mcp-server-check
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHECK_TOOLS | No | Comma-separated allowlist of individual tool names | |
| CHECK_API_KEY | Yes | Your Check API key (Bearer token) | |
| CHECK_TOOLSETS | No | Comma-separated list of toolsets to enable (e.g. companies,employees) | |
| CHECK_READ_ONLY | No | Set to 1, true, or yes to disable all write/mutating tools | |
| CHECK_TOOL_MODE | No | Tool mode: dynamic (3 meta-tools) or all (all tools individually) | dynamic |
| CHECK_TRANSPORT | No | Transport protocol: stdio, sse, or streamable-http | stdio |
| CHECK_API_BASE_URL | No | API base URL | https://sandbox.checkhq.com |
| CHECK_EXCLUDE_TOOLS | No | Comma-separated list of tool names to hide |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_toolsA | Search for available API tools by keyword. Returns matching tools with their full parameter schemas, ready for use with run_tool. Call with an empty query to see all available toolsets. Supports synonym matching (e.g. "pay employees" finds payroll tools). query: Search keywords (e.g. "list companies", "create employee", "payroll"). toolset: Optional toolset name to restrict search (e.g. "companies", "employees"). limit: Maximum number of results (default 20). |
| list_toolsetsA | List all available API toolsets with descriptions. Returns a summary of each toolset including its name, description, tool count, and example tools. Use this to understand what's available before searching for specific tools. |
| run_toolA | Execute an API tool by name with the given arguments. Use search_tools first to find the tool name and its parameter schema. tool_name: The exact tool name (e.g. "list_companies", "get_employee"). arguments: Tool arguments as a JSON string or dict (e.g. '{"company_id": "com_xxx"}' or {"company_id": "com_xxx"}). confirm: Set to true to confirm execution of a destructive tool (approve, delete, simulate, refund, cancel). Required when CHECK_CONFIRM_DESTRUCTIVE is enabled and the tool is destructive. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| list_enums | List all available enum types. |
| enum_business_type | |
| enum_pay_frequency | |
| enum_processing_period | |
| enum_payment_method_preference | |
| enum_payroll_type | |
| enum_funding_payment_method | |
| enum_bank_account_subtype | |
| enum_report_type | |
| enum_company_component_type | |
| enum_employee_component_type | |
| enum_contractor_component_type | |
| list_toolset_descriptions | Human-readable descriptions of all toolsets. |
TDQS
Scored across 3 tools
Each tool has a distinct purpose: list_toolsets provides an overview, search_tools finds specific tools, and run_tool executes them. No overlap or ambiguity.
All tools use a consistent verb_noun pattern in snake_case (list_toolsets, search_tools, run_tool), making the convention predictable.
With 3 tools, the server is well-scoped for its meta-purpose of discovering and executing API tools. Each tool is essential and the count feels appropriate.
The set covers listing, searching, and executing tools. A minor gap is the lack of a dedicated tool to get details for a single toolset, but search_tools can handle that. Overall, it's complete for the stated purpose.