mercury_get_organization
Retrieve legal identity details of your Mercury organization, including legal name, EIN, and registered address, for invoice generation and tax document preparation.
Instructions
Retrieve information about your Mercury organization (legal name, EIN, registered address, etc.).
USE WHEN: fetching the workspace's legal identity for invoice generation, tax documents, or to confirm which organization the API token is bound to.
DO NOT USE: for per-account info (use mercury_get_account). The Mercury API exposes only one organization per token, so there is no list variant.
RETURNS: { id, legalName, ein, address, ... }.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Implementation Reference
- src/tools/organization.ts:5-25 (handler)Registers and implements the 'mercury_get_organization' tool. The handler (lines 19-21) calls client.get('/organization') and returns a sanitized JSON result containing organization info (id, legalName, ein, address, etc.).
export function registerOrganizationTools(server: McpServer, client: MercuryClient): void { defineTool( server, "mercury_get_organization", [ "Retrieve information about your Mercury organization (legal name, EIN, registered address, etc.).", "", "USE WHEN: fetching the workspace's legal identity for invoice generation, tax documents, or to confirm which organization the API token is bound to.", "", "DO NOT USE: for per-account info (use `mercury_get_account`). The Mercury API exposes only one organization per token, so there is no list variant.", "", "RETURNS: `{ id, legalName, ein, address, ... }`.", ].join("\n"), {}, async () => { const data = await client.get("/organization"); return textResult(data); }, { title: "Get Organization", readOnlyHint: true, openWorldHint: true }, ); } - src/tools/organization.ts:5-25 (schema)The input schema is an empty object '{}' (line 18) — no parameters are required for this tool.
export function registerOrganizationTools(server: McpServer, client: MercuryClient): void { defineTool( server, "mercury_get_organization", [ "Retrieve information about your Mercury organization (legal name, EIN, registered address, etc.).", "", "USE WHEN: fetching the workspace's legal identity for invoice generation, tax documents, or to confirm which organization the API token is bound to.", "", "DO NOT USE: for per-account info (use `mercury_get_account`). The Mercury API exposes only one organization per token, so there is no list variant.", "", "RETURNS: `{ id, legalName, ein, address, ... }`.", ].join("\n"), {}, async () => { const data = await client.get("/organization"); return textResult(data); }, { title: "Get Organization", readOnlyHint: true, openWorldHint: true }, ); } - src/tools/organization.ts:5-25 (registration)The tool is registered via defineTool() with name 'mercury_get_organization' on the MCP server. The registration function registerOrganizationTools() is called from src/tools/index.ts line 30.
export function registerOrganizationTools(server: McpServer, client: MercuryClient): void { defineTool( server, "mercury_get_organization", [ "Retrieve information about your Mercury organization (legal name, EIN, registered address, etc.).", "", "USE WHEN: fetching the workspace's legal identity for invoice generation, tax documents, or to confirm which organization the API token is bound to.", "", "DO NOT USE: for per-account info (use `mercury_get_account`). The Mercury API exposes only one organization per token, so there is no list variant.", "", "RETURNS: `{ id, legalName, ein, address, ... }`.", ].join("\n"), {}, async () => { const data = await client.get("/organization"); return textResult(data); }, { title: "Get Organization", readOnlyHint: true, openWorldHint: true }, ); } - src/tools/_shared.ts:16-26 (helper)textResult() helper used by the handler — sanitizes JSON values and wraps them in a ToolResult with both text content and structuredContent.
export function textResult(data: unknown): ToolResult { // Walk the payload once, reuse the sanitized value for both the // LLM-display JSON string and the `structuredContent` object. // Calling sanitizeJsonForLlm(data) + sanitizeJsonValues(data) // separately would run the walker twice on the same input. const sanitized = sanitizeJsonValues(data); return { content: [{ type: "text", text: JSON.stringify(sanitized, null, 2) }], structuredContent: (sanitized ?? {}) as Record<string, unknown>, }; } - src/tools/_shared.ts:28-54 (helper)defineTool() helper that wraps the handler with rate-limiting/audit middleware (via wrapToolHandler) and registers the tool on the MCP server with strict input schema and annotations.
export function defineTool<S extends ZodRawShape>( server: McpServer, name: string, description: string, inputSchema: S, handler: (args: z.infer<z.ZodObject<S>>) => Promise<ToolResult>, annotations: ToolAnnotations, ): void { const wrapped = wrapToolHandler(name, handler); const strictSchema = z.object(inputSchema).strict(); // MCP behavioral annotations (readOnlyHint / destructiveHint / // idempotentHint / openWorldHint) — declared machine-readable so // hosts and rubrics (TDQS / Glama Behavior dimension) can detect // tool semantics without scraping the prose description. Required // (not optional) so every new tool ships with explicit semantics — // forgetting the annotation now fails typecheck instead of // silently shipping a tool with no hint set. // The MCP SDK overloads `registerTool` with shape narrowing the runtime // strict-schema and the wrapped callback can't satisfy through generics. // Both casts are runtime-safe — the signatures only diverge at the type // level. Asserted by the existing tool-registration tests. (server.registerTool as unknown as (...a: unknown[]) => unknown)( name, { description, inputSchema: strictSchema, annotations }, wrapped, ); }