Categories › AI & Agents › Multi-agent, orchestration & workflows
Verified websites as JSON commands for AI agents over plain curl or MCP.
Remote server: your requests and data go to bold-cloud-h4u6s.run.mcp-use.com. Claude Code: claude mcp add --transport http clify https://bold-cloud-h4u6s.run.mcp-use.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
clify_sites — Search the catalogue of 135 real websites clify can call (package registries, government data, science, news, jobs, weather, culture…). Passclify_help — A site's commands with params ("name*" = required, ":a|b" = allowed values, "=x" = default). Pass command for full param docs, default fieldclify_run — Call one command of a clify site and get JSON back. args holds the command's params (see clify_help). Lists return count, total and nextPagecrates__get-crate — crates.io: Get a crate's details: description, links, download totals, keywords, categories and default version Returns name, description, dpypi__get-package — pypi.org: Get a package's PyPI page for its latest version: name and version, summary, pip install command, project links and metadata sidebwikipedia__summary — en.wikipedia.org: Short summary of an article (title, description, extract, url) Returns title, description, extract, content_urls.desktop.phnsearch__search — hn.algolia.com: Search stories/comments by relevance Returns title, points, num_comments, author, created_at, url, objectID by default. (SamNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.