interview-prep-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Direct Gemini API access. | |
| OPENROUTER_API_KEY | No | Enables set_model to switch to any of 200+ OpenRouter models. |
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": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| parse_job_posting_toolA | Parse a job posting from a URL, raw HTML, or pasted text. Returns id + parsed fields. |
| parse_cv_toolB | Parse a CV from a PDF or markdown file path. First CV becomes active automatically. |
| list_cv_profiles_toolA | List all CVs with their is_active flag. |
| set_active_cv_toolB | Switch which CV other tools default to. |
| match_cv_to_job_toolB | Match a CV against a job posting. Returns score (0-100), strengths, gaps, summary. |
| start_interview_prep_toolC | Create a new interview prep session and return its id + metadata. |
| list_interviews_toolA | Return all active interview prep sessions. |
| save_research_note_toolC | Persist a research note for a prep session. Markdown content is fine. |
| get_research_toolA | Return all research notes for an interview, grouped by kind. |
| generate_questions_toolC | Generate count interview questions using job + cv + research as context. |
| list_questions_toolC | Return previously generated questions for an interview. |
| submit_practice_answer_toolC | Submit an answer; returns evaluation (score + strengths + gaps + suggestion). |
| get_practice_history_toolC | Return all practice sessions for an interview. |
| analyze_weak_areas_toolC | Summarize recurring gaps across practice sessions; recommends focus topics. |
| list_models_toolC | List available models. Provider 'all' merges Gemini + OpenRouter (top 20). |
| set_model_toolC | Set the active model (persists to config). Requires the matching API key. |
| get_active_model_toolA | Return the currently active model (provider + id) or None. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| daily_prep | |
| mock_interview |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Each tool targets a distinct operation: CV parsing vs job parsing, question generation vs answer submission, session management vs research notes. No two tools have overlapping purposes; even similar verbs like 'list' and 'get' are applied to different resources (interviews vs practice history vs questions).
All tools follow a consistent verb_noun_tool pattern in snake_case (e.g., parse_cv_tool, list_interviews_tool, set_active_cv_tool). Verbs are descriptive and uniformly placed at the start. No mixing of conventions or cryptic abbreviations.
17 tools is well-scoped for a specialized interview preparation server. The count covers essential workflows (CV management, job parsing, question generation, practice, feedback, research, model config) without being overwhelming or sparse.
Core CRUD-like operations are present for key entities (create/list for interviews, parse/list for CVs and jobs, generate/list for questions). Minor gaps: no update or delete tools for CVs, job postings, or research notes, but the primary workflow (parse-match-practice-analyze) is fully covered.