The Utility MCP Server provides general-purpose utility tools for Computer Agent ecosystem integration:
Get current datetime: Retrieve current date/time in any timezone with multiple format options (ISO, readable, timestamp, custom)
Calculate time differences: Compute duration between two dates or from a past date to present, with detailed breakdown of days, hours, minutes, and seconds
Download Read.AI meeting data: Download meeting transcripts and summaries from Read.AI platform (requires API key, currently limited due to lack of public API documentation)
Check server status: Verify configuration and availability of all utility tools
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Utility MCP Server what's the current time in Tokyo?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
General-purpose MCP server providing utility tools for Computer Agent ecosystem integration.
Tool: get_current_datetime
Purpose: Get current date/time in any timezone with multiple format options
Status: ✅ Ready - No configuration required
Timezones: Full pytz database support (UTC, US/Eastern, Europe/London, America/Sao_Paulo, etc.)
Formats: ISO, readable, timestamp, custom
Tool: calculate_time_difference
Purpose: Calculate time differences between dates or from a date to now
Status: ✅ Ready - No configuration required
Features: Detailed breakdown (days, hours, minutes, seconds), multiple input formats
Tool: download_meeting_data
Purpose: Download meeting transcripts and summaries from Read.AI platform
Status: ⚠️ API Key Required - Read.AI API documentation not publicly available
Configuration: Requires READ_AI_API_KEY environment variable
Tool: util_server_status
Purpose: Check configuration and availability of all utility tools
Related MCP server: Atlas MCP Server
cd /home/danfmaia/_repos/_mcp/util-mcp
uv installThe server is configured in /home/danfmaia/.cursor/mcp.json:
{
"utilities": {
"name": "Utility MCP Server",
"type": "command",
"command": "/home/danfmaia/.local/bin/uv",
"args": [
"--directory",
"/home/danfmaia/_repos/_mcp/util-mcp",
"run",
"util_server.py"
]
}
}uv run util_server.pyuv run python test_datetime.pyGet current time in different timezones:
get_current_datetime("UTC", "readable") → "Tuesday, September 09, 2025 at 11:56:34 PM UTC"
get_current_datetime("America/Sao_Paulo", "iso") → "2025-09-09T20:56:34-03:00"
get_current_datetime("US/Eastern", "custom") → "2025-09-09 19:56:34 EDT"
Calculate time differences:
calculate_time_difference("2025-09-09 10:00:00", "2025-09-09 14:30:00", "UTC") → "4 hours, 30 minutes"
calculate_time_difference("2025-09-08 15:00:00", "", "UTC") → Time from yesterday 3pm to now
Current Status: No publicly available Read.AI API documentation or third-party access endpoints identified.
Search Evidence:
Cursor native @Web search: No API documentation found
Custom MCP web research: No API endpoints discovered
Technical assessment: Browser automation would require significant maintenance overhead
Recommendation: Manual download workflow until Read.AI provides official API access.
mcp: Model Context Protocol framework
httpx: HTTP client for potential API calls
pytz: Timezone database for datetime operations
fastmcp: Simplified MCP server development
Built using FastMCP framework for simplified MCP server development and maintenance.
Calculate the time difference between two datetimes or from a start time to now.
Args:
start_datetime: Start datetime in ISO format (YYYY-MM-DD HH:MM:SS or YYYY-MM-DDTHH:MM:SS)
end_datetime: End datetime in ISO format (optional - defaults to current time)
timezone_name: Timezone for interpretation (default: UTC)
Returns:
Time difference with detailed breakdown
Inputs: start_datetime (required), end_datetime, timezone_name. Returns: result
Download meeting transcript and/or summary from Read.AI.
Args:
meeting_id: Read.AI meeting ID
include_transcript: Whether to download the full transcript (default: True)
include_summary: Whether to download the meeting summary (default: True)
Returns:
Meeting data in formatted text or JSON structure
Inputs: meeting_id (required), include_transcript, include_summary. Returns: result
Get the current date and time in the specified timezone and format.
Args:
timezone_name: Timezone name (e.g., "UTC", "US/Eastern", "Europe/London", "America/Sao_Paulo")
format_type: Format type ("iso", "readable", "timestamp", "custom")
Returns:
Current datetime in the requested format
Inputs: timezone_name, format_type. Returns: result
Check the status of all utility server integrations.
Returns:
Status report of available utilities and their configuration
Inputs: no named parameters. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: time calculation, meeting data download, current datetime retrieval, and server status check. The descriptions clearly differentiate their functions, eliminating any risk of misselection.
Three tools follow a consistent verb_noun pattern (calculate_time_difference, download_meeting_data, get_current_datetime), but util_server_status deviates by using a noun_verb_noun structure. The deviation is minor and doesn't significantly impact readability.
Four tools is reasonable for a utility server, though slightly thin for covering multiple domains like time and meeting data. Each tool earns its place, but the scope feels a bit broad for just four tools.
For the time-related tools, there's basic coverage (calculate difference, get current time), but missing operations like timezone conversion or date arithmetic. For meeting data, download is covered but no create/update/delete. The server status tool is standalone. Notable gaps exist that agents may need to work around.
Manage Speko voice-AI agents, sessions, calls, phone numbers, knowledge bases, evals, and docs.
Machine-readable utilities and datasets for AI agents.
AI Agent Utility Layer for agent safety, web monitoring, crypto research and tool discovery.
13 free utility tools for AI agents: web text, markdown, hashing, IDs, dates, units, JSON.
