"Understanding local computer vision models like YOLO" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Account-less MCP access to 45 Gemini models & autonomous agents via L402, x402, and MPP.
See whether your own agent falls for the traps AI models fall for: six refereed jobs. No account.
Generate AI images, video, and audio with many frontier models, private by default.
Ask Drex decision models typed questions about a state and get calibrated probabilities; free within per-network limits.
Your own AI agent on an always-on cloud computer: Claude Code, Codex and more, or managed OpenClaw.
Typed-question decisions from Jev: classify, moderate, route models and guard tool calls.
Deterministic contextual decision arbitration and action routing for autonomous software. Takes current state, context, or intent plus caller-supplied candidate actions, state transitions, routes, refusals, escalations, tools, or models and returns a deterministic ordered candidate field. Also provides persistent machine representations for memory, retrieval, indexing, and downstream coherence measurement.
AIProcurement.club offers 42 MCP tools: 27 procurement specialists, 6 fixed workflows, 2 saved-report recovery tools and 7 read-only evidence tools. Five file tools provide local PDF/DOCX/PNG/JPEG extraction, English OCR, page quotes, keyword search and exact order-document checks in private temporary RAM on AIP; no corpus or Gateway memory is added. File tools require agent:read; the two existing tenant-scoped PO/invoice readers require p2p:read. For AIP-only file handling, connect directly to https://mcp.aiprocurement.club/mcp with Authorization: Bearer YOUR_SCOPED_AIP_KEY; do not submit documents or keys to directory test profiles. Paid agents are separate: external-inference consent and prepaid AIP access (from $10/job) apply. Use one stable idempotency key per paid job for saved-result replay. Setup: https://aiprocurement.club/agent-services/for-agents.
Yinli AI is building the SI (Social Intelligence)-native human connection and instant-messaging network. Messaging connected our contacts. Yinli's vision is to open the human network beyond them: let your Agent discover people you do not yet know, turn everyday intent into conversations, and bring companions, communities and opportunities into reach. People are at the center; Agents help bridge the distance. Connect through MCP and let your Agent enter the network on your behalf. 引力AI正在构建 SI(Social Intelligence,社会智能)原生的人际互联即时通讯网络。让即时通讯从联系人走向更广阔的人际网络:以人为核心,让 Agent 连接原本不会相遇的人,把生活中的想法带向同伴、社群、机会与真实关系。通过 MCP 接入,让你的 Agent 为你开启下一次连接。
Hire a verified local human for small real-world tasks your AI agent can't do.
A remote MCP gateway for persistent agent identities, authenticated private messaging, inbox acknowledgements and a shared 24-hour public board. Six tools over Streamable HTTP. Native agents keep Ed25519 keys locally and authenticate with signed challenges; a local stdio bridge handles signing. Docs: https://a2anx.com/llms.txt. Official MCP Registry: io.github.obcraft/a2anx.
Discover, invoke, and verify ForceDream agents with cryptographic proofs. 14 local, 21 hosted tools.
Test whether AI models select your MCP tools against rivals; explore real offers and safe previews.
Remote MCP connector for AgentsGot, an AI agent task marketplace currently running on testnet. Enables agents to discover tasks and prepare task-workflow intents through a hosted Streamable HTTP endpoint. The SDK is public; core platform logic remains private. Wallet signing stays local; never send private keys to the remote service. Testnet only.
Decision models for agents over x402: yes/no, choice and score questions as probabilities, per call.
Governed local-first memory and continuity for AI agents — signed receipts, optional hosted lane.
Exact expected-cost diagnostic policies for caller-supplied finite deterministic fault models.
The editors' index of AI-native software, from AI agents to the models and frameworks behind them.
Free meeting place for AI agents: register, find agents, like, accept intros. Check whats_waiting.
Create and evaluate versioned decision models with reproducible results and declared assumptions.
Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any computer. No install on the target machine — 12 tools for screenshots, click, type, scroll, key press, and monitor-corner calibration.
Multi-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.
Run and manage H Company's Computer-Use Agents from any MCP client.
superbot is your own AI agent: anything you can do on your computer, it can do, fast.
Agents that test your web and mobile app like real users, on every pull request.
Certified local pilot boards for an unfamiliar site, with scoped authority and signed completion.
The Zeevou AI Connector connects live Zeevou data with leading AI models such as ChatGPT, Claude, Gemini, Grok, and DeepSeek, enabling property managers and developers to build custom AI agents that can read and act on operational data, automate workflows, and perform tasks through natural language.
Allows agents to use the Runtype platform to build AI products - workflows, agents, flows, and deploy them to popular surfaces like web chat, slack, telegram, MCP servers, and others.
Connect Floniks to any MCP client — Claude.ai, Claude Code, Claude Desktop, or Cursor — and drive your workflows, models, characters, and creations in natural language. Built for agent orchestration: discover capabilities, assemble workflows, run them, and iterate.
DM / IM + public arena for AI agents (A2A 1.0) — hosted endpoint or local package.
A global shared memory bank and knowledge base exclusively for autonomous AI agents. It prevents agents like Cursor and Claude from hallucinating the same bug fixes twice by allowing them to search for and contribute verified solutions. Full installation guide: https://github.com/aiagentoverflow/agents-overflow-mcp-docs
Hand off whole tasks: videos, research, posts, web pages. Uses your own Chrome, computer and phone.
Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
StremAI MCP: shared memory for AI coding agents. Connected agents can recall. OAuth + local stdio.
Memory, reflection and safety for AI agents. Hosted or local, no vector database.
Design buildings as IFC4 BIM models from a brief: an AI architect that plans, builds and edits.
MCP gateway and cloud hosting for MCP servers, agents and apps like RAG, managed from your agent.
Build, deploy, and sell AI agents for local-service businesses - from your IDE.
An MCP memory server. One memory your agents share — across models, devices and apps.
Plan, implement, and validate software changes using a virtual computer equipped with a full coding agent, development tools, browsers, and file access. Coding Agent by OpenHelm enables your agent to carry out work such as: • Implementing new features • Fixing bugs • Refactoring codebases • Updating documentation • Creating and validating pull requests
Conduct comprehensive research projects using a virtual computer equipped with a real browser, coding tools, document creation capabilities, and more. Deep Research by Openhelm enables your agent to tackle work such as: • Market and competitor analysis • Industry and company research • Investment and acquisition due diligence • Technical and scientific investigations • Report generation with sources and evidence What makes OpenHelm the best solution for this: • Research is continuously revie
Execute one-off or scheduled tasks within a virtual computer that can spin up a real browser, a full coding agent, an email inbox and more. OpenHelm unlocks the ability for your agent to carry out all sorts of tasks, such as: • Deep research on a topic • Emailing + handling responses • Coding work • Updating files What makes OpenHelm the best solution for this: • Underpinned by a powerful AI that monitors work and ensures goals are actually achieved • Browser is SUPER stealthy, meaning it c
The Stytch MCP server is a reference implementation that demonstrates remote MCP server authentication and authorization using Stytch Connected Apps. It provides OAuth 2.1-compliant authorization (including PKCE), Dynamic Client Registration, and validates Stytch-issued access tokens to enable AI agents to securely interact with external services through permissioned access, supporting scopes like openid, email, profile, and manage:project_data.
AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.