smart job apply 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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_login_statusA | Verify whether login sessions are active for job platforms before applying. Returns status for each platform (logged in, missing session, expired). Always check login status before attempting real job applications. |
| login_accountA | Open a visible browser window for the user to manually log in to a job platform (via OTP, Google sign-in, or password). The authenticated session/cookies are automatically captured and saved for automated job applies. |
| save_sessionB | Alias for login_account. Opens a visible browser window so the user can log in to a job portal and persist authenticated cookies. |
| search_jobsB | Search for jobs across LinkedIn, Naukri, Wellfound, Indeed, Hirist, Glassdoor, Instahyre, and Cutshort using browser automation. Returns job listings with match scoring against your candidate profile. |
| filter_jobsB | Filter and rank jobs by relevance against the candidate profile. Strictly eliminates over-experienced roles (3+ or 5+ years senior roles) and blacklisted titles. |
| apply_jobB | Apply to a single job via browser automation. Fills standard fields, uploads resume, and handles platform submission. If the user is not logged in, prompts for login or reports clear login instructions. |
| bulk_applyA | Apply to multiple jobs in sequence with rate-limiting (10–25s delay) and safety caps. Skips already applied jobs and caps applications per company. Validates user login sessions before starting real submissions. Use dry_run=true to preview without submitting. |
| get_application_statusA | Retrieve tracked job applications from the local SQLite database, including application dates, platform breakdown, and status. |
| extract_job_contactsA | Extract recruiter emails, career application URLs, and contact names from raw job descriptions. Used to find recruiter emails for follow-up outreach via Gmail. |
| check_profile_configA | Inspect and validate the local configuration (~/.job-apply-mcp/config.json), confirming resume PDF existence, candidate details, and autofill fields. |
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 10 tools
login_account and save_session are explicitly aliases, which creates unnecessary overlap, though the other tools are mostly distinct. search_jobs and filter_jobs have some conceptual overlap, but their descriptions clarify the difference.
All tools use consistent snake_case with clear verb_noun or verb structures. The pattern is predictable throughout the set.
10 tools is well-scoped for a job application automation server. Each tool covers a distinct step in the workflow, and none feel extraneous beyond the minor alias duplication.
The core job application lifecycle is well covered: login, search, filter, apply, bulk apply, status, contacts, and config validation. Minor gaps exist, such as no tool to update the candidate profile or modify the blacklist/config, but these are workable.