Schema | cloudflare-workspace-mcp

cloudflare-workspace-mcp

Describes the environment variables required to run the server.

Name	Required	Description	Default
`CFMCP_HOME`	No	Directory containing proot binaries and rootfs	$HOME
`CFMCP_D1_DB`	No	D1 database name (default for d1_query database)
`CFMCP_BACKEND`	No	Backend: local / proot / auto	auto
`CFMCP_ENV_FILE`	No	Path to Cloudflare credentials file	$CFMCP_WORKSPACE/.env
`CFMCP_WORKSPACE`	Yes	Workspace directory (mapped to /workspace)
`CFMCP_DEPLOY_SRC`	No	Deployment source directory (relative to workspace, default for cloudflare_deploy src_dir)	.
`CFMCP_DEPLOY_SCRIPT`	No	Deployment script (relative to workspace, used when no explicit parameters)	deploy.sh
`CFMCP_PAGES_PROJECT`	No	Pages project name (default for cloudflare_deploy project)

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tools`	{}

Functions exposed to the LLM to take actions

Name	Description
execute_commandB	在工作区内执行任意 shell 命令（local 后端直接本机 shell；proot 后端为 Debian 沙箱，Node + wrangler 已装）。cwd 默认 /workspace。
read_fileA	读取工作区下文件内容（UTF-8）。
write_fileA	写文件到工作区（自动创建父目录）。
list_filesA	列出工作区下目录内容（d 前缀=目录）。
cloudflare_apiA	Cloudflare REST API 通用网关：用 method/path/body 直接调用 Cloudflare API（自动注入 token/account_id）。path 里可用 {account_id} 占位符（自动替换）。常用路径见工作区 CF_API.md。示例：GET /zones、GET /accounts/{account_id}/workers/scripts、GET /accounts/{account_id}/kv/namespaces、POST /zones。⚠️ 全权限直通，删除类操作需用户明确授权。
cloudflare_statusA	查看 Cloudflare 账户资源清单（只读，纯 REST）。type 可选：all（默认）/pages/d1/kv/r2/zones/workers。
d1_queryA	对 D1 数据库执行只读 SQL（仅 SELECT，防误写库；纯 REST，无需 wrangler/jq）。database 默认取 .env 的 CFMCP_D1_DB。
cloudflare_deployA	部署工作区目录到 Cloudflare Pages（动线上，需用户明确授权后调用）。project/branch/src_dir/build_cmd 均可参数化；不传参数且工作区有部署脚本（CFMCP_DEPLOY_SCRIPT，默认 deploy.sh）时优先执行脚本。需要 wrangler（npm install -g wrangler）。

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/NingFlos/cloudflare-workspace-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server