"Factur-X MCP (Model Context Protocol) Integration" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Drop-in EU AI Act Article 12 compliance, OWASP MCP03 tool-poisoning defense, and unstoppable L402 failover for LangChain, CrewAI, and AutoGPT swarms. Bitcoin Stratigraphy is the enterprise Layer-402 data engine and AI Notary Hub for autonomous swarms—hardened across 1,341 automated security checks (1,033 Node tests, 280 Python tests, and 28 pipeline tests at 100% coverage). We bridge the gap between probabilistic LLM execution and institutional verification with a cryptographically auditable chain of custody, native disaster recovery, and permanent programmatic revenue sharing. **For CISOs: OWASP MCP03 Tool-Poisoning Defense & EU AI Act Article 12** Deploying autonomous agents without verifiable audit trails and schema integrity is a critical regulatory and security risk. We solve this natively: * **Boot-Time Ed25519 Tool Hash Pinning:** Defend against OWASP MCP03 tool poisoning and silent rug-pulls by verifying SHA-256 tool-definition hashes and Ed25519 signatures at `/.well-known/integrity.json` or via `stratigraphy://security/tool-integrity` before exposing tool schemas to an LLM. * **Zero-Trust Offline Verification:** Download our self-contained `/static/verify.html` verifier to independently audit signed receipts, committed NIP-98 attribution, RFC 6962 inclusion paths, signed CRL snapshots, and AGPLv3 Copyright Waiver certificates completely air-gapped using pinned Ed25519 public keys. * **Enterprise NIP-98 Kill Switch & Signed CRLs:** Instantly revoke compromised sub-agent keys via `POST /api/admin/revoke_key` and poll `GET /api/v1/compliance/revocation-snapshot` for Ed25519-signed revocation registries (fails closed with HTTP 503—never a fabricated empty CRL). * **Thermodynamic State Grounding:** Anchor agent decisions and dataset digests with portable OpenTimestamps (`.ots`) receipts (`proof.notarize`) and signed Bitcoin-tip context attestations (`proof.ground`) to stop cascading peer hallucinations. **For Finance & Engineering: Dynamic BTC Packs, Unstoppable Failover & Zero-SLA Waivers** Corporate finance teams run on credit cards, while autonomous swarms need deterministic, zero-red-tape Bitcoin rails that never stall: * **Enterprise Scanner Packs (Stripe or Dynamic BTC):** Authorize a 30-day, 100-call heuristic scanner block for **$500** via automated Stripe/Brevo card checkout, or settle natively in Bitcoin/Lightning at a **10% discount ($450 USD dynamically quoted via fail-closed Coinbase/Kraken spot oracle, locked 15 minutes)**. High-volume fleets can acquire a Bitcoin-only **Heavy Swarm Pack ($4,000 USD in BTC for 1,000 calls, valid 90 days)**. * **Unstoppable Failover Protocol (Disaster Recovery):** If centralized fiat gateways suffer a Stripe 5xx outage or breach our 5-second checkout deadline, our additive protective wrapper automatically emits `HTTP 402` (`error="fiat_gateway_offline"`, `fallback="native_lightning_active"`), issuing the dynamic $450 USD-pegged native Lightning invoice so mission-critical swarms never stall. * **Drain-Attack Containment:** Replace uncapped static API keys with attenuated L402 child macaroons (`proof.attenuate`) locked to a single delegate pubkey, exact RPC method, hard call ceiling, and UTC expiry—mathematically capping blast radius even if a worker agent is hijacked. * **Self-Serve, Zero-SLA Bitcoin AGPLv3 Copyright Waivers:** Private VPC and air-gapped deployments can obtain time-locked AGPLv3 Section 13 network source-disclosure waivers directly on-chain—**Single-Swarm ($2,500/mo or $25,000/yr)** or **Global Organization ($25,000/mo or $250,000/yr)**—settled via unique, watch-only