Fraud Alert MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
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.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_transactionB | Analyzes a real-time transaction against known patterns to return a fraud probability score |
| flag_transaction_statusB | Allows the AI agent to take action by updating the status of a transaction and triggering an alert |
| get_user_risk_profileB | Fetches historical transaction behavior and current risk standing for a specific user to give the AI agent context |
| update_fraud_ruleC | Allows the AI to dynamically deploy new fraud detection rules based on emerging attack vectors |
| create_userB | Create a new user in the system |
| get_userB | Retrieve a user by ID |
| update_userC | Update user information (e.g., location, phone, address) |
| list_usersA | List all users in the system |
| delete_userB | Delete a user and remove their stored information |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| calculator_help | Get help with calculator operations |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Calculator Operations | List of available calculator operations |
| Health Checks | Current health status of all registered health checks |
| Alert Dashboard | UI component for Alert Dashboard |
| Widget Examples | Provides metadata and examples for all registered UI widgets |
TDQS
Scored across 9 tools
All tools have clearly distinct purposes: four focus on fraud-specific actions (analyzing, flagging, risk profiling, rule updating) and five on user CRUD operations. No overlapping functionality.
All tool names follow a consistent verb_noun snake_case pattern (e.g., flag_transaction_status, create_user), making it predictable for an agent.
9 tools is well-scoped for the server's purpose, covering both user management and fraud operations without excess or deficiency.
User CRUD is complete, and fraud operations cover analysis, flagging, risk profiling, and rule updating. However, missing tools to retrieve transactions or list fraud rules create minor gaps.