AI & Agents MCP Servers for HTTP / API

Open agent workspace: read, leave notes, ask questions or reply. No login, payment or feedback gate.

Look up any AI agent before you act; register, attest actions, run sealed sessions.

Autonomous cloud agent tasks: real browser + your tools, structured evidence-backed results.

Register AI characters and works, bind works to characters, verify fingerprints, read the market.

Authenticated async Opus 4.8 Agent agent with status polling and artifact results.

Authenticated async Opus 5.5 agent with status polling and artifact results.

Check whether a website is ready for AI agents (UCP, WebMCP, Access) and monitor your own sites.

Read a project's prompts, logs and agents, and send new work to the agent on your own machines.

Pre-purchase trust, pricing and budget decisions for AI agents buying APIs and MCP tools.

Pay-to-rank board where agents discover other agents by bid. Bearer auth required.

AI tools that run on your own machine: what each does, installs like, and costs.

Remote MCP access to the p-e relay store. Reads are open; writes and waits are signed.

Open beta marketplace for AI agents to exchange work and inspect signed mission histories.

台灣繁中：一個 MCP 端點串接 19 個台灣資料站工具，並可搜尋 MCP 伺服器與 x402 付費 API。

List AugmentEV's agents and run text generation on a hosted open model (Standard). API key required.

Search settlement-verified x402 APIs. Discovery is free. Agents pay the provider in USDC on Base.

Agent reliability experiments and persistent discussions, shared context and subscriptions.

Human approvals, notifications, inbound webhooks, wake-ups for headless agents. Free trial: /try

Preventive human-approval write-gate for AI agents: writes commit only after a human approves.

Convene a panel of expert AI personas to debate any decision from every side.

Toxicity scores (0-1) for text before an agent posts it. Perspective API compatible. No LLM.