local-tech-digest-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TZ | No | Timezone for scheduling | America/New_York |
| SMTP_HOST | No | SMTP server host | smtp.gmail.com |
| SMTP_PASS | Yes | Gmail App Password (16-character code without spaces) | |
| SMTP_PORT | No | SMTP server port | 587 |
| SMTP_USER | Yes | Gmail email address for SMTP authentication | |
| SMTP_SECURE | No | Whether to use secure connection (true/false) | false |
| NOTIFY_EMAIL | Yes | Email address to receive digests | |
| MIN_JOB_SCORE | No | Minimum job score to include in digest (0-14) | 0 |
| MAX_JOBS_PER_DOMAIN | No | Maximum job cards per domain per email | 25 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_jobsA | Scrape all 6 job sources (SimplifyJobs, RemoteOK, The Muse, Remotive, Jobicy, Arbeitnow), apply 4-gate filter, score, and store. Returns per-source breakdown. |
| list_new_jobsA | List un-notified jobs sorted by score. Optional domain and min_score filters. |
| get_top_matchesA | Return top N jobs by stack-match score across all stored jobs. |
| search_jobsB | Full-text search across title, company, tags, domain. |
| filter_jobsB | Filter stored jobs by domain, type, status, and min score. |
| mark_jobA | Update the application status of a job by its ID. |
| get_pipelineA | Show your job application pipeline grouped by status. |
| suggest_skillsA | Analyse the stored job database to suggest skills most in-demand that are NOT in your current stack. |
| fetch_conferencesA | Scrape confs.tech for upcoming USA tech conferences. |
| list_upcoming_conferencesB | List upcoming conferences in the next N days (default 60). |
| search_conferencesC | Search conferences by keyword. |
| send_digest_emailA | Manually trigger a digest email. mode="daily" → jobs only; mode="weekly" → jobs + conferences. |
| get_statsB | Database counts for jobs (by status, type, salary) and conferences. |
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 13 tools
Tools are mostly distinct: fetch, list, search, filter, mark, pipeline, skills, conferences, email, stats each have clear roles. Minor overlap exists among job listing tools (list_new_jobs, get_top_matches, search_jobs, filter_jobs) but descriptions clarify their specific filters and purposes.
All tool names follow a consistent verb_noun pattern using lowercase with underscores (fetch_, list_, get_, search_, filter_, mark_, suggest_, send_). The pattern is uniform, and there are no mixed conventions or ambiguous verbs.
13 tools is well within the ideal 3-15 range for a server with this scope. The count feels balanced: 8 tools for job operations, 3 for conferences, plus digest email and stats, each earning its place without bloat.
The surface covers the main workflows: fetching/ingesting data, searching/filtering, managing a job pipeline, suggesting skills, sending digests, and viewing stats. Minor gaps exist such as no dedicated get_job_details or conference detail view, but these are workable via searches/filters.