Задачи и проекты

PhaseFolio

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Biotech rNPV / probability-of-success engine for AI agents.

• Get Project: Fetch a PhaseFolio project's metadata: indication, sub-indication, modality, biomarker, asset name, and stage at entry. Use this when you need to ground an analysis question in the projec
• List Scenarios: List all scenarios in a PhaseFolio project. Returns scenario IDs, names, created/updated timestamps, and top-line eNPV/rNPV. Use this to discover what scenarios exist before fetching o
• Get Scenario: Fetch a PhaseFolio scenario's complete inputs (stage costs, durations, PoS, commercial assumptions, IRA settings) and computed outputs (eNPV, rNPV, cumulative PoS, per-stage breakdown, t

Pinchwork MCP Server

Сбои

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

MCP server for Pinchwork - an agent-to-agent task marketplace with credits-based economy

PlanExe

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

MCP server for generating rough-draft project plans from natural-language prompts.

Planner MCP — provable "done" for AI agents

Сбои

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.

Plith Operations

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

The base layer for AI agents.

• Dedupq Check: Before executing any LLM task, check if an identical or semantically similar task has already been completed. Returns cached result on hit, saving one LLM call. On a miss, execute your t
• Dedupq Complete: After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check. Costs 2 credits.
• Burnrate Estimate: Before executing a multi-step agent plan, estimate the total LLM cost. Returns per-step breakdown and optimization suggestions. If the estimate exceeds your budget, pipe the same pl

Pod

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Search what agents actually experienced with a product, API, service, or place — firsthand observations recorded during real work, rather than what the…

• Find Mcp: Find canonical MCP servers by task, claimed or observed capability, name, source directory, client compatibility, transport, authentication posture, or deployment kind. Results stay compact,
• Inspect Mcp: Inspect one canonical MCP from find_mcp, including distinct upstream claims, deployments, Pod-observed tools, and selected decision-useful GitHub issues. GitHub reports remain separate fr
• Search: Search what people and agents actually experienced with a product, API, service, place, organization, or anything else. Use this before choosing, buying, integrating, visiting, or recommending

Poland Invoices (KSeF 2.0 national e-invoice API)

Сбои

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Poland KSeF 2.0 national e-invoices for AI agents: issue FA(3) faktura, query by KSeF number.

project-classifier

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Classify text or JSON input into structured categories using Claude AI — with no setup, no API keys, and no credentials required.

• Classify Content: Classify text or JSON into a category using Claude AI. Returns the top label, confidence score, ranked list of all labels, and an optional reasoning sentence.
• Classify Content Trial: Classify text using Claude AI (free trial — sentiment/topic only, 4KB max). Multi-label is always disabled. Use classify_content for full access.

Project Desk

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Agent-updated work tracker for builders directing AI across multiple projects.

Personal context and preferences for AI via OAuth-approved profile sections and taste data.

Project Gumball

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

One MCP server exposing every tool in the Gumball portfolio.

Identify the project handle from an intake note

project-little-weirdo

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Deterministic public-web change observation with evidence-bound commercial interpretation.

Project Paced

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

AI project timelines & Gantt charts, plus enterprise resourcing, capacity & weekly status reporting.

project-substitute-arena

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

AI agents replace the CEO of Toys R Us (2006-2017).

project-summarizer

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

x402 Text Summarizer compresses text, Markdown, or JSON into structured summaries using Claude AI.

• Summarize Text: Compress text, Markdown, or JSON to a structured summary using Claude AI. Returns summary text, word count, and compression ratio. Set explain=true to receive notes on what was omitted
• Summarize Text Trial: Compress text to a prose summary using Claude AI (free trial — prose only, 4KB max). Use summarize_text for bullets, headline, tldr formats or larger inputs.

Task tracking built for coding agents.

Prompt Injection Scanner MCP - LLM Security Testing

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

PromptGuard Scan MCP helps SaaS teams test LLM applications for prompt injection, jailbreaks, indirect prompt injection, hidden instruction leakage, unsafe…

• Get Site Profile: Return PromptGuard Scan identity, MCP URL, data boundaries, and capability tags.
• Get Health Status: Return route, asset binding, analytics binding, and payment configuration health.
• Get Pricing Catalog: Return the public PromptGuard Scan plan catalog.

PulseNetwork

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

73 specialized intelligence APIs (825 endpoints) in one server.

• Alphapulse: AlphaPulse: Global alternative trading intelligence API. AI-synthesized signal provider rankings, managed account analysis, copy trading discovery, expert advisor (EA/robot) vetting, multi
• Arbipulse: ArbiPulse: 12 endpoints scanning arbitrage opportunities across DeFi yield spreads, DEX price differentials, perpetual funding rates, sports surebets, ETF/NAV gaps, and commodity regional p
• Autopulse: AutoPulse: Automotive intelligence API — 10 endpoints powered by NHTSA, EPA, and live market data. Safety recalls, reliability analysis, DIY repair guides, vehicle comparison, market value,

Pushary

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Push notifications and human-in-the-loop approvals for AI agents.

• Send Notification: Send a one-way push notification to the user's phone and browser. Nothing is awaited; use ask_user instead when you need an answer back. Reach for this when a long-running task fini
• List Subscribers: List push notification subscribers for the site, with optional filters. Use it to find who can receive notifications, look up a subscriber ID for targeted delivery, or audit subscrip
• Get Subscriber: Get full details of a single subscriber by ID: browser, OS, location, tags, subscription status, and activity. Use it to inspect one recipient before targeting them or to debug why a d

PyAI — Voice AI

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Build voice agent profiles, generate text-to-speech (TTS), transcribe audio with speech-to-text (STT), and translate recordings with Dubbing.

• Get Started: Return a concise, correct quickstart for building with PyAI (auth, SDK install, TTS/STT/realtime snippets, error handling). No key or network needed, read this before writing PyAI code so
• Whoami: Introspect the active key (GET /v1/me): org, environment (test/live), granted scopes, and rate-limit/credit posture. Use it to self-diagnose a 401/403/402.
• List Models: List the available PyAI models (catalog). No arguments.

Multi-agent governance: task orchestration, compliance, decision validation, and ML predictions.

OAuth-protected, read-only-by-default MCP server for provenance-labeled QuillCaddie project memory.

radtask-mcp

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

AI task cockpit: an agent does your tasks and asks before anything irreversible.

Design a React Native app in a browser and emit it as a real Expo project you own, iOS and Android.

Brain dump, routines, task planning, focus, and instant thought retrieval

RelayMarket

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Agent-to-agent marketplace for AI task discovery, matching, delivery, and trust.

remnus

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

MCP-native open-source Notion alternative: read & write pages, databases and kanban boards.

RentHuman

Работает

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключением

Hire real humans in Russia for physical-world tasks: storefront photos, address verification, offline errands.

• Get Balance: Get your RentHuman balance in USDT. RentHuman is a marketplace where AI agents hire real humans in Russia for physical-world tasks: photos of storefronts, address verification, offline er
• Create Task: Create a task for human executors. Cost = reward × max_executors × 1.2 (20% platform fee), charged from your balance into escrow. Write title and description IN RUSSIAN, clearly, with acc
• List Tasks: List all your tasks with statuses: open (accepting applications), in_progress (slots filled), paused, completed, cancelled.

Publish HTML & Markdown to shareable links with versions, comments, and project organization.