BIP-84 `zpub` deposit addresses and minted as offline-verifiable Ed25519 certificates. All prepaid access and waivers are 100% self-serve and provided **STRICTLY AS-IS, WITH ALL FAULTS—zero SLAs, zero uptime warranties, zero custom MSAs, and zero support obligations**. **For Developers & Swarm Orchestrators: 19 MCP Tools & Permanent 21% Agent Yield** Stop building compliance and payment rails from scratch. Connect to our live 19-tool Streamable HTTP endpoint in seconds: * **The 21% Programmatic Agent Yield:** Orchestrators and security integrators routing verified L402 traffic earn permanently from our mathematically enforced 21% programmatic yield pool (15% upstream origin allocation + 6% verifying caller allocation on eligible confirmed `proof.verify` settlements; 79% retained). * **Zero-Install Live Connection:** Connect Claude Code, Cursor, Codex, LangChain, CrewAI, or ElizaOS immediately with `npx add-mcp 'https://bitcoinstratigraphy.com/mcp'`. Run free tool discovery (`stratigraphy.list`, `proof.list`) and check itemized satoshi quotes (`POST /api/v1/cost`) before spending a single sat. * **High-Velocity Batching & Boilerplate:** Acquire 100-, 1,000-, or 10,000-call Macro-Macaroons (`X-L402-Batch-Size: 100 | 1000 | 10000`) at the fixed 250-sat base tariff (preserving the 21% Agent Yield across all batch tiers), or clone our public GitHub boilerplate (`CharlesStrogish/zk-flight-recorder-template`) to wire your agents in minutes. [OWASP MCP03 Defense Blog](https://bitcoinstratigraphy.com/blog/defending-autonomous-ai-swarms-mcp-tool-poisoning-hijacking/) | [Disaster Recovery Guide](https://bitcoinstratigraphy.com/developers/enterprise-troubleshooting) | [1,341-Check Security Audit](https://bitcoinstratigraphy.com/security) | [Developer Portal](https://bitcoinstratigraphy.com/developers)
Savvly MCP: query fund data, model projections, and compare against alternative retirement products.
CellMath is a governed AI memory and knowledge-cell MCP server designed to stop context bloat, unverified memory drift, and agent hallucinations. Instead of dumping raw, noisy RAG chunks into every turn, CellMath organizes persistent agent knowledge into structured, isolated Knowledge Cells with causal graph edges and strict write-time governance—keeping the full 3-tool MCP schema ultra-compact (~1,200 tokens). Core 3-Tool Pipeline: • vault_access — Read-only lookup, cell hydration, and graph edge traversal with strict zero-match silence (never fabricates context when no verified cell exists). • verify_safety — Preflight security and policy gate that blocks destructive or unsafe operations before execution. • vault_commit — Governed state mutation (store, update, causal edges, session checkpoints, and 4-tier purge) enforcing source provenance. Built for Claude, Cursor, ChatGPT, Gemini, and autonomous agents over Streamable HTTP.
Cryptographic 563-leaf LLM rate oracle, context-cliff auditor, and prompt cache optimizer.
Design a data model, metrics and dashboards; generate realistic data and check known answers.
HefestoAI checks AI-generated code before you ship it.
Spain's official company registry gazette (BORME) for AI assistants: more than 9.6 million company events since 2009, updated every business day. Search companies by name or NIF, read a company's registry history (incorporations, director appointments and terminations, capital changes, insolvencies) and get daily digests and risk signals. Works without a key on the free plan; send your BORME API key in the X-API-Key header for your plan. For OAuth sign-in use https://mcp.bormeapi.com/mcp/oauth.
Daily feed of AI releases, tools and techniques, each labeled with how it was checked.
