Official HostTracker MCP server: run uptime, SSL, DNS, blacklist and page-speed checks from 300+ global locations, and manage monitors, alerts, incidents and status pages.
Scheduled watchdog for x402 sellers: polls Coinbase CDP's public Bazaar discovery catalog for your registered resources and payTo address, flagging a drop or a recovery — instead of finding out from a revenue dip days later. **How it works:** register a payTo address and resource URLs once; a scheduled poll diffs them against the live discovery catalog and alerts on a state change. The `check_listing_health` MCP tool runs the same scoped diff on demand, whether or not a payT
Let AI agents accept payments in Mexico (MXN) — OXXO cash vouchers, SPEI bank transfer, cards, Mercado Pago wallet — via Mercado Pago Checkout Pro. Stateless, bring-your-own credentials (x-mercadopago-access-token), never holds funds. Owner policy guardrails: x-agentpay-max-amount / x-agentpay-approval-above.
Let AI agents accept payments in Uruguay (UYU) — cards, Abitab / Redpagos cash, Mercado Pago wallet — via Mercado Pago. Stateless, bring-your-own credentials (x-mercadopago-access-token), never holds funds. Owner policy guardrails: x-agentpay-max-amount / x-agentpay-approval-above.
WhenPeak tells your agent when its human peaks, when to protect the dip, and how ready they are today, so it can schedule work around real capacity instead of treating every hour as equal. Returns the peak window, natural dip, secondary peak, readiness score and chronotype from sleep. Also projects a 7 to 30 day outlook, finds today's best slot for analytical, creative, learning or administrative work, and reports whether right now is a peak or a dip. Built on the Two-Proce
Every agent debugs alone. Fixes die in the conversation. knownissue is the shared memory where they don't have to. When your agent hits a bug, it searches knownissue first. If another agent already solved it, yours gets the fix instantly. When your agent solves something new, it reports the fix so the next agent doesn't start from scratch. **5 tools:** - `search` — find known issues by error message or library context - `report` — report a new issue with an optio
MemoryRouter is a persistent AI memory layer delivered as an MCP memory server. Connect this server to Claude, ChatGPT, Cursor, or any MCP client and your assistant gets user-scoped, cross-AI memory: store memories, search them semantically, and carry context from one session and one tool to the next. Move useful context from ChatGPT to Claude, keep decisions and preferences across sessions, and give agents memory that survives compaction. Sign up at https://memoryrouter.ai,
Simple memory for AI: keep, recall, update, and forget information across sessions. Maindex Smart is a user-controlled memory layer for AI assistants. It lets you persist useful information like preferences, decisions, notes, and project context, then retrieve it later without repeating yourself. Core tools: - keep — save something worth remembering - recall — find relevant memories when you need them - update — revise existing information - forget — remove or permanently d
Stores important facts, decisions, and patterns for persistent access across different sessions. Retrieves relevant historical context instantly through semantic search to maintain continuity. Organizes your knowledge base by archiving outdated information while keeping the most useful insights accessible.
Artel is a self-hosted, self-organizing mesh for AI agent fleets — shared memory with embeddings, session continuity (handoffs across context resets and machines), agent-to-agent messaging, tasks/events, cross-instance feed meshing with no central coordinator, and an async archivist that synthesizes connections no single agent can see. Any HTTP-capable agent participates: Claude Code, AutoGen, raw API scripts. **Hosted-backend model:** you deploy one Artel instance (Docker)
Save, search, and format memories with semantic understanding. Enhance your memory management by leveraging advanced semantic search capabilities directly from Cline. Organize and retrieve your memories efficiently with structured formatting and detailed context.
WorkingMemory is a private, cloud-synced persistent memory that builds your personal knowledge base as you go, so you can stop re-explaining yourself when moving a task between AI chats.
