Skip to main content
Glama
suthio

Redash MCP Server

by suthio

get_query_results_csv

Exports query results as CSV. Retrieves cached data or refreshes the query for the latest results. Designed for queries without parameters.

Instructions

Get query results in CSV format. Returns the last cached results, or optionally refreshes the query first to get the latest data. Note: Does not support parameterized queries.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryIdYesID of the query to get results from
refreshNoWhether to refresh the query before fetching results to ensure latest data (default: false)

Implementation Reference

  • Input schema for the get_query_results_csv tool: expects queryId (number) and optional refresh (boolean, default false).
    // Tool: get_query_results_csv
    const getQueryResultsCsvSchema = z.object({
      queryId: z.coerce.number(),
      refresh: z.boolean().optional().default(false)
    });
    
    async function getQueryResultsCsv(params: z.infer<typeof getQueryResultsCsvSchema>) {
      try {
        const { queryId, refresh } = params;
        const csv = await redashClient.getQueryResultsAsCsv(queryId, refresh);
    
        return {
          content: [
            {
              type: "text",
              text: csv
            }
          ]
        };
      } catch (error) {
        logger.error(`Error getting CSV results for query ${params.queryId}: ${error}`);
        return {
          isError: true,
          content: [
            {
              type: "text",
              text: `Error getting CSV results for query ${params.queryId}: ${error instanceof Error ? error.message : String(error)}`
            }
          ]
        };
      }
    }
  • Handler function for get_query_results_csv tool. Calls redashClient.getQueryResultsAsCsv(queryId, refresh) and returns the CSV text content.
    async function getQueryResultsCsv(params: z.infer<typeof getQueryResultsCsvSchema>) {
      try {
        const { queryId, refresh } = params;
        const csv = await redashClient.getQueryResultsAsCsv(queryId, refresh);
    
        return {
          content: [
            {
              type: "text",
              text: csv
            }
          ]
        };
      } catch (error) {
        logger.error(`Error getting CSV results for query ${params.queryId}: ${error}`);
        return {
          isError: true,
          content: [
            {
              type: "text",
              text: `Error getting CSV results for query ${params.queryId}: ${error instanceof Error ? error.message : String(error)}`
            }
          ]
        };
      }
    }
  • src/index.ts:1700-1711 (registration)
    Tool registration for 'get_query_results_csv' with description and inputSchema defining queryId (required) and refresh (optional, default false) parameters.
    {
      name: "get_query_results_csv",
      description: "Get query results in CSV format. Returns the last cached results, or optionally refreshes the query first to get the latest data. Note: Does not support parameterized queries.",
      inputSchema: {
        type: "object",
        properties: {
          queryId: { type: "number", description: "ID of the query to get results from" },
          refresh: { type: "boolean", description: "Whether to refresh the query before fetching results to ensure latest data (default: false)" }
        },
        required: ["queryId"]
      }
    },
  • src/index.ts:2360-2362 (registration)
    Tool execution dispatch: routes 'get_query_results_csv' tool name to getQueryResultsCsv handler with validated args.
    case "get_query_results_csv":
      logger.debug(`Handling get_query_results_csv`);
      return await getQueryResultsCsv(getQueryResultsCsvSchema.parse(args));
  • Helper method getQueryResultsAsCsv in RedashClient. Optionally refreshes the query first if refresh=true, then fetches CSV from /api/queries/{queryId}/results.csv endpoint.
    async getQueryResultsAsCsv(queryId: number, refresh = false): Promise<string> {
      try {
        // Optionally refresh the query before fetching results
        if (refresh) {
          logger.debug(`Refreshing query ${queryId} before fetching CSV results`);
          await this.executeQuery(queryId);
        }
    
        logger.debug(`Fetching CSV results for query ${queryId}`);
        const response = await this.client.get(`/api/queries/${queryId}/results.csv`, {
          responseType: 'text'
        });
    
        return response.data;
      } catch (error) {
        if (axios.isAxiosError(error)) {
          const axiosError = error as AxiosError;
          logger.error(`Error fetching CSV results for query ${queryId}: ${axiosError.message}`);
    
          if (axiosError.response) {
            const statusCode = axiosError.response.status;
            const errorData = axiosError.response.data;
            throw new Error(`Failed to fetch CSV results for query ${queryId}: Redash API error (${statusCode}): ${errorData}`);
          } else if (axiosError.request) {
            throw new Error(`Failed to fetch CSV results for query ${queryId}: No response received from Redash API: ${axiosError.message}`);
          } else {
            throw new Error(`Failed to fetch CSV results for query ${queryId}: ${axiosError.message}`);
          }
        } else {
          const errorMessage = error instanceof Error ? error.message : String(error);
          logger.error(`Error fetching CSV results for query ${queryId}: ${errorMessage}`);
          throw new Error(`Failed to fetch CSV results for query ${queryId}: ${errorMessage}`);
        }
      }
    }
Behavior4/5

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

With no annotations provided, the description carries full burden and discloses caching behavior, optional refresh, and lack of parameterized query support. It does not cover rate limits or authentication, but is sufficient for simple tool.

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

Conciseness5/5

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

The description is two sentences long, front-loads the core purpose, and includes all necessary information without extraneous details.

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

Completeness4/5

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

For a simple tool with two parameters and no output schema, the description is comprehensive enough, covering purpose, behavior, and a limitation. Could mention output format specifics like encoding or delimiter.

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

Parameters4/5

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

Schema coverage is 100% and description adds value by explaining the 'refresh' parameter's effect (getting latest data) and default behavior (cached results), beyond the schema's basic description.

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 that the tool gets query results in CSV format, mentioning caching and optional refresh. However, it does not differentiate from sibling tools like 'execute_query' or 'get_query' that might return different formats.

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

Usage Guidelines3/5

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

The description implies usage for obtaining CSV results and notes the refresh option, but lacks explicit guidance on when not to use it or compare to alternatives like 'execute_query' for non-CSV formats.

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/suthio/redash-mcp'

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