Which LLM should I use for this task? Ask in plain words and get the models that score best on the matching benchmark board, within your price, context window and open-weights limits. Covers 400+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, Mistral and more, with benchmark scores (coding, agentic, reasoning, math, knowledge, design) and API list prices per million tokens, updated daily. Tools: recommend_model, get_leaderboard, compare_models, get_model, get_prices, list_categories. Free, no API key, data under CC BY 4.0. Docs: https://llmbenchmark.ai/api
OpenAny is the B2A (business to agent) marketplace. Add one MCP endpoint, https://mcp.openany.si, and your agent can find and use 3,200+ APIs and 168+ AI models. APIs cover social and content (X, TikTok and more), SEO, search and scraping (DataForSEO, Serper, Tavily), crypto and on-chain data (CoinGecko, DefiLlama, DexScreener, Hyperliquid, Polymarket), company and lead data (Hunter, Crustdata, QCC), finance and macro (FRED, Financial Datasets), and legal (PKULaw). Models include chat and reasoning (GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM, MiniMax), image (Midjourney, FLUX, Nano Banana, Seedream, GPT Image), video (Veo, Kling, Seedance, Hailuo, Wan) and audio. Searching and checking prices is free with no key. You only need an OpenAny API key to run a call, and you pay per call.
Multi-LLM entity enrichment: schemas, single/batch enrichment, fusion, model benchmarks.
Official hosted Model Context Protocol (MCP) server for LogToLast. Connects Anthropic Claude and Cursor IDE directly to your live Tradovate, NinjaTrader, and MetaTrader 5 trading journal, quantitative performance metrics (Win Rate, Profit Factor, Expectancy, Golden Hours), active Playbook risk rules, in-app skills, and recent trade execution logs for real-time AI strategy and discipline coaching.
Living docs and MCP context for GitHub repos — conventions, gaps, and source-cited pages on merge.
Live GitHub repo AST X-Ray, 42 coding-agent DoD gates, Git worktree guards & brownfield baselines.
Check a link's share card on X, Facebook, LinkedIn: real image size, tag problems, fixed tags.
Cryptographically verified 563-model LLM API pricing oracle, context-cliff calculator, prompt cache optimizer, and real-time bill reconciliation engine.
AstroMansion is a hosted MCP server for astrology computed exactly, never estimated. Positions come from our own engine on NASA JPL ephemerides, with no third-party astrology API behind it. Checked against NASA JPL Horizons, major-planet positions stay within half an arcsecond, and the audit is public at https://astromansion.com/en/accuracy. 52 techniques Natal charts, transits and transit hits, stations, solar, lunar and Saturn returns, secondary progressions, solar arc, primary directions, synastry, composite charts, compatibility, dignities, profections, firdaria, zodiacal releasing, decennials, horary, electional, lunar mansions, Arabic lots, Vedic charts, nakshatras, Vimshottari dasha, navamsa, aspect patterns, midpoints, antiscia, declinations, harmonics, draconic and heliocentric charts, astrocartography, fixed stars, parans, heliacal risings, rectification, great conjunctions, Venus star points, ingresses, the age point, temperament and moon phases. Tools - search_places finds a birthplace with its coordinates and time zone. - natal_chart casts a birth chart with its planets, houses and aspects. - body_sign tells the sign a body stood in at a birth. - list_techniques lists every technique, the plan it needs, and an example of its options. - run_technique runs any of the 52 techniques. - sky_calendar lists moon phases, retrogrades, eclipses and void-of-course Moon periods. - chart_image draws the chart wheel as a PNG. - mansionsql_query answers SQL questions about a chart. Eight tools keep the assistant's context small. list_techniques shows what exists, and run_technique runs it. Connect - Claude and ChatGPT: add https://api.astromansion.com/mcp as a custom connector and sign in with your AstroMansion account. - Claude Code: claude mcp add --transport http astromansion https://api.astromansion.com/mcp --header "X-API-Key: YOUR_KEY" - Any other client: Streamable HTTP at https://api.astromansion.com/mcp, with OAuth or an X-API-Key header. Plans The free plan includes 100 calls a month for natal charts. Paid plans open the other techniques. See https://astromansion.com/en/pricing.
Travel ranking, place facts, weather, visa, and profile tools for Sorted Travel.
