career-agent-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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyse_jobA | Score a job posting against the master profile using a deterministic weighted rubric (technical 25, experience 20, AI relevance 15, backend 10, seniority 10, location 5, compensation 5, growth 5, learnability 5). Returns the score breakdown, an APPLY / MAYBE / DO_NOT_APPLY / MANUAL_REVIEW decision, hard-reject reasons, and gaps split into learnable versus critical. |
| tailor_resumeA | Generate a role-specific resume by reordering and selecting from the master profile, then run the factual-validation gate over the result. Never adds a skill, employer, metric or certification that is not already in the profile. A resume that fails validation is returned with is_final=false and the blocking issues listed. |
| validate_resumeB | Run the factual-validation gate over a resume object independently. Use this to check a resume that was edited by hand or generated elsewhere. |
| track_applicationB | Add a job to the application tracker, or return the existing entry. Deduplicates on company + normalised role + canonical URL, so the same posting seen on two boards is one row. Never overwrites history. |
| update_application_statusB | Move an application to a new status. Appends to history; never rewrites it. |
| show_pipelineB | Return every tracked application and a count by status. |
| profile_summaryA | Return what the master profile can and cannot support: printable skills by label, and the skills deliberately recorded as LEARNING or UNSUPPORTED so they are never printed as competencies. |
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 7 tools
Each tool has a clearly distinct purpose: viewing pipeline data, tailoring a resume, validating a resume independently, tracking an application, updating status, summarizing profile capabilities, and analysing a job posting. Overlap between tailor_resume and validate_resume is explicitly clarified in the descriptions (one generates-and-validates, the other validates standalone).
Most tools follow a consistent verb_noun pattern (show_pipeline, tailor_resume, validate_resume, track_application, update_application_status, analyse_job). profile_summary is the lone exception, using a noun_noun form instead of a verb-led name.
Seven tools is well-scoped for a career-agent server, covering the key areas of application tracking, resume tailoring and validation, profile introspection, and job analysis without redundancy. Each tool appears to earn its place.
The surface covers core lifecycle operations: tracking applications, updating status, viewing the pipeline, summarizing profile support, analysing jobs, and tailoring/validating resumes. Minor gaps exist around deleting or archiving applications and editing the master profile, though these may be intentional given the explicit no-overwrite and read-only profile-summary design.