Most AI tools give you a chatbot. We give your AI a brain. Hjarni is a clean, simple knowledge base with a built-in MCP server. Your AI reads your notes, follows your instructions, and remembers what you told it, across every conversation. Stop repeating yourself. Start building a knowledge base that works twice: once for you, once for your AI.
Cross-tool AI memory that recalls first every turn and admits when it doesn't know. Every recall passes an anti-confabulation gate (answer | verify | abstain) — it abstains rather than guess. Eight tools: Memory Write, Memory Recall, Playbook Recall, Gated Recall (abstains when unsure), Verified Recall (high precision), Memory Feedback (label a recall decision), Memory Search, and Fetch Memory — full parameter-level reference at https://ultramemory.io/docs/tools/. Connect wit
Generate PDFs from HTML templates via AI agents or API. List templates, submit jobs with JSON data, check credits, and generate watermarked previews — all through MCP tools. Templates support LiquidJS templating with conditionals, loops, and raw variable injection.
Machine-first AI Agent digital goods marketplace enabling autonomous purchases of APIs, Datasets, Prompts, and Tools via the x402 Payment Protocol on Base and Remote MCP.
Publish Markdown or HTML straight from your AI agent and get back a live, shareable URL — no repo, no build, no deploy. Pages are served from a hardened, cookieless host, and the agent keeps control after publishing: list your pages, update one in place (the URL, view counts, and expiry all survive), or delete it. Free links last 7 days; paid plans add permanent links, custom slugs, password protection, and no dochost branding.
Read PDFs and images into agent context as markdown or plain text. $0.75 per 1,000 pages with exact per-call cost reporting, a free cost estimator, and spend caps." — homepage https://pennyocr.com
A markdown writing workspace your AI can actually write in. Connect an agent to search, read, draft, suggest edits you approve, comment, and publish to WordPress/Ghost/Sanity — in the same live documents you edit, with every agent edit signed and yours to accept or reject. A knowledge base you own and can actually read, not an opaque store.
Transforms Markdown content into professional PDF slide decks instantly. Provides comprehensive layout specifications to help users craft visually appealing presentations with ease. Delivers public links for sharing finished decks without requiring complex design software.
Access web content in markdown format reliably and efficiently. Unblock web pages and search the web seamlessly, enhancing your agents' capabilities. Integrate with your scripts and applications to leverage markdown delivery like a CDN.
Enable AI assistants to perform real-time web searches, extract data from web pages, map website structures, and crawl websites systematically. Enhance your AI's capabilities with powerful tools for intelligent data retrieval and analysis from the web. Seamlessly integrate advanced search and extraction features into your MCP client workflows.
Provide real-time, detailed information about U.S. National Parks including park details, alerts, visitor centers, campgrounds, and events. Enable users to search parks by location, activities, and other criteria to plan visits effectively. Access up-to-date alerts and operational information to enhance trip planning and safety.
Search Booking.com stays by destination and dates, and read a single property in full, as structured JSON. Runs on HasData's hosted API.
Enable real-time web search and data extraction capabilities.
Integrate Mapbox's powerful navigation and search capabilities into your applications. Access directions, travel matrices, and geocoding services seamlessly. Enhance your projects with real-time mapping functionalities using this server.
Live zoning intelligence from county council meetings: search hearings, rezoning decisions, and vote records across 160+ US counties
Search and retrieve cryptographically-verified compliance nodes. 9500+ nodes across 39 pillars, including a MITRE layer across 6 frameworks (ATT&CK Enterprise, ATT&CK Mobile, ATT&CK ICS, D3FEND, ATLAS, CAPEC) - AI Governance, Banking & Global Finance, Cybersecurity, Medical & Healthcare, Legal & IP Sovereignty, ESG and more. Zero hallucination: every node traces to primary legal sources with avg 7 citations.
Free, keyless demo of the Geomelon geographic API — city autocomplete with multilingual names across 50 languages, no signup or API key required. This hosted instance exposes one tool: `search_cities_autocomplete` (country-scoped, language-specific city name prefix search). For the full 22-tool set (countries, regions, languages, compound lookups) install the npm package with your own free [RapidAPI key](https://rapidapi.com/hom3chuk/api/geomelon): `npx -y geomelon-mcp`.
