Install Circulara Core in Claude Code
claude mcp add circulara-core -e CIRCULARA_BACKEND_URL=... -e CIRCULARA_TENANT_ID=... -e CIRCULARA_TOKEN=... -e CIRCULARA_SEAT_ID=... -e CIRCULARA_USER_ID=... -- npx -y @circulara/plugin{
"mcpServers": {
"circulara-core": {
"command": "npx",
"args": [
"-y",
"@circulara/plugin"
],
"env": {
"CIRCULARA_BACKEND_URL": "...",
"CIRCULARA_TENANT_ID": "...",
"CIRCULARA_TOKEN": "...",
"CIRCULARA_SEAT_ID": "...",
"CIRCULARA_USER_ID": "..."
}
}
}
}Replace each ... with your own value.
Frequently asked questions
What does the Circulara Core MCP server do?
Circulara Observe MCP plugin - meters your AI agents' token spend and carbon, free tier.
Is the Circulara Core MCP server free?
The server is free, but you will likely need an account. The server itself is free, but it connects to a service that needs an account or API key, which may have paid tiers. Check the provider for current pricing.
Does Circulara Core run locally or remotely?
Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.
How do I add Circulara Core to Claude Code?
Run: claude mcp add circulara-core -e CIRCULARA_BACKEND_URL=... -e CIRCULARA_TENANT_ID=... -e CIRCULARA_TOKEN=... -e CIRCULARA_SEAT_ID=... -e CIRCULARA_USER_ID=... -- npx -y @circulara/plugin
More ai agents & coding agents MCP servers
View allClarx Cloud
Gernika-Labs/clarx-cloud
Score agent manifests, generate CI workflows, and pull Clarx scan findings into your IDE.
Chinese Text Tools
Cail726/chinese-text-tools
Claude Code 中文写作四合一工具箱:文本分析(字数/段落/阅读时间)、结构化大纲生成(论文/小说/商业计划书)、GB/T 7714 参考文献格式化、中文字频统计。纯本地运行。
Claude Code Organizer
mcpware/claude-code-organizer
Organize Claude Code memories, skills, MCP servers, commands, agents, rules via drag-and-drop.
ChiefLab
bdentech/chiefmo-agent
Open execution contract for agents doing business work. 6 operators, one MIT-licensed spec.
Claude Context Sync
ybin4548/claude-context-sync
Share context, detect conflicts, and message across parallel Claude Code sessions
chargehand
Egoushka/chargehand
Runs coding-agent workers on a codebase question; every claim in the answer carries evidence.