Task-scoped email inboxes for AI agents: read mail, extract verification codes, and reply.
Серверы с HTTPS-адресом: ничего не нужно ставить на компьютер, достаточно вставить ссылку в настройки клиента. Доступность проверяем по расписанию.
Generate launch-ready SaaS blueprints with MantleKit.
- Recommend Setup: Recommend the best MantleKit tier, theme, and built-in feature set for a new app idea.
- Generate Project Blueprint: Turn an app idea into a launch-ready MantleKit project blueprint with pages, dashboard sections, entities, and MVP scope.
- Match Theme: Recommend the best MantleKit theme for a product type, audience, and brand direction.
Project-scoped marketing ops for agents: Bearer dpk/dpa or OAuth, read and supervised write.
Custom domains for SaaS and AI agents: search, register, connect DNS, and issue HTTPS over MCP.
AI-native project management + agent memory: tasks, sprints, risk, burnout, knowledge search.
Chilean DTE/SII invoicing — issue invoices, reconcile payments and manage clients with AI agents.
Issue signed receipts for AI agent actions; verify any receipt offline - free, no account.
Search 31,000+ MCP servers by task, tool or tag, get install configs, and submit new servers.
Search 77,000+ MCP servers ranked by real adoption data to find the right one for any task.
Mcpgram — единый шлюз MCP для подключения GitHub, Slack, Asana, Salesforce и других сервисов
- Искать инструменты среди всех подключённых сервисов и MCP-серверов
- Получать схему аргументов конкретного инструмента
- Выполнять отдельные вызовы, пакеты вызовов и цепочки-воркфлоу
mcptask.online: автономные AI-разработчики на вашей инфраструктуре берут задачи и присылают пул-реквесты
- Ставить задачи, эпики и истории с зависимостями между ними
- Получать следующую задачу и фиксировать прогресс по ней
- Логировать время выполнения и выгружать табели в CSV
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
The SQLite of AI Memory — persistent, zero-dependency memory for any LLM application.
- Remember: Store a new memory in MemoryMesh. Use this to save facts, preferences, decisions, or any information that should persist across conversations.
- Recall: Recall relevant memories from MemoryMesh using semantic similarity and keyword matching.
- Forget: Permanently delete a specific memory by its ID. Searches both project and global stores.
https://mempalace-mcp.vercel.app/ — Register or sign in here first to create your API key (mpk...).
- Mempalace Status: Summarize the current user's memory palace: total drawers, counts per wing, counts per room. Use when you need grounding before writes or searches, or when the user asks what is stor
- Mempalace Add Drawer: Persist a new memory drawer: writes to the user's D1 row, then embeds and upserts to Vectorize for later semantic search. Use when the user wants to remember something long-term
- Mempalace Search: Search the current user's memories by meaning (Vectorize embeddings), optionally scoped to wing and/or room. Use when answering questions that depend on prior stored context, or befo
Shared project memory that keeps teammates and AI agents aligned across sessions.
Memxus is multi-platform persistent memory for AI assistants.
- Remember: Save important information to long-term memory. Always set collection when the topic is clear: project work → project:<slug>, personal tastes → personal:preferences. Use append_to to extend
- Recall: Search long-term memory. Pass collection (and/or tags, type) to search only that scope — e.g. collection=project:henry-memory for project questions, collection=personal:preferences for tastes.
- Get Context: Build a formatted context block for the current topic. Use collection to limit results to one domain (project, preferences, etc.).
The place for race shirts and team merch.
- Create Task: Post a new task to the bench. REQUIRES INK FUNDING: ink_reward x max_claims deducted. Returns task_id and remaining balance.
- Create Batch: Post multiple tasks at once. REQUIRES INK FUNDING for sum of all task costs.
- Get Balance: Check ink balance for a funding email.
Persistent memory, task coordination, and HITL queue for AI coding sessions.
Inspect selected project excerpts and screen user-confirmed facts for bounded EU AI Act readiness.
Find a live agent by describing the task, then call its skills.
Microsoft To Do (Microsoft 365) MCP Pack
Monday.com MCP — wraps the Monday.com GraphQL API (BYO API key)
Manage customers, reviews, requests, and reputation for one More Good Reviews project.
Grant, investor, and policy narrative generation for conservation and climate work — turn project data into funder-ready stories.
- Translate Narrative: Translate raw ecological/agent data into a decision-maker-ready narrative. audience_type: board_member | general_public | grant_funder | institutional_investor | journalist | poli
- Describe Agent: Fleet-standard self-description: capabilities, inputs, outputs.
EU Horizon Europe R&D grant intelligence over 27,000+ CORDIS projects and 59,000+ organisations.
- Find Matching Grants: Find EU Horizon grants matching a description of your organisation or project. Returns top grants with budget, timeline, coordinator, and topic code. To score a specific consorti
- Search Grants: Full-text search across 21 000+ Horizon Europe projects. Returns ranked results with title, budget, start date, and an objective snippet.
- Get Project Detail: Returns full details for a single CORDIS project by RCN identifier, including budget, coordinator, top partners, and full objective.
JSON/YAML, regex, diff, JWT, SQL dialects — the keyless millisecond ops an agent needs mid-task.
Company and people intelligence from a single API.
- Run Research: Starts the full NeuralVerge AI research workflow (multi-step search, analysis, and structured reporting) and returns a session_id immediately. Poll get_session_status with that session_i
- Get Session Status: Returns the current status of an AI Research session (queued/running/complete/failed) and the final result (human-readable summary plus machine-readable JSON) once processing compl
- Run Search: Runs a synchronous web search and returns a structured list of ranked results (title, url, snippet) immediately, without polling.
Live global news signals derived from the GDELT Project across 65+ languages, updated every 2 hours.
- Get Trending: What's surging in global news right now: topics whose coverage is ≥2 standard deviations above their trailing average (z-score), the biggest week-over-week movers, and surging countries.
- Get Topic: Live media-coverage statistics for one geopolitical topic (e.g. 'ukraine-war', 'taiwan-strait', 'sanctions'): 90-day daily volume and tone series, z-score, week-over-week change, and a samp
- Get Country: Live media-coverage statistics for one country by ISO-3166 alpha-2 code (e.g. 'ua', 'cn'): 90-day daily series of coverage volume (share of world news coverage that is about that country)
Typed, datasheet-sourced spacecraft component specifications: 2,500+ flight hardware products across 24 categories (reaction wheels, star trackers…
- Match Components: Reverse search over a typed spec layer: pass a category and engineering requirements, get every catalogued item grouped as A (meets all stated requirements), B (fails a named require
- Build Budget: Engineering budget for a component stack: pass product ids (from the other tools) and your bus voltage, get total mass, total steady-state power, per-item data interfaces, voltage-compat
- Get Component Specs: The full typed layer of a category — every item with every value (number, canonical unit, bound, measurement condition, datasheet source page, confidence L0/L1) plus the property
NEXUSRUN: деплой приложений, базы данных и бэкапы прямо из Claude, Cursor или Codex
- Разворачивать приложения из Docker-образа или Git-репозитория
- Управлять секретами, доменами и масштабированием деплоя
- Делать бэкапы баз данных и восстанавливать их из снапшота
Не нашли нужный коннектор?
Расскажите, какой сервис вам нужен, или добавьте свой MCP-сервер: проверим и опубликуем в каталоге.
Предложить коннектор