Real-time Google Flights fares for agents. Three things people do with this server. Scan for deals: one call takes a date range and a list of destination airports, expands every combination server side, and returns each fare with Google's own low, typical or high verdict. Put live search in your app: flat JSON with a bookable link on every result, and round trips priced as paired legs. Run a 24/7 AI travel agent: add the server, sign in with Google, and schedule it. No ads, no sponsored content. You bring your own RapidAPI key, so every search is billed to your plan and never to anyone else's. Add https://flights.flightpowers.com/mcp , click Sign in, sign in with Google, and paste your RapidAPI key once on the page that opens. Scripts and clients without a sign-in button send the key as x-rapidapi-key on the same URL.
AI marketing team for founders, callable from any agent: plan what to say, edit video, generate images and clips, write and design posts, publish to LinkedIn, X, Instagram, TikTok, YouTube, Facebook, Threads, Bluesky, Discord and Mastodon and read what performed. OAuth sign-in, no API key; every draft waits for approval unless you say publish now. Free Forever plan: 10 posts a day, no card.
Behind Check and GAIP Watch, and Diagnose: A2A, MCP and OpenAPI checks with a dated change log.
Architecture context for Claude and Cursor: estate graph, evidence, standards; ADRs back for review.
Real-time Booking.com rates for agents. Three things people do with this server. Scan for rate gaps: price_as_seen_from prices the same room from another market, so an agent can sample a property across countries and compare. Put live search in your app: search a destination or look a property up by name, no internal IDs, room-level rates as flat JSON. Run a 24/7 AI travel agent: add the server, sign in with Google, and schedule it. No ads, no sponsored content. You bring your own RapidAPI key, so every search is billed to your plan and never to anyone else's. Add https://hotels.flightpowers.com/mcp , click Sign in, sign in with Google, and paste your RapidAPI key once on the page that opens. Scripts and clients without a sign-in button send the key as x-rapidapi-key on the same URL.
Give your AI assistant the competitive context it can’t see on its own. Connect it to Watchr for competitive intelligence and brand monitoring across your connected sources and get direct access to validated insights and reports.
Long-term memory for each person your app serves: saves, recalls later, keeps facts current.
Load testing and synthetic monitoring platform: test with Playwright, Browser Bot, or Protocol Bots.
Now part of GAIP Diagnose: diagnoses failed agent or API calls (gaip_diagnose).
The Smarty-Pants MCP provides a ranking of the probability a URL is malicious. Designed as an agentic cybersecurity product. 1000 requests free with developer account (also free but must sign up). Easy to use return JSON: { "url": "http://evil.co/1", "probability": 0.987787, "malicious_percent": 98.78, "is_malicious": true, "threshold": 0.6, "source": "model" }
Managed cloud RSS and Atom feed reader with a remote Model Context Protocol (MCP) endpoint. Zero server setup required — enables AI agents like Claude to instantly subscribe to feeds, search full-text articles, extract readable content, and access curated AI editions ("Your Newspaper") over secure streamable HTTP.
Email finder and enrichment: LinkedIn, GitHub, or a person's name on any page, X and YouTube too.
