Agent Directory
Browse 160,118 AI agents
2881–2928 of 160,109
By ai.daiku
Your own browser in the cloud, logged in to your sites, shared by you and your AI.
- official
- remote
- mcp
By ai.devicelink
Read and search folders on your own computer with explicit consent. Files are never uploaded.
- official
- remote
- mcp
By ai.cardboard
Edit your own videos by chatting in Claude or ChatGPT: cut, caption, add music and export.
- official
- remote
- mcp
By webgraphic
Create a new Pondchat video room and return the shareable URL.
- Smithery skill
- Skills
By webgraphic
Join an existing Pondchat room by ID or full URL.
- Smithery skill
- Skills
By timothy-walton45
the paid API router for AI agents. One proven job first: URL-to-Markdown at $0.001 USDC per accepted read on Base via x402 (96 settlements and counting). Underneath: web research, provider trust, stock quotes, FX conversion, fact verification, and prediction-market intelligence — all pay-per-call, no subscriptions, no API keys. Built by ScriptMasterLabs (SDVOSB). Caller controls spend. SML never holds your keys.
- local
- mcp
By koulis
Koulis MCP is an open Model Context Protocol server that acts as a neutral aggregation layer between AI agents and restaurant management systems. Rather than locking into a single PMS, Koulis provides a unified booking interface that any reservation system can connect to as a provider, and any LLM can consume as a client. The protocol currently exposes 4 tools: discover restaurants with live availability, browse time slots, create a reversible 5-minute hold, and confirm with customer details. The 2-step flow ensures users always approve before a booking is finalized. PMS vendors connect via the Koulis Connector API — a standardized interface for pushing availability and receiving reservations. AI agents connect via MCP over Streamable HTTP (public endpoint, no API key required) or stdio for local development. Currently serving indie restaurants in France. Open to any PMS integration.
- remote
- official
- mcp
By hello-ddxh
Elenca i calcolatori, le guide, le risorse e i cataloghi pubblici del sito ufficiale. Cerca nell’indice pubblico della Matrice del Destino. Restituisce metadati e statistiche oggettive per una pagina pubblica indicizzata.
- remote
- mcp
By transopt
AI dispatcher for food delivery and other same-day local deliveries. Give Delopt your restaurant, store or depot, your drivers and the pending orders (street addresses or coordinates). It decides which driver takes which orders, in what sequence, and when each should leave, so customers wait as little as possible and hot or chilled food arrives fresh. Plans include per-stop ETAs and each order's wait against its promised time. Works just as well for groceries, pharmacy, flowers and parcels. It can also sequence a single driver's departure and look up addresses. Sign in with OAuth or use a Delopt API key.
- remote
- mcp
By maxim-pkk
Continuous mandate enforcement for AI agents: every proposed action is checked against a signed mandate BEFORE it happens, not once at signing. Six rules in fixed order - amount, payee, audience, currency, validity window, intent - so a refusal names the most important reason. Deny-by-default, with an append-only ledger and a tamper-evident chain fingerprint. Stops an agent from overspending, paying the wrong recipient, or acting after the mandate expired. Free tier 100 checks/day; beyond that pay-per-call via x402 on Base. HTTP + MCP endpoint: https://drift.rta.lat/mcp
- remote
- mcp
By scott-zj62
sncro is a lightweight MCP relay and framework plugin system that lets AI coding assistants (Claude Code, Cursor, Copilot) inspect a live browser during development. Instead of asking you for screenshots, Claude calls MCP tools to query the DOM, read console logs, check network timing, or pull a page snapshot — all against your actual running app. Drop-in middleware for FastAPI and Flask today; Django, Express, Next.js, Rails welcome as community PRs. Debug-only (zero code in production). Free tier + hosted relay at relay.sncro.net, or self-host from the MIT-licensed source.
- remote
- mcp
By kamolc4
MCP server for the Swagger Petstore API with 19 tools. Generated from OpenAPI using MCPForge with security scoring, tool permissions, audit logging, and hosted deployment.
