Skip to main content
Glama
suthio

Redash MCP Server

by suthio

execute_adhoc_query

Execute an ad-hoc SQL query against a specified data source without saving it; the temporary query is automatically deleted after execution.

Instructions

Execute an ad-hoc query without saving it to Redash. Creates a temporary query that is automatically deleted after execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSQL query to execute
dataSourceIdYesID of the data source to query against

Implementation Reference

  • src/index.ts:1756-1767 (registration)
    Registration of the execute_adhoc_query MCP tool in the ListToolsRequestSchema handler
    {
      name: "execute_adhoc_query",
      description: "Execute an ad-hoc query without saving it to Redash. Creates a temporary query that is automatically deleted after execution.",
      inputSchema: {
        type: "object",
        properties: {
          query: { type: "string", description: "SQL query to execute" },
          dataSourceId: { type: "number", description: "ID of the data source to query against" }
        },
        required: ["query", "dataSourceId"]
      }
    },
  • MCP tool handler for execute_adhoc_query - parses params and delegates to redashClient.executeAdhocQuery
    async function executeAdhocQuery(params: z.infer<typeof executeAdhocQuerySchema>) {
      try {
        const { query, dataSourceId } = params;
        const result = await redashClient.executeAdhocQuery(query, dataSourceId);
    
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(result, null, 2)
            }
          ]
        };
      } catch (error) {
        logger.error(`Error executing adhoc query: ${error}`);
        return {
          isError: true,
          content: [
            {
              type: "text",
              text: `Error executing adhoc query: ${error instanceof Error ? error.message : String(error)}`
            }
          ]
        };
      }
    }
  • Zod schema for execute_adhoc_query input validation (query string and dataSourceId number)
    // Tool: execute_adhoc_query
    const executeAdhocQuerySchema = z.object({
      query: z.string(),
      dataSourceId: z.coerce.number()
    });
  • Core implementation: executes an ad-hoc SQL query via Redash API POST /api/query_results, supports async job polling
    async executeAdhocQuery(query: string, dataSourceId: number): Promise<RedashQueryResult> {
      try {
        logger.info(`Executing adhoc query: ${query.substring(0, 100)}...`);
    
        // Prepare the request payload
        const payload = {
          query: query,
          data_source_id: dataSourceId,
          max_age: 0,  // Force fresh results (no cache)
          apply_auto_limit: true,  // Apply auto limit like in the web version
          parameters: {}
        };
    
        logger.debug(`Sending adhoc query request: ${JSON.stringify(payload)}`);
    
        // Execute the query directly without creating a query object
        const response = await this.client.post('/api/query_results', payload);
    
        // Handle async execution if job is returned
        if (response.data.job) {
          logger.debug(`Query is being executed asynchronously, job ID: ${response.data.job.id}`);
          return await this.pollQueryResults(response.data.job.id);
        }
    
        return response.data;
    
      } catch (error) {
        logger.error(`Error executing adhoc query: ${error}`);
        throw new Error(`Failed to execute adhoc query: ${error instanceof Error ? error.message : String(error)}`);
      }
    }
  • src/index.ts:2380-2382 (registration)
    Dispatch handler for execute_adhoc_query in the CallToolRequestSchema handler
    case "execute_adhoc_query":
      logger.debug(`Handling execute_adhoc_query`);
      return await executeAdhocQuery(executeAdhocQuerySchema.parse(args));
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses the temporary and auto-deletion behavior, but omits details like whether the tool can run destructive SQL, required permissions, or error handling. The disclosure is adequate but not rich.

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, no wasted words, and front-loads the core purpose. It is perfectly concise for the information it conveys.

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

Completeness3/5

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

Given the tool's simplicity and lack of output schema, the description lacks details about the return value (e.g., query results format). It is sufficient to differentiate from siblings but misses potentially useful information for an agent.

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% coverage with descriptions for both parameters (query and dataSourceId). The description does not add further meaning beyond what the schema already provides, so it meets the baseline.

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

Purpose5/5

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

The description clearly states it executes an ad-hoc query without saving, and explicitly mentions it creates a temporary query that is automatically deleted. This distinguishes it from sibling tools like execute_query which likely saves the query.

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

Usage Guidelines4/5

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

The description tells when to use this tool (for ad-hoc queries without persisting), but does not explicitly state when not to use or mention alternatives like execute_query for saved queries. The context is clear but lacks explicit exclusions.

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