Check internet providers, plans, speeds, and known pricing at a specific U.S. street address.
Explore the rich cultural heritage and attractions of Korea. Access detailed tourism information, including attractions, festivals, and accommodations tailored to your interests. Easily search for tourism content based on area codes, keywords, or locations to plan your perfect trip.
Find places and addresses with precise geocoding, or search by category or brand. Plan routes and compare travel times using directions, isochrones, and distance matrices. Generate static map images to visualize locations and share context.
Read-only, source-linked news intelligence for AI agents. Search The Neural Ledger stories, compare sources, validate events, map asset exposure and operational risk, and generate cited weekly briefs through six OAuth-protected MCP tools.
Two capabilities in one server. RESEARCH: query a compliance knowledge graph of 723 frameworks, 20,473 controls and 332,959 cross-framework mappings. Search frameworks and controls, map controls between two standards, and run coverage analysis. ACT: search a catalogue of 314,000+ self-paced professional courses by need, framework, role or industry, and hand the user a direct purchase link. One tool answers the query a product listing cannot: which courses cover two or more
India's first Land Intelligence MCP Lookup survey numbers for any location in india
MCP server for accessible indoor navigation and building management. Query buildings, floors, rooms, elevators, and parking spaces. Calculate barrier-free routes, search facilities, and submit accessibility feedback. Supports 26 tools, 10 prompts, and 25 resources for comprehensive building data access.
Discover live sponsorship availability on **Kann KI das?**, the German AI software build-or-buy platform. Lists ten fixed slots and creates a Stripe-hosted checkout only after explicit buyer confirmation of the €990 net price and 30-day term. - Read-only slot discovery without authentication - OAuth-protected checkout creation - Buyer confirmation and idempotency enforced - Stripe Checkout and verified webhooks
Let AI agents ship parcels in the UK — create Royal Mail Tracked shipments, buy labels, track and refund. Stateless remote MCP server: bring your own Shippo API key, it never holds funds or stores data.
Hosted ambient memory for AI agents. Retrieve context and save notes via MCP tools with OAuth.
Haldir is a security and governance layer for AI agents. Session-scoped permissions (Gate), encrypted secret storage (Vault), and tamper-evident audit logging (Watch).
# Hevy MCP (unofficial) This unofficial MCP server provides secure access to your Hevy fitness data through the Hevy API. AI assistants can analyze your workout history, manage routines, track progress, and help you plan future training using your real fitness data. ## Features - View workout history and training statistics - Create and update workouts - Access and manage workout routines - Browse exercise templates - Organize routines with folders - Track training progres
An open-source agent that observes & fixes your application. Query logs, traces, metrics, incidents.
Bug reports with the full context already attached — console errors, network requests, interactions, and the screen recording — read straight from your agent, without opening the dashboard. Point it at a domain you've claimed in Session Replay and it can search the reports filed against it, read one in full, pull a still from the recording at the exact moment something failed, and move the report through triage. **Tools** - `list_domains` — the domains this account can rea
Deterministic sequence enforcement for AI agents: ALLOW or DENY a step before it runs, sealed into an Ed25519-signed, hash-chained receipt that verifies offline against published keys. No signup, no key needed to try.
DNS analytics and optimization. Debug DNS issues and optimize performance based on your setup.
DoneThat automatically tracks all work and uses this context to boost your productivity: Automated timesheets, long-term memory for AIs, proactive coaching, and social sharing for accountability and remote trust. DoneThat is built privacy-first, cross-platform, and takes five minutes to set up.
Capture and report bugs with automatic screen recordings and environment details. Create, view, and manage bug reports with full context.
AI Gateway management. Search logs, inspect prompts and responses, and monitor AI traffic.