Multi-purpose MCP server providing tools for Google Workspace integration, Korean weather data, code execution, document retrieval, web search, text extraction, stock trading information, and AWS service operations
21 tools with highly inconsistent quality. Most lack proper input schemas (cannot verify in source). Descriptions vary from adequate (gog_* tools) to minimal (retrieve, draw_stock_trend). No tool annotations (readOnlyHint/destructiveHint). Many tools accept free-form strings where enums should exist (e.g., gog_run accepts arbitrary command strings). Output schemas undocumented. Error handling guidance absent. STDIO transport caps protocol readiness at 50, limiting overall utility.
Draw a graph of the given trend.
Extract text from an image using an LLM (AWS Bedrock). Provide either image_base64 or image_path. The image is resized automatically if it exceeds size limits (5MB, ~2M pixels).
Get Korean air quality forecast for a specified location.
Get Korean weather forecast and observations for a specified location.
Show available calendar event colors (IDs 1-11).
List calendar events for a date range.
gog_run accepts arbitrary command strings with no validation or enum constraints. LLMs can pass invalid subcommands, malformed arguments, or injection payloads. Should split into discrete tools (gog_gmail_search, gog_calendar_create, etc.) or validate against a whitelist.
Output schemas undocumented for all 21 tools. LLMs cannot plan downstream tool calls or extract required fields (e.g., does gog_gmail_search return thread_id, message_id, or both?). Add explicit return type documentation.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 59 | <=2025-11-25 | v2 |
List Google Contacts.
Read Google Docs content as plain text.
Search Google Drive files.
Search Gmail messages (per email, ignores threading). Use when you need every individual email.
Search Gmail threads by query. Returns one row per thread.
Run a gog CLI command for Google Workspace (Gmail, Calendar, Drive, Contacts, Sheets, Docs). Examples: - Gmail search: gmail search 'newer_than:7d' --max 10 - Gmail messages: gmail messages search "in:inbox from:example.com" --max 20 - Gmail send: gmail send --to [email protected] --subject "Hi" --body "Hello" - Calendar events: calendar events primary --from 2025-03-01 --to 2025-03-31 - Calendar create: calendar create primary --summary "Meeting" --from 2025-03-15T10:00 --to 2025-03-15T11:00 - Drive search: drive search "query" --max 10 - Contacts: contacts list --max 20 - Sheets get: sheets get <sheetId> "Tab!A1:D10" --json - Docs cat: docs cat <docId> For read operations, add --json --no-input for machine-readable output. Confirm before sending mail or creating events.
Get values from a Google Sheet range.
Execute Python code to perform calculations or data processing. You MUST provide the 'code' parameter. Rules: - If you want to see the output of a value, you should print it out with `print(...)`. This is visible to the user. - The code should be written in English.
Execute a Python script to draw a graph. You MUST provide the 'code' parameter. Rules: - Since Python runtime cannot use external APIs, necessary data must be included in the code. - The graph should use English exclusively for all textual elements. - Do not save pictures locally because the runtime does not have filesystem. - When a comparison is made, all arrays must be of the same length.
Search the user's knowledge base (RAG) for relevant documents. Use together with web/wiki search when looking up information the user may have stored.
Returns the last ~period days price trend of the given company name as a JSON string.
Performs a web search using Tavily's AI search engine and generates a direct answer to the query, along with supporting search results.
Searches recent news articles using Tavily's specialized news search functionality.
Performs a comprehensive web search using Tavily's AI-powered search engine. Excels at extracting and summarizing relevant content from web pages, making it ideal for research, fact-finding, and gathering detailed information.
Execute AWS service operations using boto3 with comprehensive error handling and validation. This tool provides a universal interface to AWS services, allowing you to execute any operation supported by boto3. It handles authentication, parameter validation, response formatting, and provides helpful error messages with schema recommendations when invalid parameters are provided.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Agents cannot distinguish safe read operations from destructive writes. gog_gmail_send and use_aws are WRITE operations but lack destructiveHint. gog_gmail_search is READ_ONLY but lacks readOnlyHint.
Minimal error handling guidance. gog_run returns {status, stdout, stderr} but does not guide LLM on recovery (e.g., 'gog not found, install from https://gogcli.sh'). No categorization of retryable vs fatal errors.
retrieve and draw_stock_trend have descriptions under 40 characters ('Search the user's knowledge base (RAG)...', 'Draw a graph of the given trend.'). Insufficient context for LLM tool selection.