CareerPilot
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CAREERPILOT_DB | No | Path to SQLite database file. Default is ~/.careerpilot/careerpilot.db. | |
| CAREERPILOT_TOKEN | No | Bearer token for HTTP auth. Used when running with --http. | |
| CAREERPILOT_POLL_SECONDS | No | Poll interval for watched searches in seconds (default 900). | 900 |
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": true,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| watch_searchA | Create a watched search: CareerPilot re-runs it in the background and notifies subscribers of careerpilot://watches when NEW jobs are posted. The current results become the baseline — only jobs appearing later count as new. |
| check_watchesA | Re-run all watched searches right now and report newly-found jobs. |
| unwatchC | Delete a watched search. |
| mark_watch_reviewedA | Clear the 'new' flag on a watch's findings after you've reviewed them. |
| search_jobsA | Search live job openings across free job boards. Args: query: Keywords, e.g. "python backend" or "devops kubernetes". source: "remotive", "remoteok", "hn" (Hacker News Who is Hiring), or "all". limit_per_source: Max results per board (1-20). |
| save_jobA | Save a job to the shortlist. Pass the fields from a search_jobs result, or enter a job found elsewhere manually (source='manual'). |
| track_applicationB | Record that you applied to a saved job. Creates a pipeline entry with status 'applied'. |
| update_applicationB | Update an application's status and/or notes. Valid statuses: saved, applied, screening, interviewing, offer, accepted, rejected, withdrawn, ghosted. |
| schedule_follow_upC | Schedule a follow-up reminder for an application. Date format: YYYY-MM-DD. |
| list_due_follow_upsA | List follow-ups that are due today or overdue. |
| set_profileC | Store a profile fact used by prompts and fit-scoring. Useful fields: name, role, years_experience, skills, location, salary_expectation, resume_path. |
| delete_applicationA | Delete an application from the pipeline (asks the user to confirm first). |
| score_job_fitA | Score how well a saved job matches the user's profile/resume (0-10 with reasoning). Demonstrates MCP sampling: this server sends a prompt to the CLIENT's LLM and uses the completion — the server needs no API key of its own. |
| find_resumeA | Locate the user's resume in folders the client has granted access to (MCP roots), and remember its path in the profile. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| tailor_resume | Rewrite resume bullet points to target a specific saved job. |
| cover_letter | Draft a cover letter for a saved job. |
| interview_prep | Generate likely interview questions and strong answers for a saved job. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| watches_resource | All watched searches and how many unreviewed new jobs each has. |
| pipeline | The full application pipeline, grouped by status. |
| saved_jobs | All jobs saved to the shortlist. |
| profile_resource | The user's stored profile (skills, experience, preferences). |
TDQS
Scored across 14 tools
Each tool has a clearly distinct purpose: searching jobs, managing watches, tracking applications, scheduling follow-ups, etc. There is no ambiguity between tools like 'watch_search' and 'check_watches' or 'list_due_follow_ups' and 'schedule_follow_up' as they handle different actions.
All tool names follow a consistent verb_noun pattern using underscores (e.g., search_jobs, save_job, track_application). Even 'unwatch' and 'set_profile' fit the convention. No mixing of styles or vague verbs.
14 tools is well-scoped for a career assistant covering job search, application tracking, watches, profile management, and fit scoring. Each tool serves a clear role without being excessive or insufficient.
The tool set covers core workflows: searching, saving, applying, tracking, scheduling, and scoring. Minor gaps exist, such as no tools to list saved jobs or list all applications, which an agent might need to navigate the pipeline programmatically.