Skip to main content
Glama
mikusnuz

umami-mcp

create_report

Create and save a new analytics report for a website. Specify report name, type (funnel, retention, utm, goals, insights, revenue, journey, attribution), and parameters to customize tracking and analysis.

Instructions

Create and save a new report

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
websiteIdYesWebsite UUID
nameYesReport name
typeYesReport type
descriptionNoReport description
parametersNoReport-specific parameters (JSON object)

Implementation Reference

  • The handler function for the 'create_report' tool. It takes websiteId, name, type, description, and parameters as input, builds a body object, and calls POST /api/reports via the UmamiClient.
    server.tool(
      "create_report",
      "Create and save a new report",
      {
        websiteId: z.string().describe("Website UUID"),
        name: z.string().describe("Report name"),
        type: z
          .enum(["funnel", "retention", "utm", "goals", "insights", "revenue", "journey", "attribution"])
          .describe("Report type"),
        description: z.string().optional().describe("Report description"),
        parameters: z
          .record(z.unknown())
          .optional()
          .describe("Report-specific parameters (JSON object)"),
      },
      async ({ websiteId, name, type, description, parameters }) => {
        const body: Record<string, unknown> = { websiteId, name, type };
        if (description) body.description = description;
        if (parameters) body.parameters = parameters;
        const data = await client.call("POST", "/api/reports", body);
        return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
      }
  • The input schema for 'create_report' using Zod. Defines required fields: websiteId (string), name (string), type (enum of 8 specific values), and optional fields: description (string) and parameters (record of unknown).
    {
      websiteId: z.string().describe("Website UUID"),
      name: z.string().describe("Report name"),
      type: z
        .enum(["funnel", "retention", "utm", "goals", "insights", "revenue", "journey", "attribution"])
        .describe("Report type"),
      description: z.string().optional().describe("Report description"),
      parameters: z
        .record(z.unknown())
        .optional()
        .describe("Report-specific parameters (JSON object)"),
    },
  • The 'create_report' tool is registered via server.tool() inside the registerReportTools function in src/tools/reports.ts.
    server.tool(
      "create_report",
      "Create and save a new report",
      {
        websiteId: z.string().describe("Website UUID"),
        name: z.string().describe("Report name"),
        type: z
          .enum(["funnel", "retention", "utm", "goals", "insights", "revenue", "journey", "attribution"])
          .describe("Report type"),
        description: z.string().optional().describe("Report description"),
        parameters: z
          .record(z.unknown())
          .optional()
          .describe("Report-specific parameters (JSON object)"),
      },
      async ({ websiteId, name, type, description, parameters }) => {
        const body: Record<string, unknown> = { websiteId, name, type };
        if (description) body.description = description;
        if (parameters) body.parameters = parameters;
        const data = await client.call("POST", "/api/reports", body);
        return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] };
      }
    );
  • src/index.ts:33-33 (registration)
    The registerReportTools function (which registers 'create_report') is called from the main entry point src/index.ts.
    registerReportTools(server, client);
  • src/index.ts:76-76 (registration)
    The registerReportTools function is also called in the createSandboxServer function for the Smithery sandbox environment.
    registerReportTools(sandbox, mockClient);
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only states creation and saving, omitting information about side effects (e.g., overwriting existing reports), required authentication, or whether the operation is destructive. This is insufficient for an untrusted AI agent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short sentence with no wasted words, but it is too terse for a tool with 5 parameters and no other documentation. It lacks any structural elements like examples or bullet points that would improve readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 parameters, no output schema, no annotations), the description is incomplete. It fails to explain the return value, error states, or how the 'parameters' nested object should be structured, leaving the agent underinformed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so the parameters are already documented. The description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create and save a new report' with a specific verb and resource, distinguishing it from siblings like update_report or run_report. However, it lacks specificity about what 'saving' entails and does not differentiate from similar operations like adding a report draft.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as update_report, run_report, or list_reports. No context is given about prerequisites, required permissions, or use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mikusnuz/umami-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server