Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@FFS MCP Server check if account 123456 has the 'call-recording' flag enabled"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) Server for managing FFS (Feature Flag Service).
🔐 ffs_get_user_info: Get AccountId and ExtensionId from RingCentral credentials
🔍 ffs_search_flag: Search for FFS flags by keyword
📋 ffs_get_flag_options: Get all available options for a Flag
✅ ffs_check_account: Check account status in a Flag
✏️ ffs_update_account: Update account's Flag value
Related MCP server: @shipeasy/mcp
The server requires the following environment variables:
Variable | Description | Required |
| FFS API base URL | ✅ |
| RingCentral API URL | ✅ |
| Base64 encoded client credentials | ✅ |
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"ffs": {
"command": "npx",
"args": ["@xcodeyang/ffs-mcp-server"],
"env": {
"FFS_BASE_URL": "http://your-ffs-server:8080",
"FFS_RC_API_URL": "https://your-rc-api-server",
"FFS_RC_CLIENT_CREDENTIALS": "your-base64-credentials"
}
}
}
}{
"augment.advanced": {
"mcpServers": [
{
"name": "ffs",
"command": "npx",
"args": ["@xcodeyang/ffs-mcp-server"],
"env": {
"FFS_BASE_URL": "http://your-ffs-server:8080",
"FFS_RC_API_URL": "https://your-rc-api-server",
"FFS_RC_CLIENT_CREDENTIALS": "your-base64-credentials"
}
}
]
}
}# Build first
npm run build
# Publish to RingCentral Nexus registry
npm publishGet AccountId and ExtensionId from RingCentral credentials.
Input:
username: RingCentral user email
password: RingCentral password
Output:
accountId: Company-level ID (affects all users in the company)
extensionId: User-level ID (affects only this user)
Search for FFS flags by keyword.
Input:
keyword: Search keyword or complete Flag ID
Get all available options for a Flag.
Input:
flagId: Complete FFS Flag ID
Output:
List of options with valueId (needed for updates)
Check account status in a Flag.
Input:
flagId: Complete FFS Flag ID
id: AccountId or ExtensionId
Update account's Flag value using MCP Auto Condition.
Input:
flagId: Complete FFS Flag ID
id: AccountId or ExtensionId
targetValueId: Value ID from ffs_get_flag_options
# Run in development mode
npm run dev
# Build
npm run build
# Test tools
npx tsx test-tools.tsCheck the current status of an AccountId or ExtensionId in a Flag.
Inputs: flagId (required), id (required).
Get all available options (values) for a Flag. Shows Value IDs needed for updates.
Inputs: flagId (required).
Get AccountId and ExtensionId from RingCentral credentials. Use ExtensionId for individual user, AccountId for entire company.
Inputs: username (required), password (required).
Search for FFS flags by keyword. Returns matching flags with their IDs and types.
Inputs: keyword (required).
Update an AccountId or ExtensionId to use a specific Flag value. Uses MCP Auto Condition for management.
Inputs: flagId (required), id (required), targetValueId (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
Each tool has a clearly distinct purpose: checking account status, getting flag options, retrieving user info, searching flags, and updating accounts. There is no overlap in functionality, and the descriptions make the boundaries explicit, preventing agent misselection.
All tools follow a consistent 'ffs_verb_noun' pattern with snake_case, such as ffs_check_account and ffs_update_account. This predictability makes the tool set easy to navigate and understand at a glance.
With 5 tools, the server is well-scoped for managing FFS flags and accounts. Each tool serves a specific, necessary function without redundancy, fitting typical expectations for a focused utility server.
The tool set covers core CRUD-like operations for FFS management: checking, searching, getting info, and updating. A minor gap exists in not having a tool to create or delete flags, but the available tools support key workflows without dead ends.
MCP server for Statsig API - interact with Statsig's feature flags, experiments, and analytics
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
The Fireflies MCP Server enables AI tools to connect directly to meeting data from Fireflies.ai, providing access to meeting transcripts, summaries, action items, and insights without switching platforms. It includes capabilities for querying cross-meeting data for analysis (such as sales insights or product feedback), and a separate Documentation MCP Server that allows searching the Fireflies knowledge base for API references, guides, and code examples.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
