Your AI compass from private sector to federal career — MCP server for USAJobs API
Strong tool naming (all verb-first), comprehensive parameter schemas with Zod validation, and clear descriptions. Most tools have 50-150 char descriptions meeting the 10-1024 baseline. All 10 tools have explicit input schemas with type definitions and parameter descriptions. Key gaps: no output schemas documented, no error recovery guidance, no tool annotations (readOnlyHint/destructiveHint), and some parameter descriptions lack format/constraint details. The save_cv tool (WRITE risk) lacks confirmation/dry-run pattern. Overall solid foundation with room for production hardening.
Calculate federal GS salary with locality pay adjustment. Returns base pay plus locality-adjusted pay for a specific grade, step, and location. Covers all 15 GS grades and ~58 locality pay areas.
Compare your saved CV against a specific job posting. Returns your CV and the job requirements side by side for analysis. Requires a saved CV.
Compare 2-5 federal job postings side by side. Returns salary, grade, clearance, location, and more for each job. Makes one API call per job.
Explain federal career concepts in plain language: GS grades, security clearances, hiring paths, pay plans, and more.
Extract KSA (Knowledge, Skills, Abilities) requirements from a federal job posting. Categorizes requirements by type (knowledge, skill, ability, experience, education, certification, other) and optionally matches them against your saved CV.
No output schemas documented. LLMs cannot plan downstream calls or extract required fields without knowing response structure. All 10 tools lack documented return types.
save_cv (WRITE operation) lacks confirmation/dry-run pattern. Agents could overwrite CV without verification, risking data loss.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint). Clients cannot distinguish safe reads from destructive writes without parsing descriptions.
Error handling lacks recovery guidance. No indication of retryable vs fatal errors, or what the LLM should do next (e.g., 'CV not found. Call save_cv() first.').
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 66 | <=2025-11-25 | v2 |
Find federal jobs that match your saved CV. Extracts skills and keywords from your CV and searches USAJobs. Requires a saved CV.
Read your saved CV. Returns the CV text and metadata (when it was saved, original format).
Get full details for a specific federal job posting including duties, qualifications, and how to apply.
Save your CV text locally for automatic use in job matching and qualification checks. The CV is stored only on your machine.
Search federal job openings on USAJobs. All parameters are optional. Returns job listings with title, agency, salary, location, and apply URL.
Parameter descriptions lack format/constraint details. E.g., 'grade' accepts 'GS-13' or '13' but description doesn't specify format; 'location' examples suggest free-form but should clarify valid locality pay areas.