career-scout-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| rescore_postingA | Re-score one posting against the current rubric via the configured LLM. Loads the posting, loads the current rubric, scores it via LiteLLM, persists the new score row, and returns the structured result. Raises ValueError if posting not found; ScoringError on LLM/parse failure. |
| tag_mismatched_scoreB | Record that a stored score does not match operator judgment. Writes to tagged_mismatches.db. The tune_rubric prompt aggregates these for rubric refinement workflows. Reason must be non-empty. |
| query_postingsB | List postings matching the filter criteria, with their latest score. Returns only postings that have at least one score (the JOIN excludes never-scored ones). Empty result is valid output. |
| regenerate_digestA | Render a digest HTML of the current top-20 postings. Output path is settings.digest_output_path (operator-controlled, not user-input — no path traversal vector). Writes a single self-contained HTML file with minimal inline styling. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| tune_rubric | Produce a prompt asking the LLM to suggest rubric refinements. Aggregates the most recent N tagged mismatches and the current rubric, then asks the LLM to identify scoring-pattern problems and propose specific rubric language changes grounded in those cases. |
| analyze_digest_trends | Produce a prompt asking the LLM to analyze scoring history trends. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| digest_current | Return the most recent digest HTML, or a placeholder if none exists. |
| scores_history_default | Return the most recent 50 scoring records. |
| rubric_current | Return the current rubric text + version + source path. |
| config_scrapers | Return the synthetic scraper config (demonstration only). |
| stats_summary | Return aggregate stats for dashboard / overview consumption. |
| get_health | Aggregate health into a single dict. |
TDQS
Scored across 4 tools
Each tool targets a distinct action: re-scoring, tagging mismatches, querying postings, and generating a digest. No overlap in purpose.
All tool names follow the verb_noun pattern in snake_case, providing a predictable and consistent naming convention.
With 4 tools, the server is well-scoped for focused tasks like scoring, mismatch recording, querying, and digest generation without being too heavy or too thin.
The set covers scoring, discrepancy tracking, and reporting but lacks tools for CRUD operations on postings or rubric management, leaving notable gaps in a typical career management workflow.