, ChatGPT or any MCP client create, schedule, edit and review posts across every platform. Upload images and videos to your media library and attach them to posts. Signs in with OAuth; HubPost never sees your passwords. Also available in the [Claude directory](https://claude.ai/directory/hubpost) and as a [ChatGPT app](https://chatgpt.com/plugins/plugin_asdk_app_6ab141477a708191a7c5f68714ee7c39). Setup guide: [hubpost.co/mcp](https://hubpost.co/mcp?utm_source=glama&utm_medium=mcp-directory).
Built-in MCP server of every NET Genium Online instance (low-code platform for business apps). Your agent reads and writes your application data, reads and changes the application model (forms, view pages, controls, permissions, SQL data model) and searches the platform docs, so what it builds follows the platform's conventions. Connect through one address and pick your instance at sign-in (OAuth). A single-user instance is free at netgenium.online, no payment card.
Edge platform audit: a deliverable delivered per API call as an independent atom service.
Official-data MCP server for French charities. Search, profile and compare 170,000+ French associations and foundations by name, cause, city or département, using SIREN/RNA identifiers from official public registries (INSEE Sirene, RNA, JOAFE). Each profile includes a transparency score built on four public criteria (transparency, impact, governance, finances), verified donation links and donor guides on French tax deductions. Read-only, no login needed, free tier included. 8 tools: search_ngos, get_ngo, compare_ngos, top_ngos, list_causes, get_donation_paths, search_guides, get_guide.
SEO and market data: SERP, keyword volume, backlinks, site audit, Maps, reviews, traffic, ChatGPT visibility, Amazon, jobs, DNS, bulk HTTP/API requests.
Email inboxes for AI agents, on @pidgeon.email or your domain, and for every user of your platform.
Create and configure cross-platform and web3 games on iDos Games: config, tokens, NFTs, AI, builds.
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Production-grade unit conversion server covering 460+ units across 36 categories. Features full regional land measurement provenance (Bigha, Marla, Kanal, Gaj, Guntha) with state revenue manual citations.
Younanix is the Engineering Judgment Layer for AI-generated software: Arete Memory plus adversarial audits. MCP endpoint (Streamable HTTP): https://bbuaschzvigwmoxekmoo.supabase.co/functions/v1/mcp-server Public tools: query_lessons is a free preview (1 query per session, degraded results). query_lessons_premium returns a full Arete brief for $0.10 USDC on Base or Solana, or free for approved agents with an x-agent-key. Other tools (query_lessons_full, incident reports, task-run trail, ops snapshot) require a Younanix-issued x-agent-key; tools/list is open so directories can health-check the server. Humans: free architecture check and Private Audit (by invitation) at https://www.younanix.com/private-audit Agent Auditor tiers and payment details: https://www.younanix.com/llms.txt
QA platform for agents: coverage signals, in-repo test plans, verified tests and release governance.
ShipCargo is an AI-powered vehicle shipping platform. Its MCP server lets AI assistants get instant car shipping quotes and live shipment tracking: three tools (service information, instant quote, shipment tracking), secured with OAuth 2.0 and per-client scoped permissions. Nationwide door-to-door open and enclosed auto transport through vetted carriers; no upfront payment — card charged at pickup.
Check Supabase SQL for who can read and write each table: RLS gaps, open policies, grants, fix SQL.
Create and manage quizzes, leads, and respondents on RooQuiz, a lead-capture assessment platform.
Read-only facts on Holos33, an EU privacy-first wellbeing platform: modules, Early Access, privacy.
Thumbtack MCP server for ChatGPT, Claude and any AI agent: list leads, reply to lead, send quote, update weekly budget, list reviews and export past leads in your own Thumbtack account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Thumbtack yourself; Cotlet does not store your password and you need no Thumbtack API key. About the official Thumbtack API: Thumbtack has an official Partner Platform API for leads (called negotiations), messages and reviews, but its docs are gated and access is by request for integration partners (checked 11 Oct 2026). A pro gets no API key for their own account. Setup and FAQ: https://cotlet.dev/integrations/thumbtack-api-mcp-server
NSW DAs, CDCs and property planning reports: zoning, height, FSR, nearby DAs. Pay per call via x402.
