frisk-mcp
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 |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| screen_paymentA | Screen a counterparty an agent is about to pay. Runs entirely offline: address sanity, dynamic-payTo comparison, transport check, and your spending policy. Returns allow / review / block with reasons. Advisory: the caller decides. Set FRISK_API_KEY to add hosted reputation signals. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap. The tool's purpose is singular and clearly defined.
The single tool uses a clear verb_noun pattern ('screen_payment'), which is consistent and predictable.
One tool feels thin for a general-purpose server, but for a narrowly focused payment screening service, it may be sufficient. It's borderline on the calibration scale.
The tool covers the essential screening workflow (address checks, policy, etc.), but lacks auxiliary capabilities like configuration or reporting. Minor gaps that agents can work around.