Skip to main content
Glama
luizzzvictor

mcp-comexstat

by luizzzvictor

queryHistoricalData

Retrieve historical trade data by specifying flow, time period, detailed metrics, and filters for exports or imports using the MCP server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
detailsYes
filtersNo
flowYes
languageNopt
metricsYes
monthDetailNo
periodYes

Implementation Reference

  • MCP tool handler that receives parameters, calls ComexstatClient.queryHistoricalData, stringifies the result as JSON, and returns it as text content.
    async ({
      flow,
      period,
      monthDetail,
      filters,
      details,
      metrics,
      language,
    }) => ({
      content: [
        {
          type: "text",
          text: JSON.stringify(
            await this.client.queryHistoricalData(
              flow,
              period,
              monthDetail,
              filters || [],
              details,
              metrics,
              language
            )
          ),
        },
      ],
    })
  • Zod input schema for validating parameters of the queryHistoricalData MCP tool, including flow type, date period format, optional filters, required details and metrics arrays.
    {
      flow: z.enum(["export", "import"]),
      period: z.object({
        from: z
          .string()
          .regex(
            /^\d{4}-\d{2}$/,
            "Must be in YYYY-MM format (e.g., '2023-01')"
          ),
        to: z
          .string()
          .regex(
            /^\d{4}-\d{2}$/,
            "Must be in YYYY-MM format (e.g., '2023-01')"
          ),
      }),
      monthDetail: z.boolean().optional().default(false),
      filters: z
        .array(
          z.object({
            filter: z.string(),
            values: z.array(z.number()).or(z.array(z.string())),
          })
        )
        .optional(),
      details: z.array(z.string()),
      metrics: z.array(z.string()),
      language: z.string().optional().default("pt"),
    },
  • Registration of the 'queryHistoricalData' MCP tool using server.tool(), specifying the tool name, input schema, and execution handler.
      "queryHistoricalData",
      {
        flow: z.enum(["export", "import"]),
        period: z.object({
          from: z
            .string()
            .regex(
              /^\d{4}-\d{2}$/,
              "Must be in YYYY-MM format (e.g., '2023-01')"
            ),
          to: z
            .string()
            .regex(
              /^\d{4}-\d{2}$/,
              "Must be in YYYY-MM format (e.g., '2023-01')"
            ),
        }),
        monthDetail: z.boolean().optional().default(false),
        filters: z
          .array(
            z.object({
              filter: z.string(),
              values: z.array(z.number()).or(z.array(z.string())),
            })
          )
          .optional(),
        details: z.array(z.string()),
        metrics: z.array(z.string()),
        language: z.string().optional().default("pt"),
      },
      async ({
        flow,
        period,
        monthDetail,
        filters,
        details,
        metrics,
        language,
      }) => ({
        content: [
          {
            type: "text",
            text: JSON.stringify(
              await this.client.queryHistoricalData(
                flow,
                period,
                monthDetail,
                filters || [],
                details,
                metrics,
                language
              )
            ),
          },
        ],
      })
    );
  • Supporting client method implementation that validates input dates, constructs POST request to '/historical-data' endpoint with parameters, and returns the API response. This is called by the MCP handler.
    async queryHistoricalData(
      flow: "export" | "import",
      period: { from: string; to: string }, // Format: YYYY-MM (e.g., "2023-01")
      monthDetail: boolean = false,
      filters: Array<{ filter: string; values: number[] | string[] }> = [],
      details: string[],
      metrics: string[],
      language: string = "pt"
    ): Promise<{
      data: Array<{
        year: number;
        monthNumber?: number;
        metricFOB: string;
        metricKG: string;
        [key: string]: any;
      }>;
      success: boolean;
      message: string | null;
      processo_info: any;
      language: string;
    }> {
      // Validate date format
      const dateFormatRegex = /^\d{4}-\d{2}$/;
      if (
        !dateFormatRegex.test(period.from) ||
        !dateFormatRegex.test(period.to)
      ) {
        throw new Error(
          'Period dates must be in YYYY-MM format (e.g., "2023-01")'
        );
      }
    
      return this.post(
        "/historical-data",
        {
          flow,
          monthDetail,
          period,
          filters,
          details,
          metrics,
        },
        { language }
      );
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Related 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/luizzzvictor/mcp-comexstat'

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