Kount Developer MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KOUNT_API_KEY | No | Your Kount Sandbox portal API key, used as the Basic credential value for Sandbox authentication. | |
| KOUNT_CLIENT_ID | No | Your Kount Sandbox client ID. Configure it in the environment of the MCP server process; local tools work without credentials, but authenticate_sandbox requires it. | |
| KOUNT_MCP_SCHEMA_PATH | No | Optional absolute path to the separately downloaded Commerce OpenAPI specification (default is ~/.cache/kount-developer-mcp/commerce-v2-2026-11-03.json). |
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 |
|---|---|
| get_integration_guideA | Get sourced Payments Fraud v2 guidance, recommendations and unresolved documentation conflicts. |
| get_api_schemaB | Read a separately downloaded, verified v2 request/response schema. operation: evaluate_order, update_order, get_order, batch_update_reversals; component is an exact schema name. |
| validate_order_payloadB | Validate a synthetic v2 order against the local spec and sourced prose constraints. valid:null means unavailable or indeterminate. No network calls. |
| generate_order_exampleB | Generate a synthetic basic_purchase, physical_goods or digital_goods request; only returns payloads that pass the shared validator. |
| explain_api_errorB | Explain documented status semantics, separate hypotheses, and optionally validate a synthetic payload. Never echoes response messages or infers a cause for HTTP 500. |
| check_integration_readinessB | Assess caller-reported capabilities and local credential/authentication status against a cited checklist. Never returns credentials or authenticates automatically. Includes manual verification; does not inspect application code or certify readiness. |
| authenticate_sandboxA | Network-enabled: obtain and cache a bearer token from https://login-uat.equifax.com/as/token using local KOUNT_CLIENT_ID and KOUNT_API_KEY environment configuration. Never returns a token or credential value. No arguments and no order API calls. |
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 7 tools
Most tools have clearly distinct purposes: readiness checking, sandbox authentication, documentation, schema reading, payload validation, example generation, and error explanation. There is some minor overlap around synthetic payload handling among validate_order_payload, generate_order_example, and explain_api_error, but the descriptions clarify their different roles.
All seven tools follow a consistent snake_case verb_noun pattern, such as check_integration_readiness, authenticate_sandbox, get_api_schema, and validate_order_payload. No mixed casing or conflicting naming styles are present.
Seven tools is well-scoped for a developer integration assistant covering readiness, authentication, guidance, schema access, validation, example generation, and error explanation. Each tool appears to earn its place without unnecessary breadth.
The surface covers the main developer integration workflow from readiness and authentication through schema lookup, payload validation, example generation, and error explanation. Minor gaps remain around operation/component discovery and token lifecycle management, but core workflows are addressed.