27 tools and 4 resources over the Model Context Protocol. Let Claude Code, Cursor, and Windsurf manage your flags, configs, and AI prompts natively.
Any MCP-compatible agent can connect to FlagDash out of the box.
A real conversation between an AI agent and the FlagDash MCP server. Natural language in, structured actions out.
Create a feature flag called
new-checkout
with type boolean.
Toggle
new-checkout
to enabled and set the rollout to 25%.
Your AI agent can manage every aspect of FlagDash without leaving the editor.
6 tools — Full feature flag lifecycle
6 tools
6 tools
3 tools
4 auto-discovered resources
Add FlagDash to your MCP configuration and your AI agent instantly gains access to all 27 tools. No SDK installation, no dependencies.
Use an API key (
sk_
prefix) with read+write scopes for full access, or read-only scopes for evaluation only.
Purpose-built for AI-native workflows. Your agent becomes a first-class citizen.
No packages to install, no dependencies to manage. The AI agent connects directly over MCP — just add one config file.
Agents discover all available tools and resources automatically. No documentation lookup needed — the schema IS the docs.
Create, read, update, and delete flags, configs, and AI prompts. Agents can manage your entire feature stack.
One tool call loads all agent instructions, skills, and rules. Your AI agent self-configures from FlagDash on every session.
Give agents read-only or read-write access with scoped API keys. Principle of least privilege built in.
Built on the Model Context Protocol — an open spec from Anthropic. Future-proof and compatible with the growing MCP ecosystem.
27 tools. 4 resources. One JSON config. Your agents manage flags, configs, and prompts natively.