- remote
- mcp
By hristovdimitri2
**Paid REST + MCP API for live crypto market intelligence on Base.** Pay-per-call in USDC via **x402** — no API keys, no subscriptions. Tools: - `get_market_stats` — market activity, daily stats, live market data (CoinGecko, DEXScreener, Fear & Greed). Paid via x402. - `get_onchain_sales` — real on-chain sales history (USDC transfers to the Kristo fee receiver). Paid via x402. - `get_bot_status` — Telegram bot integration status. Paid via x402. MIT-licensed. Docs: https://kristo-intelligence-api.onrender.com/llms.txt
- remote
- mcp
By touseonx2
## What is Oathlayer? Oathlayer is an independent verification layer for AI outputs. It checks answers against independent real-world sources and returns a trust signal before anyone acts on them. It works with any AI model. ## How it works Every question goes through a verification pipeline. The answer is checked against trusted web sources, scored on source consensus, and given a plain tag and a permanent doc reference number. ## Trust states - Oath Approved: passed verification, use it freely - Threshold Not Met: strong answer, your call to check it - Various Perspectives Apply: open to opinion, Oathlayer stays neutral - Complex Question, Threshold Reserved: specialist question, recommend checking - Clarity Needed to Continue: the question was not clear enough to check Fast-changing answers (scores, prices, weather, populations) carry a note that the result may have changed. ## Legal citation checks One feature is checking legal citations against official court and legal sources for the US, UK, Canada and Australia. Oathlayer confirms a citation, flags a mistaken one and shows the correct citation, or says it could not be found. ## Verify for free Every answer gets a unique doc number. Anyone can verify for free at oathlayer.com/verify, no account needed. ## For agents Tool: verify output (question, API Key). Remote server: https://mcp.oathlayer.com ## Pricing Pay for what you use. Full details at oathlayer.com
- remote
- mcp
By ttrpg
# Grimoire Grimoire turns your TTRPG campaign into a structured, queryable database and knowledge graph and exposes it to any MCP-compatible AI client. Your campaign becomes first-class context for whatever client you bring. ## What it does This server connects an AI client to a live Grimoire campaign through 41 tools across six surfaces: - **Entities** — 14 typed schemas (NPCs, locations, factions, quests, items, creatures, lore, vehicles, and more) with full CRUD and batch creation - **Knowledge graphs** — Traverse and edit the relationship web: who allies with whom, which faction holds which ground, who knows what about whom - **Wiki pages** — Block-based rich content with embedded entries and hierarchical structure - **Open threads** — Track unresolved obligations, debts, and promises with session-anchored progressions - **Campaign bible and constitution** — Surface the immutable truths of your setting (gods, magic rules, history, canon) so the AI stops contradicting your world - **Search and catalog** — Full-text search across the campaign, plus discoverable field options and tag taxonomies for downstream tool calls ## Who it's for GMs and worldbuilders running multi-session campaigns who want their AI assistant to actually know their world, not invent generic fantasy that contradicts established canon. Works for any genre: Fantasy, Sci-Fi, Post-Apocalyptic, Horror, Modern/Urban, Superhero, or Historical, with stackable facets (Cyber, Mecha, Mystery, War, Survival) layered on top. ## What you can ask your client - "Parse my session 12 notes into NPCs and link them to the right factions." - "How would Queen Mira react if her brother betrayed her?" - "Show every NPC connected to House Vale, sorted by faction loyalty." - "What does Queen Mira know about the missing prince?" (respects DM-only secrets) - "Add Eldric the innkeeper. Gambling debts to House Vale, met the party in session 4." - **Visibility-aware.** Three tiers (DM-only, player-knowledge, common-knowledge) wrap every read. DM secrets stay DM secrets even when players are the ones querying through their own client. ## Setup 1. Click connect — Smithery handles the OAuth flow with ttrpg.bot. 2. Sign in to your Grimoire account and pick which campaign to grant access to. 3. Start asking your client about your world. A free tier covers one campaign with unlimited entities and the full MCP surface. Paid plans unlock unlimited campaigns, custom fields, and additional storage. ## Links - [Grimoire homepage] (https://www.ttrpg.bot/) - [MCP overview and use cases] (https://www.ttrpg.bot/mcp/) - [Setup documentation] (https://www.ttrpg.bot/docs/mcp/)
- remote
- mcp
By ermine-G7Ya
Automatically parses typescript's official documentation making it accessible for agents to use.