Minds is a synthetic market research platform. This MCP server lets ChatGPT, Claude, and Cursor build Audiences from a brief, run durable Studies and Question Blocks, compare segments, and export results. OAuth 2.1 or Minds API key.
Every EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.
Atomic AGI is an agentic marketing platform for AI search optimization: SEO and AI search analytics, visibility tracking, content and entity strategy, brand reputation, technical and Agent Experience (AX) audits, and execution through AI agents, content workflows and MCP. Built by Omnius, a B2B SEO & AI search optimization (AEO/GEO) agency for SaaS, Fintech and AI. https://www.atomicagi.com
PushPress MCP server for ChatGPT, Claude and any AI agent: list members, book class reservation, check in member, cancel reservation and update membership plan in your own PushPress account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to PushPress yourself; Cotlet does not store your password and you need no PushPress API key. About the official PushPress API: PushPress has a Platform API and an SDK that doubles as a local MCP server, both using an API key from Settings > Security & Access, but they are mostly read-only beyond creating customers and invitations (checked 11 Oct 2026). Booking, check-ins, plan changes and class cancellations are done by staff in Core. Setup and FAQ: https://cotlet.dev/integrations/pushpress-api-mcp-server
Everfit MCP server for ChatGPT, Claude and any AI agent: list clients, get client overview, assign program, read body metrics and message client in your own Everfit account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Everfit yourself; Cotlet does not store your password and you need no Everfit API key. About the official Everfit API: Everfit has an API, but only for Enterprise customers, who ask the Enterprise team by email for a token (checked 11 Oct 2026). It manages clients, programs, Autoflows, collections, groups and forums, and sends two webhooks; its guide lists no endpoints for messages, body metrics, tasks or workout results. Setup and FAQ: https://cotlet.dev/integrations/everfit-api-mcp-server
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.
Deltabridge brings an AI-native cyber threat intelligence platform into your AI agent. Search a knowledge graph of 400,000+ threat actors, malware families, vulnerabilities, indicators and campaigns, mapped to MITRE ATT&CK. Look up and enrich IOCs, trace links between entities and read living briefs built from 300+ open sources. Read-only, scoped to your organisation, with OAuth sign-in or an API key. Included on Researcher, Business and Enterprise plans.
Multi-tenant backend your coding agent configures over MCP: auth, RBAC, data, workflows, deploy.
AI-native project and portfolio management platform for PMOs. OAuth + PAT.
GradeAtlas MCP — convert grades between 1,159 grading systems across 246 countries into the US 4.0 GPA scale, with university search and country grading guides.
Vigilia watches your live app, explains every problem in plain language and writes the fix prompt. Your AI fixes it; Vigilia confirms with real traffic. Vigilia watches web apps that are live with real users, including apps built with Lovable, Bolt, v0, Cursor and Claude Code. It catches errors, failed requests and downtime, explains each problem in plain language, and writes a fix prompt for it. Connect Vigilia to Claude and ask what's broken. Claude lists your open incidents worst first. For each one it reads the plain-language diagnosis, who it affects, the technical evidence (error, page, failing request, stack frames and what the visitor did right before) and Vigilia's fix prompt. In Claude Code or another coding agent, Claude can then fix the cause in your own codebase. Once you've deployed, it marks the incident fixed, and Vigilia watches real traffic to confirm the error stayed away. If it comes back, the incident reopens as a regression. You can also ask how an app is doing (uptime, open incidents, today's traffic), get the exact install snippet for a new project, and check that a live site is running Vigilia. Vigilia never reads or changes your code: the fixing happens in your session, by your AI, in front of you. The only tool that changes anything is marking an incident fixed (the install check just records its result on the app), and you can connect with read-only access. Your data is stored in the EU. Emails, tokens and card numbers are stripped from what visitors' browsers send, and only that scrubbed error context is sent to Anthropic to write the diagnosis. Requires a Vigilia account. The free plan covers one app; reporting backend errors (Supabase, Next.js routes, Workers) is part of Pro.
Exact developer checks: email DNS, Supabase RLS, cron, JSON, contrast, time zones, npm/PyPI packages
NotebookLM MCP server for ChatGPT, Claude and any AI agent: list notebooks, create notebook, add source, ask notebook, save note, generate Audio Overview and share notebook in your own NotebookLM account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to NotebookLM yourself; Cotlet does not store your password and you need no NotebookLM API key. About the official NotebookLM API: NotebookLM has an official API only for NotebookLM Enterprise (checked 5 Nov 2026). It is a REST API in v1alpha preview that creates, gets, lists, deletes and shares notebooks, and it needs an Enterprise license and a Google Cloud role. Setup and FAQ: https://cotlet.dev/integrations/notebooklm-api-mcp-server
GDPR platform: your assistant fills in VVT, TOMs, AVV and DSFA, your DSB reviews them.
Deploy apps from Claude Code or Cursor: hosting, Postgres, email, files. Vercel+Supabase in one.
Read-only unofficial platform predictions and departure information for London Euston and Paddington, with measured accuracy. Predictions may be wrong; station screens are the official source.
Work with marketing activity and available campaign data in your connected workspace. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=marketing. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
The Decision Operations Platform for engineering teams
Convert Apple Numbers (.numbers) to Excel (.xlsx) in the browser — first sheet free. MCP v1.1.0 (Streamable HTTP) exposes four tools: open_numbers2excel (open site / Stripe checkout intents; conversion is browser-local), get_site_info (product overview, pricing, URLs; read-only), get_pro_status (Stripe subscription_id sub_… status), get_unlock_from_session (Checkout session_id cs_… → entitlement). Path A: MCP does not accept or upload files.
SELISE Signature is a Swiss e-signature platform for PDFs and Word documents with simple, advanced and qualified electronic signatures (SES, AES, QES), aligned with eIDAS and ZertES, with Swiss/EU data residency. Free plan with 20 signatures per month, no credit card. Its MCP server lets AI assistants such as Claude, Cursor and Grok Bot prepare and send documents for signature, with a human approving every send.
The beta program platform for hardware and IoT teams, who run structured betas with their own testers. Connect your AI assistant to build tasks and steps, screen applicants, triage tickets, read results and track tester progress. Actions that reach testers return a preview first and take effect only after confirmation. Sign in with OAuth, with read-only or read and write access. Stomio does not recruit testers.
Open registry of 1.14M+ rooftop-solar detections across France, queryable by natural language.
Hard daily caps on your AI agents’ API spend (OpenAI, Anthropic, Google, OpenRouter via proxy keys), plus phone approval before any other payment.
Kahunas fitness coaching platform MCP server: list check-ins, assign workout plan, add client.
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 sixteen read-only tools. Every name follows one pattern: list_, get_, search_ or verify_. Changes and context: • list_changes — Browse the newest published changes, newest first, 20 per page. • search_changes — Search changes by words in English, Chinese or Japanese, ranked by relevance. • get_change — One change with its sources: outlet, link, date, evidence level and role. • list_topics — Browse curated topics, optionally by coverage domain. • get_topic — One topic and up to 50 of its recent changes. • get_latest_brief — The latest daily or weekly brief. • list_scheduled_events — Upcoming central-bank decisions, data releases, earnings, rule dates and more. Companies: • search_companies — Find a company by name, alias or ticker. • get_company — A company's profile, listings, recent changes, stated facts and relations. Countries and SeekEarth: • list_countries — Every country with its name and this week's number of changes. • get_country_heat — Change Heat per country against its own normal, with a seven-day series. • get_earth_view — One place and moment on SeekEarth: changes, heat and the Earth's layers. Evidence (SeekTrace): • get_change_history — A change's evidence receipts and what AiSeek knew at an earlier time. • get_receipt — One evidence receipt. • verify_receipt — Check that a stored receipt is unchanged. • list_corrections — Public corrections, newest first. Tool calls need an AiSeek API key (Authorization: Bearer or the x-api-key header), made at aiseek.dev/en/account; the handshake and the tool list are open. Optional connection defaults go on the endpoint URL: ?locale=en|zh|ja&limit=1-50&domain=MARKETS. Answers carry sources and links, never quoted passages.