Skip to main content
Glama

gcp_logs_read

Read-onlyIdempotent

Retrieve and filter GCP Cloud Logging entries by severity, resource, and time range to identify errors and monitor services.

Instructions

로그 조회|에러 확인|Cloud Logging|gcp logs|에러 로그 - GCP Cloud Logging에서 로그를 조회합니다

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filterNo로그 필터 (예: "severity=ERROR", "resource.type=cloud_run_revision")
project_idNoGCP 프로젝트 ID (기본: 현재 설정된 프로젝트)
time_rangeNo시간 범위 (예: "1h", "6h", "24h", "7d"). 기본: "1h"1h
limitNo최대 로그 수 (기본: 50, 최대: 500)
formatNo출력 형식 (기본: text)text

Implementation Reference

  • Tool definition and input schema for 'gcp_logs_read' including filter, project_id, time_range, limit, and format properties.
    export const gcpLogsReadDefinition = {
      name: 'gcp_logs_read',
      description: '로그 조회|에러 확인|Cloud Logging|gcp logs|에러 로그 - GCP Cloud Logging에서 로그를 조회합니다',
      annotations: {
        title: 'GCP 로그 조회',
        readOnlyHint: true,
        destructiveHint: false,
        idempotentHint: true,
        openWorldHint: true,
      },
      inputSchema: {
        type: 'object' as const,
        properties: {
          filter: {
            type: 'string',
            description: '로그 필터 (예: "severity=ERROR", "resource.type=cloud_run_revision")',
          },
          project_id: {
            type: 'string',
            description: 'GCP 프로젝트 ID (기본: 현재 설정된 프로젝트)',
          },
          time_range: {
            type: 'string',
            description: '시간 범위 (예: "1h", "6h", "24h", "7d"). 기본: "1h"',
            default: '1h',
          },
          limit: {
            type: 'number',
            description: '최대 로그 수 (기본: 50, 최대: 500)',
            default: 50,
          },
          format: {
            type: 'string',
            enum: ['text', 'json'],
            description: '출력 형식 (기본: text)',
            default: 'text',
          },
        },
        required: [],
      },
    };
  • TypeScript interface GcpLogsReadArgs defining the input argument types for the handler function.
    interface GcpLogsReadArgs {
      filter?: string;
      project_id?: string;
      time_range?: string;
      limit?: number;
      format?: 'text' | 'json';
    }
  • Main handler function gcpLogsRead that executes the gcloud logging read command, parses JSON output, transforms to LogEntry format, and returns formatted results with error reports.
    export async function gcpLogsRead(args: GcpLogsReadArgs) {
      try {
        const projectId = await getProjectId(args.project_id);
        const timeRange = args.time_range || '1h';
        const limit = Math.min(args.limit || 50, 500);
        const timestamp = parseTimeRange(timeRange);
    
        // Build filter
        let filter = `timestamp>="${timestamp}"`;
        if (args.filter) {
          filter += ` AND ${args.filter}`;
        }
    
        // Execute gcloud logging read
        const command = `logging read '${filter}' --project=${projectId} --limit=${limit} --format=json`;
        const result = await executeGcloud(command, 60000);
    
        // Parse JSON output
        let logs: any[] = [];
        try {
          logs = JSON.parse(result.stdout || '[]');
        } catch {
          logs = [];
        }
    
        // Transform to LogEntry format
        const logEntries: LogEntry[] = logs.map((log: any) => ({
          timestamp: log.timestamp || log.receiveTimestamp || '',
          severity: log.severity || 'DEFAULT',
          message: log.textPayload || log.jsonPayload?.message || JSON.stringify(log.jsonPayload || {}),
          resource: log.resource?.type,
          labels: log.labels,
        }));
    
        // Create error report for hi-ai integration
        const errorReport = createErrorReport(logEntries);
    
        if (args.format === 'json') {
          return {
            content: [
              {
                type: 'text',
                text: JSON.stringify({
                  project: projectId,
                  timeRange,
                  totalLogs: logEntries.length,
                  ...errorReport,
                  logs: logEntries,
                }, null, 2),
              },
            ],
          };
        }
    
        // Format text output
        const header = `📋 Cloud Logging 조회 결과\n프로젝트: ${projectId}\n시간 범위: ${timeRange}\n총 ${logEntries.length}개 로그\n`;
        const formattedLogs = formatLogEntries(logEntries);
    
        // 에러가 있으면 상세 리포트 (hi-ai 힌트 포함), 없으면 기본 요약
        const reportSection = errorReport.hasErrors
          ? createDetailedErrorReport(logEntries)
          : errorReport.summary;
    
        return {
          content: [
            {
              type: 'text',
              text: `${header}\n${reportSection}\n\n${formattedLogs}`,
            },
          ],
        };
      } catch (error: any) {
        return {
          content: [
            {
              type: 'text',
              text: formatError(error),
            },
          ],
          isError: true,
        };
      }
    }
  • src/index.ts:19-19 (registration)
    Import of gcpLogsReadDefinition and gcpLogsRead from './gcp/logs.js'.
    import { gcpLogsReadDefinition, gcpLogsRead } from './gcp/logs.js';
  • src/index.ts:79-79 (registration)
    Registration of gcpLogsReadDefinition in the tools array for the ListTools handler.
    gcpLogsReadDefinition,
Behavior3/5

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

Annotations already declare readOnlyHint true, idempotentHint true, etc. The description adds minimal context beyond the source (GCP Cloud Logging). It does not disclose output format, pagination, or error handling.

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

Conciseness4/5

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

Very short (two lines) but includes unnecessary pipe-separated tags. It is concise and front-loaded with the action, but structure could be cleaner.

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?

No output schema exists, and the description does not explain return values or pagination. With rich annotations and schema, it is adequate but leaves some gaps for a read tool.

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?

Input schema has 100% coverage with good param descriptions. The tool description does not add extra meaning beyond what the schema provides, so baseline 3 is appropriate.

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 it queries logs from GCP Cloud Logging, and the tags ('로그 조회', '에러 확인') indicate its purpose for error checking. It is distinguished from sibling 'gcp_run_logs' which is likely more specific to Cloud Run logs.

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?

Tags imply use cases (error checking, general log querying) but no explicit when-to-use or alternative guidance is provided. Sibling tools exist but are not mentioned.

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/su-record/hi-gcloud'

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