What is the MCP endpoint?
The server is available via streamable-http at `https://mcp.sitepulsar.ai/mcp`. Anonymous tool discovery is supported on the `/initialize` and `/tools/list` endpoints.

@SitePulsar
基本信息
Agent Experience Optimization (AEO) audits over MCP — score how findable, readable, and usable your site is to AI agents across FIND/READ/USE, then get prioritized machine-actionable fixes.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"sitepulsar": {
"url": "https://mcp.sitepulsar.ai/mcp"
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
点击上方按钮,直接连接服务器端点实时获取工具列表。
SitePulsar is agent-infrastructure for the agent-native web. Its hosted MCP server lets AI agents and developers run Agent Experience Optimization (AEO) audits that return a single Agent Readiness Score across three pillars — FIND (AI discoverability), READ (content and schema parseability), and USE (autonomous action readiness) — along with prioritized, machine-actionable fixes.
Connect via streamable-http at https://mcp.sitepulsar.ai/mcp. Use anonymous discovery (initialize/tools/list) to list tools, then authenticate with OAuth or a Bearer API key for all tool calls. Most read tools are free; run_audit and scan_visibility are metered (Pro/Business tier).
The server is available via streamable-http at `https://mcp.sitepulsar.ai/mcp`. Anonymous tool discovery is supported on the `/initialize` and `/tools/list` endpoints.
Use OAuth or a Bearer API key. Anonymous access is only allowed for discovery; all functional tool calls require authentication.
Most read tools (e.g., `get_audit`, `check_agent_readiness`, `probe_*`) are free. `run_audit` and `scan_visibility` are metered and require a Pro or Business plan.
13 tools: `check_agent_readiness`, `run_audit`, `get_audit`, `get_audit_detail`, `get_audit_full`, `compare_aeo`, `get_fixes`, `search_companies`, `probe_agent_discovery`, `probe_mcp_functional`, `probe_ucp_readiness`, `scan_visibility`, `scan_product_page`.
Full documentation is available at `https://www.sitepulsar.ai/llms.txt`.
🚀 The fast, Pythonic way to build MCP servers and clients.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
MCP Toolbox for Databases is an open source MCP server for databases.
评论