Clonvo

Clonvo MCP server

Clonvo's remote Model Context Protocol server gives agents web search, page reading, site crawling, structured extraction, research reports, a browser agent, and company and people lookups.

Calls run on your own Firecrawl, Tavily, Exa, Parallel or TinyFish keys when you've added them to Clonvo, otherwise on Clonvo credits. Every call is listed in Clonvo's Activity with its cost.

Setting	Value
URL	https://api.clonvo.com/mcp
Transport	Streamable HTTP
Authentication	OAuth: add the URL and sign in. An API key also works, for agents and scripts.

This repository holds the server's documentation and its MCP Registry entry (server.json). The server itself is hosted by Clonvo; there's nothing to install or run.

Before you connect

Create a Clonvo account and buy credits once. That moves your organization to Pay as you go, which the tools need. Calls run on credits, or on your own key for a tool provider under Provider keys → Tools.

Connect with OAuth

Add https://api.clonvo.com/mcp to any app that supports remote MCP servers, then sign in to Clonvo when it asks. You choose the organization and project the app works in. There's no key to create or paste.

• ChatGPT, Claude and other apps with custom connectors: add a custom connector with the URL above.
• Claude Code, Cursor, VS Code and Codex: see the setup for each below.

An app connected this way can call the tools and nothing else. Its calls are billed to the organization you chose, and appear in Activity under the app's name. To see or disconnect your apps, go to Settings → Connected apps in Clonvo.

Connect with an API key

For agents and scripts that run without a person to sign in, create a key under API keys, keep it in an environment variable, and send it as Authorization: Bearer <key>:

export CLONVO_API_KEY="sk-cv-v1-…"

Tools

Tool	What it does
web_search	Search the web for ranked pages with snippets. Narrow by category (news, companies, people, research papers, GitHub, PDFs, financial reports), domains or time range, and optionally get each page's content.
web_scrape	Read one page as clean markdown or plain text.
web_map	List a website's URLs, optionally ranked by a topic.
web_extract	Read one page and get typed JSON back, shaped by a JSON Schema you give.
web_answer	Get a short answer to a question from current web sources, with citations.
find_similar	Find pages similar to a URL: competitors, other coverage, related papers.
company_search	Find companies by what they do, their industry or the technology they use.
company_enrich	Look up one company's profile by its domain, LinkedIn URL or name.
company_news	Get recent news and announcements about a company.
company_jobs	List a company's open job postings.
company_similar	Find competitors and lookalikes of a company.
people_search	Find professional profiles by role, company, name or a description.
people_enrich	Look up one person's professional profile from their LinkedIn URL.
web_crawl	Read many pages of one website as markdown. Runs as a job.
web_research	Research a question across many sources and get a cited report, or data in a shape you give. Runs as a job.
browser_task	Have a browser agent work through a page to reach a goal you describe. Runs as a job.
job_status	Check a job and get its result once it's done. Free.

Long-running tools return an MCP task to clients that support tasks. Other clients get the result directly when the job ends within about 25 seconds, otherwise a job id to check with job_status.

Prices for each tool are on clonvo.com/docs/tools.

Claude Code

claude mcp add --transport http clonvo https://api.clonvo.com/mcp

Then run /mcp in Claude Code and choose Authenticate for clonvo. Add --scope user to use it in every project.

To use an API key instead, add --header "Authorization: Bearer $CLONVO_API_KEY", or commit a .mcp.json for your team where each person sets CLONVO_API_KEY:

{
  "mcpServers": {
    "clonvo": {
      "type": "http",
      "url": "https://api.clonvo.com/mcp",
      "headers": {
        "Authorization": "Bearer ${CLONVO_API_KEY}"
      }
    }
  }
}

The Clonvo skills plugin for Claude Code connects this server too (sign in the same way), along with skills for building on the Clonvo API.

Cursor

Add Clonvo to .cursor/mcp.json in your project, or to ~/.cursor/mcp.json for every project. Cursor asks you to sign in when it first connects:

{
  "mcpServers": {
    "clonvo": {
      "url": "https://api.clonvo.com/mcp"
    }
  }
}

To use an API key instead, add "headers": { "Authorization": "Bearer ${env:CLONVO_API_KEY}" }. Cursor replaces ${env:CLONVO_API_KEY} with the variable from the environment it starts in.

VS Code

Add Clonvo to .vscode/mcp.json. VS Code asks you to sign in when it first connects:

{
  "servers": {
    "clonvo": {
      "type": "http",
      "url": "https://api.clonvo.com/mcp"
    }
  }
}

Codex

Add Clonvo and sign in:

codex mcp add clonvo --url https://api.clonvo.com/mcp
codex mcp login clonvo

To use an API key instead, add the server with --bearer-token-env-var CLONVO_API_KEY and skip the login.

Other clients

Any client that supports remote MCP servers over Streamable HTTP can connect: by signing in with OAuth, or with the header Authorization: Bearer <your Clonvo API key>.

Clonvo's MCP docs cover the OpenAI Agents SDK, the Vercel AI SDK, OAuth details, routing between providers, and what a call returns.

Support

Email [email protected], or open an issue in this repository.

License

MIT