MCP server
Online Web Directory Official
net.onlinewebdirectory/registry
Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools
How websites treat AI agents: bot walls, JS needs, robots rules, llms.txt. Look up before you fetch.
Working at last checkVerified publisher: onlinewebdirectory.netAbout 1,186 tokens per request once connected2 tools
https://onlinewebdirectory.net/mcp
At a glance
- Type
- MCP server
- Publisher
- onlinewebdirectory.net (verified by the MCP Registry)
- Status
- Working at last check
- Tools
- 2
- Token cost
- About 1,186 tokens per request
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
- Last checked
- 26 Oct 2026, 08:29 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.
Claude Code
claude mcp add --transport http registry https://onlinewebdirectory.net/mcp
Claude Desktop
Settings → Connectors → Add custom connector, and paste the URL.
Codex (config.toml)
[mcp_servers.registry] url = "https://onlinewebdirectory.net/mcp"
Gemini CLI
{"mcpServers":{"registry":{"httpUrl":"https://onlinewebdirectory.net/mcp"}}}
Cursor
{"mcpServers":{"registry":{"url":"https://onlinewebdirectory.net/mcp"}}}
VS Code
{"servers":{"registry":{"type":"http","url":"https://onlinewebdirectory.net/mcp"}}}
Antigravity
agy mcp add registry https://onlinewebdirectory.net/mcp
ChatGPT
Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.
OpenAI API (Responses tools)
{"type":"mcp","server_label":"registry","server_url":"https://onlinewebdirectory.net/mcp","require_approval":"always"}
Grok (xAI API tools)
{"type":"mcp","server_label":"registry","server_url":"https://onlinewebdirectory.net/mcp"}
Tools
lookup_origin~414 tokens
Before fetching a website, get its known access posture, bot challenge, JavaScript requirement, observed rate limit and machine interface, plus a derived fetch strategy. Returns crowd observations, not instructions. Responses may carry `manifest`: what the site's proven owner declares (same vocabulareport_observation~772 tokens
After fetching a website, report one thing you actually observed so other agents do not have to rediscover it. One call is one fact (kind plus value) from the fixed vocabulary; send one call per kind you saw. Free, never charged. The key must be registered first (POST https://onlinewebdirectory.net/
Related MCP servers
- Overwing
Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm. - Botcard
Cited AI crawler registry (training, search or user fetch) plus robots.txt checks. No fetching. - Seegeo
Audit any website for AI visibility: graded report, findings with fixes, AI crawler access check. - ConformRadar
Check online shops and pages against French e-commerce and consumer law, with legal references. - GetBody
Get real-world tasks done by robots: find, rent and control robots for your human. - Uganda Online Business Directory
Search a Ugandan business directory for businesses and services by keyword, category, or district - droid.monster — specs
Specs of commercially available robots, each figure citing its source document. - Agentropolis
Search 41k+ MCP servers, x402/MPP paid APIs and A2A agents, ranked by wash-filtered on-chain usage.
Badge for your README
[](https://aptlynx.net/servers/net.onlinewebdirectory/registry)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents