Active Jobs Db MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | Yes | API密钥，用于认证 |
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 | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_jobs_7_daysC | Search and retrieve jobs on title, description, location, remote, and organization. Optionally add a text or html description |
| ultraB | Search and retrieve jobs modified during the last 24h. Run this API at the same time every day to get newly modified jobs without any duplicates |
| ultra_2A | Firehose API, includes jobs we discovered in the last hour. Perfect for one or more hourly API calls. Requires Ultra or Mega subscription |
| ultra_3B | You can use this endpoint to backfill your job application before moving on to the 7d, 24h, or hourly endpoint |
| get_jobs_24hB | Search and retrieve jobs on title, description, location, remote, and organization. Optionally add a text or html description. The jobs in this API have been indexed by us during the last 24 hours. |
| ultra_4A | Contains IDs of jobs that were flagged as expired yesterday. Updates once per day at 01:30 UTC. Requires Ultra or Mega subscription |
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 6 tools
The get_jobs_* tools are somewhat distinguishable by time window, but ultra and get_jobs_24h both cover 24-hour periods, creating overlap. The ultra_2, ultra_3, and ultra_4 names provide no semantic hint about their purpose, making it difficult to select the right tool without reading descriptions.
The naming is highly inconsistent: get_jobs_7_days and get_jobs_24h follow a verb_noun_time pattern, while the other four tools are named ultra, ultra_2, ultra_3, and ultra_4 with no descriptive verb or noun and arbitrary numeric suffixes. This mixes conventions and obscures functionality.
Six tools is a reasonable number for a jobs database server, covering different time-based queries without excessive overlap or bloat. The count fits within the typical well-scoped range.
The tools cover several retrieval scenarios (7-day, 24h, hourly, backfill, expired), but there is no direct job-by-ID lookup or a general search across all jobs. Additionally, the overlap between get_jobs_24h and ultra suggests unclear boundaries rather than comprehensive coverage.