SEO · https://api.octen.ai
set up treg — https://treg.to/llms.txt
claude mcp add --transport http treg https://treg.to/mcp
Settings → Connectors → add https://treg.to/mcp as a custom connector.
Add https://treg.to/mcp as a remote MCP connector in its tool settings.
Settings → Connectors → Add custom connector → https://treg.to/mcp.
Point it at https://treg.to/mcp (HTTP transport).
curl -fsSL https://treg.to/install.sh | sh
LangChain, CrewAI or any code: /call/<tool-id> + X-Treg-Token: <token>. No SDK.
Using treg, search the open web by meaning or keyword. Show me the price first.
treg call octen.web.search --method POST --data '{"query":"Octen API documentation","count":1}'Eligible tools run on treg.to's key, metered per call from a prepaid balance.
The provider's own rate, $0.000 markup. How billing works.
Platform calls are charged per call. $1.00 free per new team, no card to start.
Register it and those calls are never metered. Your key always wins.
Another provider is a different word in the prompt, not a new integration.
The same token calls Context.dev, Exa, Firecrawl and 3,360 other tools.
octen.web.extractocten.web.searchocten.web.search.broadocten.web.search.newsReliability badges come from live traffic through treg.to. Live-verified means a successful provider check; it does not verify every request variant.
No. Eligible tools run on treg.to's key and the call is metered from your team's prepaid balance, priced up front. If your team registers its own Octen key, that key always wins and those calls are never metered.
Each tool on this page shows its rate; the cheapest is $0.0025/success. The rate is the provider's own and treg.to adds no markup; it is billed per call from a prepaid balance. It is not Octen's subscription pricing, which is on their own site. New teams start with $1.00 of free credit.
Run: claude mcp add --transport http treg https://treg.to/mcp. One MCP server carries Octen and the rest of the catalog.
Anything that speaks MCP (Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, Grok) and anything that can make an HTTP request (LangChain, CrewAI, LlamaIndex, plain code).
No. treg.to serves Octen's real API through its own metered proxy: the request is the provider's own, the credential is injected server-side, and the answer is relayed verbatim. The official Octen channels are linked above.