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
Quinyx MCP server for ChatGPT, Claude and any AI agent: list approval requests, approve request, deny request, offer open shift, add absence, create shift, attest worked hours and publish schedule in your own Quinyx account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Quinyx yourself; Cotlet does not store your password and you need no Quinyx API key. About the official Quinyx API: Quinyx has a REST API (checked 22 Oct 2026), but no official MCP server, and the API leaves out the manager's daily work: it cannot approve requests, offer shifts, attest hours or publish a schedule. Credentials are generated by someone with access to Account Settings > Integrations credentials, and a developer has to build the integration. Setup and FAQ: https://cotlet.dev/integrations/quinyx-api-mcp-server
AutoLeap MCP server for ChatGPT, Claude and any AI agent: list estimates, send estimate, convert estimate to repair order, list repair orders, text a customer and book appointment in your own AutoLeap account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to AutoLeap yourself; Cotlet does not store your password and you need no AutoLeap API key. About the official AutoLeap API: AutoLeap has a REST Partner API, but it is gated: credentials go to approved integration partners, and AutoLeap describes it as not available for the Essentials, Pro and Elite plans (checked 28 Oct 2026). There is no official MCP server, so a shop owner cannot connect an AI agent through the official route. Setup and FAQ: https://cotlet.dev/integrations/autoleap-api-mcp-server
Phorest MCP server for ChatGPT, Claude and any AI agent: book appointment, reschedule appointment, list clients, find free slots and add client note in your own Phorest account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Phorest yourself; Cotlet does not store your password and you need no Phorest API key. About the official Phorest API: Phorest has an API, but credentials come only through Phorest Support with your account number, and Phorest says integration needs your own development team (checked 8 Nov 2026). It has no webhooks and no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/phorest-api-mcp-server
Invoice2go MCP server for ChatGPT, Claude and any AI agent: create invoice, send invoice, send payment reminder, create estimate and list unpaid invoices in your own Invoice2go account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Invoice2go yourself; Cotlet does not store your password and you need no Invoice2go API key. About the official Invoice2go API: Invoice2go publishes no public API or self-serve API keys; its integrations site lists a REST API only as "Request this integration" (checked 8 Nov 2026). It connects through built-in integrations and a Zapier app, and has no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/invoice2go-api-mcp-server
Every EmpirioLabs model and platform feature as tools: chat, media, search, jobs, GPU Cloud, agents.
Connect AI assistants to PingRelay to monitor websites and APIs, investigate incidents, retrieve uptime and response-time metrics, manage maintenance windows, and access status pages through the Model Context Protocol. Access: Requires a PingRelay paid plan with MCP access and an authorized API key.
Find buyers, run LinkedIn, email and X outreach, and answer replies from your AI.
The best prompt and the best model for the job, tested and improved by your coding agent.
TaxDome MCP server for ChatGPT, Claude and any AI agent: create job, request documents, send invoice, message client and list overdue tasks in your own TaxDome account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to TaxDome yourself; Cotlet does not store your password and you need no TaxDome API key. About the official TaxDome API: TaxDome has no public API that firms can use today (checked 14 Oct 2026). Its Zapier integration only creates, updates and finds contacts, and TaxDome MCP, which would let Claude or ChatGPT work in a firm account, is announced but not open yet and is offered to Professional and Business plan firms first. Setup and FAQ: https://cotlet.dev/integrations/taxdome-api-mcp-server
SnelStart MCP server for ChatGPT, Claude and any AI agent: create sales invoice, add relation, book entry, list open items and upload document in your own SnelStart account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to SnelStart yourself; Cotlet does not store your password and you need no SnelStart API key. About the official SnelStart API: Yes, but it is gated (checked 14 Oct 2026). SnelStart has a B2B API for software partners: you request a connection, get a development key and portal access, and a production integration for several users needs certification, OAuth, a webhook URL and at least five named customers. Setup and FAQ: https://cotlet.dev/integrations/snelstart-api-mcp-server
