career_monitor
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CAREER_PYTHON | No | Python interpreter path used for PDF processing (default is 'python'). | |
| CAREER_POWERSHELL | No | PowerShell executable path (default is 'powershell.exe'). | |
| CAREER_BROWSER_PATH | No | Path to a custom Chrome browser (default uses Playwright Chromium). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| monitorA | Control the HH new-vacancy notifications (no model analysis): status, start every 15 minutes, stop, check now, login (open separate Chrome for manual HH login), login_done (close login window after user confirms). Requires local Telegram setup. First scan establishes a baseline without old-vacancy notifications. Works only while this MCP process is alive. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of ambiguity or overlap between tools. The single 'monitor' tool clearly bundles all control actions, making selection trivial.
With a single tool, there are no naming conventions to compare or contradict. The name 'monitor' is a simple verb that broadly reflects its purpose, though it is somewhat vague, consistency is perfect.
A single tool for a niche monitoring purpose is borderline; it works but feels thin for the variety of actions (start, stop, login, etc.) it claims to handle. The server could benefit from separating concerns into distinct tools, but the count is not extreme.
The tool covers the main lifecycle actions (start, stop, check, login), but lacks configuration options such as customizing the search query or notification filters. It also depends on external setup, leaving gaps that could cause agent failures when specific monitoring needs arise.