- remote
- mcp
By r-space-technology-ltd
R.Space — the real estate OS for the UAE. The platform powers every side of the UAE property market: 2100+ off-plan projects direct from developers, the full secondary (resale) market, real-time price and availability tracking, broker tools and transactions, ROI analytics, and a connected marketplace of services around property — interior design studios, furniture brands, construction and fit-out companies, property management. This MCP is the AI-agent gateway into the platform. Through the server your agent can: • Search off-plan projects and resale listings — filter by price, location, developer, handover, bedrooms, furnishing • Compare up to 5 properties side-by-side with investment / end-use / luxury / family lens • Calculate ROI including DLD, agent commission, and NOC fees • Pull live market stats by district — average price, ranges, project counts, new launches • Find licensed brokers and agencies Grounded in live data from [rspace.ae](https://rspace.ae). Free, read-only, no auth. 30 req/min per tool.
- remote
- mcp
By garasegae
Agent-first skill marketplace with USK (Universal Skill Kit) open standard. Search, evaluate, and install skills for AI agents across 7 platforms including Claude Code, OpenClaw, Cursor, Gemini CLI, and Codex CLI. Agents discover skills via API with trust-level filtering (verified/community/sandbox). No auth required for reads.
- remote
- mcp
By MaziyarPanahi
mergekit-slerp-rcoqutv-GGUF is an open-weight text-generation model published by MaziyarPanahi on the Hugging Face Hub. It has 269 downloads. Runs with transformers.
- Text generation
- Conversational
- GGUF quantised builds
- +1
- Research
- Productivity
By featherless-ai-quants
Ppoyaa-KunoichiVerse-7B-GGUF is an open-weight text-generation model with roughly 7B parameters published by featherless-ai-quants on the Hugging Face Hub. It has 252 downloads.
- Text generation
- Conversational
- GGUF quantised builds
- +1
- Productivity
By MaziyarPanahi
patricide-12B-Unslop-Mell-GGUF is an open-weight text-generation model with roughly 12B parameters published by MaziyarPanahi on the Hugging Face Hub. It has 252 downloads.
- Text generation
- GGUF quantised builds
- 12B parameters
- Writing
By MaziyarPanahi
Kosmos-EVAA-gamma-light-8B-GGUF is an open-weight text-generation model with roughly 8B parameters published by MaziyarPanahi on the Hugging Face Hub. It has 252 downloads.
- Text generation
- GGUF quantised builds
- 8B parameters
- Writing
By unsloth
Seed-Coder-8B-Instruct-unsloth-bnb-4bit is an open-weight text-generation model with roughly 8B parameters published by unsloth on the Hugging Face Hub. It has 252 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- +1
- Coding
- Productivity
By enes1987
Qwen3-0.6B-Gensyn-Swarm-freckled_bellowing_pelican is an open-weight text-generation model with roughly 0.6B parameters published by enes1987 on the Hugging Face Hub. It has 252 downloads. Runs with transformers.
- Text generation
- Library: transformers
- 0.6B parameters
- Writing
By QuantTrio
Kimi-Dev-72B-GPTQ-Int4 is an open-weight text-generation model with roughly 72B parameters published by QuantTrio on the Hugging Face Hub. It has 252 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- +1
- Coding
- Productivity
- +1
By baa-ai
MiniMax-M2.7-RAM-100GB-MLX is an open-weight text-generation model published by baa-ai on the Hugging Face Hub. It has 268 downloads. Runs with mlx.
- Text generation
- Conversational
- Library: mlx
- Coding
- Productivity
By k0valik
Qwen3.6-27B-Omnimerge-v4-IQ4_XS-12.76GiB-GGUF is an open-weight text-generation model with roughly 27B parameters published by k0valik on the Hugging Face Hub. It has 260 downloads. Runs with gguf.
- Text generation
- Conversational
- GGUF quantised builds
- +2
- Coding
- Research
- +2
By sifat-febo
bangla-banglish-companion-gguf is an open-weight text-generation model published by sifat-febo on the Hugging Face Hub. It has 252 downloads. Runs with gguf.
- Text generation
- Conversational
- GGUF quantised builds
- +1
- Productivity
By aifeifei798
Heretic-Scalpel-TriTier-E2B is an open-weight text-generation model with roughly 2B parameters published by aifeifei798 on the Hugging Face Hub. It has 252 downloads.
- Text generation
- Conversational
- 2B parameters
- Coding
- Productivity
By OpenAI
OpenAI image model for production generation, edits, and brand-safe visual workflows. Weights are not publicly released; access is via the provider API.