SingleOps MCP server for ChatGPT, Claude and any AI agent: create lead, list proposals, schedule visit, list unpaid invoices and list jobs in your own SingleOps account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to SingleOps yourself; Cotlet does not store your password and you need no SingleOps API key. About the official SingleOps API: SingleOps has a Lead Entry API only: "It is not a general-purpose job-creation or read/write API, and there is no native Zapier integration". The token comes by email to support (checked 9 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/singleops-api-mcp-server
ResMan MCP server for ChatGPT, Claude and any AI agent: list work orders, create work order, update work order status, list units and make-ready status, list leases, list move-outs, list prospects and list aged receivables in your own ResMan account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to ResMan yourself; Cotlet does not store your password and you need no ResMan API key. About the official ResMan API: ResMan has an API, but only for approved Integration Partners (checked 23 Oct 2026). A property manager cannot get a key for their own account, and ResMan has no official MCP server. Setup and FAQ: https://cotlet.dev/integrations/resman-api-mcp-server
PeopleHR MCP server for ChatGPT, Claude and any AI agent: list holiday requests, approve holiday request, decline holiday request, list employees, get employee planner, create task and run saved query in your own PeopleHR account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to PeopleHR yourself; Cotlet does not store your password and you need no PeopleHR API key. About the official PeopleHR API: PeopleHR has a REST API, the Access PeopleHR Integration API v4.0, but no official MCP server (checked 22 Oct 2026). The API covers 31 resources and 150 actions, mostly employee records, holiday and absence data, and every call needs an API key that an HR admin creates in Settings. Setup and FAQ: https://cotlet.dev/integrations/peoplehr-api-mcp-server
My PT Hub MCP server for ChatGPT, Claude and any AI agent: book session, add client, assign program, create nutrition plan and list clients in your own My PT Hub account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to My PT Hub yourself; Cotlet does not store your password and you need no My PT Hub API key. About the official My PT Hub API: My PT Hub publishes no public API. Its only connection is a Zapier integration sold as an add-on on Premium plans, mostly triggers plus adding clients (checked 8 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/my-pt-hub-api-mcp-server
Mariana Tek MCP server for ChatGPT, Claude and any AI agent: list classes, book reservation, cancel reservation, find customer and add class credits in your own Mariana Tek account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Mariana Tek yourself; Cotlet does not store your password and you need no Mariana Tek API key. About the official Mariana Tek API: Yes, but gated: Mariana Tek has APIs (Customer, Studio, Admin, Webhooks and more), and credentials go only to integration partners who sign the Developer Tools Terms of Service and to developers working with a single studio, with the studio owner included in the request; no official MCP server exists (checked 11 Oct 2026). A technical review of about 1 to 3 weeks may follow, and reporting data and Stripe data are not available through the API. Setup and FAQ: https://cotlet.dev/integrations/mariana-tek-api-mcp-server
Freshchat MCP server for ChatGPT, Claude and any AI agent: list conversations, read conversation, send reply, assign conversation, resolve conversation with label, list canned responses and get CSAT report in your own Freshchat account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Freshchat yourself; Cotlet does not store your password and you need no Freshchat API key. About the official Freshchat API: Freshchat has a REST API (v2) but no official MCP server (checked 22 Oct 2026). Freshworks' MCP integration covers Freshdesk and Freshservice, and its docs do not list Freshchat. Setup and FAQ: https://cotlet.dev/integrations/freshchat-api-mcp-server
Fortnox MCP server for ChatGPT, Claude and any AI agent: create invoice, send invoice, create customer, book voucher and list unpaid invoices in your own Fortnox account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Fortnox yourself; Cotlet does not store your password and you need no Fortnox API key. About the official Fortnox API: Yes, Fortnox has a public REST API with scopes for invoices, customers, vouchers and invoice payments (checked 14 Oct 2026), but it is not open by default: you register an integration, request scopes, and the company must hold the Fortnox licence each resource needs. Fortnox publishes no MCP server of its own. Setup and FAQ: https://cotlet.dev/integrations/fortnox-api-mcp-server
Expensify MCP server for ChatGPT, Claude and any AI agent: create expense, attach receipt, create report, submit report and approve report in your own Expensify account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Expensify yourself; Cotlet does not store your password and you need no Expensify API key. About the official Expensify API: Yes, but it is narrow (checked 14 Oct 2026). Expensify's Integration Server API creates expenses, creates reports (domain and policy admins, after enablement) and exports reports, with credentials you generate yourself. Setup and FAQ: https://cotlet.dev/integrations/expensify-api-mcp-server
Autotask MCP server for ChatGPT, Claude and any AI agent: search tickets, create ticket, update ticket, add ticket note, log time entry and find company in your own Autotask account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Autotask yourself; Cotlet does not store your password and you need no Autotask API key. About the official Autotask API: Autotask has a full REST API, and Kaseya publishes an official Autotask MCP server that is still in alpha (checked 6 Nov 2026). Both run as an API-only user with an integration code, set up by an admin, and the MCP server supports Claude only. Setup and FAQ: https://cotlet.dev/integrations/autotask-api-mcp-server
Absorb LMS MCP server for ChatGPT, Claude and any AI agent: list users, list course enrollments, list overdue learners, approve enrollment request, enroll users in a course, message learners, create user and deactivate user in your own Absorb LMS account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Absorb LMS yourself; Cotlet does not store your password and you need no Absorb LMS API key. About the official Absorb LMS API: Absorb LMS has an Integration API, a REST API with JSON for learners, courses, departments and grades, but it needs a private key tied to your portal that your Absorb account team provides, and your own code (checked 20 Oct 2026). Absorb's Aura MCP for Claude and ChatGPT is planned for 27 Oct 2026 and is read and answer only. Setup and FAQ: https://cotlet.dev/integrations/absorb-lms-api-mcp-server
17hats MCP server for ChatGPT, Claude and any AI agent: add contact, create project, send quote, send invoice and record payment in your own 17hats account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to 17hats yourself; Cotlet does not store your password and you need no 17hats API key. About the official 17hats API: 17hats publishes no public API. Its only key is for Zapier, on the new subscription plan, and that integration "is limited to importing, updating and syncing Contacts" (checked 9 Nov 2026). Setup and FAQ: https://cotlet.dev/integrations/17hats-api-mcp-server
Build Learnosity integrations from Learnosity's own documentation and integration skills.
Twitter (X) trends over time, with growth for any keyword. Free key at trendsmcp.ai
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.
Shiftbase MCP server for ChatGPT, Claude and any AI agent: list timesheet entries, approve timesheet entries, approve absence request, decline absence request, approve exchange request, list open shifts, list shifts and add worked hours in your own Shiftbase account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Shiftbase yourself; Cotlet does not store your password and you need no Shiftbase API key. About the official Shiftbase API: Shiftbase has a Public API for employees, schedules, time registration, clocks and reports, but no official MCP server (checked 22 Oct 2026). An admin installs the Public API tile in the App center to get a token, and every integration is code you write and run yourself. Setup and FAQ: https://cotlet.dev/integrations/shiftbase-api-mcp-server
Deliverect MCP server for ChatGPT, Claude and any AI agent: list orders, get order, retry failed order, snooze product, unsnooze product, set busy mode, add special hours and export orders in your own Deliverect account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Deliverect yourself; Cotlet does not store your password and you need no Deliverect API key. About the official Deliverect API: Deliverect has an API, but credentials go to integration partners, not to restaurants (checked 31 Oct 2026). A partner applies, builds in staging and passes certification before it gets production credentials. Setup and FAQ: https://cotlet.dev/integrations/deliverect-api-mcp-server
Bokio MCP server for ChatGPT, Claude and any AI agent: create invoice, send invoice, upload receipt, create journal entry and list unpaid invoices in your own Bokio account. Cotlet works in the account through your Cloud Browser, a real Chrome where you sign in to Bokio yourself; Cotlet does not store your password and you need no Bokio API key. About the official Bokio API: Yes, Bokio has a public REST API for invoices, customers, journal entries, uploads and supplier invoices (checked 14 Oct 2026), but it depends on your price plan and on the kind of integration: a private integration token works for one company only, and a tool that serves several companies must be registered as a public integration with OAuth 2.0. Bokio publishes no MCP server of its own. Setup and FAQ: https://cotlet.dev/integrations/bokio-api-mcp-server
Public procurement for AI agents: Chile tenders and Compra Ágil, fit, buyer and supplier history.
8pt makes any AI model ship professional-grade UI: curated components, full-page templates, themes, icons and Skills, delivered to Claude Code, Cursor, Codex and Trae through one MCP server and CLI. Hosted remote server: Streamable HTTP endpoint at https://8pt.dev/api/mcp, authenticated with the Authorization: Bearer <8pt API Key> header (users create keys at 8pt.dev > Settings > API Key, Builder plan). Docs: https://8pt.dev/docs/mcp/