- Image generation
- File attachments
- Image input
- +1
- Design
By Yunhao-Feng
AdaGuard-8B is an open-weight text-generation model with roughly 8B parameters published by Yunhao-Feng on the Hugging Face Hub. It has 262 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- +1
- Productivity
By yuxuanw8
qwen3b-racpo-v2-fisher-acc-hotpot-2device-collate-0.75-0.25-final is an open-weight text-generation model with roughly 3B parameters published by yuxuanw8 on the Hugging Face Hub. It has 260 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- +1
- Productivity
By Z-L-Leo
my-sft-model-20260930-224915 is an open-weight text-generation model published by Z-L-Leo on the Hugging Face Hub. It has 261 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- Productivity
By peikoff
objectivist-phi4-CP-SFT-merge-GGUF is an open-weight text-generation model published by peikoff on the Hugging Face Hub. It has 266 downloads.
- Text generation
- Conversational
- GGUF quantised builds
- Productivity
By rmehra007
gemma-sql-merged is an open-weight text-generation model published by rmehra007 on the Hugging Face Hub. It has 261 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- Productivity
By francesca9805
zho-hans-100mb-ppt-mp-struct-100mb_seed10 is an open-weight text-generation model with roughly 100M parameters published by francesca9805 on the Hugging Face Hub. It has 271 downloads. Runs with transformers.
- Text generation
- Library: transformers
- 100M parameters
- Writing
By cribl-ai
cribl-decision-1.0 is an open-weight text-generation model published by cribl-ai on the Hugging Face Hub. It has 257 downloads. Runs with peft.
- Text generation
- Conversational
- Library: peft
- Productivity
By nics-efc
TaH2-1.7B-max2 is an open-weight text-generation model with roughly 1.7B parameters published by nics-efc on the Hugging Face Hub. It has 323 downloads.
- Text generation
- Conversational
- 1.7B parameters
- Productivity
By OpenLLM-France
Luciole-8B-KD-Math-Base is an open-weight text-generation model with roughly 8B parameters published by OpenLLM-France on the Hugging Face Hub. It has 269 downloads.
- Text generation
- 8B parameters
- Research
By jiangchengsong
MemDuet-S1-Qwen3.5-2B is an open-weight text-generation model with roughly 2B parameters published by jiangchengsong on the Hugging Face Hub. It has 267 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- +1
- Productivity
By JiteshJha
gowise-qwen2.5-1.5b-instruct is an open-weight text-generation model with roughly 1.5B parameters published by JiteshJha on the Hugging Face Hub. It has 271 downloads. Runs with transformers.
- Text generation
- Conversational
- Library: transformers
- +1
- Productivity
By Norod78
hebrew_poetry-gpt_neo-small is an open-weight text-generation model published by Norod78 on the Hugging Face Hub. It has 256 downloads. Runs with transformers.
- Text generation
- Library: transformers
- Writing
By digitous
Alpacino30b is an open-weight text-generation model with roughly 30B parameters published by digitous on the Hugging Face Hub. It has 256 downloads. Runs with transformers.
- Text generation
- Library: transformers
- 30B parameters
- Writing
By LoneStriker
Nous-Capybara-34B-5.0bpw-h6-exl2 is an open-weight text-generation model with roughly 34B parameters published by LoneStriker on the Hugging Face Hub. It has 256 downloads. Runs with transformers.
- Text generation
- Library: transformers
- 34B parameters
- Productivity
By MaziyarPanahi
mergekit-slerp-werhsur-GGUF is an open-weight text-generation model published by MaziyarPanahi on the Hugging Face Hub. It has 259 downloads. Runs with transformers.
- Text generation
- Conversational
- GGUF quantised builds
- +1
- Research
- Productivity
By roleplaiapp
Qwen2.5-Coder-14B-Instruct-Uncensored-Q5_K_M-GGUF is an open-weight text-generation model with roughly 14B parameters published by roleplaiapp on the Hugging Face Hub. It has 256 downloads. Runs with transformers.
- Text generation
- Conversational
- GGUF quantised builds
- +2
- Coding
- Productivity
By loleg
Apertus-v1.1-4B-Instruct-mlx is an open-weight text-generation model with roughly 4B parameters published by loleg on the Hugging Face Hub. It has 256 downloads. Runs with mlx.
- Text generation
- Conversational
- Library: mlx
- +1
- Productivity
By emrevrg
Norovox-Alpha-MoE-3.9B is an open-weight text-generation model with roughly 3.9B parameters published by emrevrg on the Hugging Face Hub. It has 262 downloads.
- Text generation
- Conversational
- 3.9B parameters
- Research
- Productivity