// SCAN REPORT

Interview Prep

17 tools. 7 can modify or destroy data without limits.

7 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

7 can modify or destroy data

10 read-only

17 tools total

Community server · catalogue entry verified 02/07/2026

How to control Interview Prep ↓

TOOL MAP

What Interview Prep exposes to your agents

Read (10) Write / Execute (7) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Interview Prep tools

Execute · Medium parse_job_posting_tool This tool fetches and processes external content (URL fetching, HTML parsing) and returns a stored record with an ID, implying it executes an outbound network request and writes a record to storage. Write · Low start_interview_prep_tool The tool creates a new session record in the system, which is a reversible write operation. Write · Low generate_questions_tool This tool generates interview questions based on user-provided context but does not modify, delete, or execute external operations. Write · Low save_research_note_tool This tool creates or stores a research note, which is a write operation.

7 of Interview Prep's 17 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Interview Prep

PolicyLayer is an MCP gateway — it sits between your AI agents and Interview Prep, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "generate_questions_tool": {
    "limits": [
      {
        "counter": "generate_questions_tool_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_weak_areas_tool": {
    "limits": [
      {
        "counter": "analyze_weak_areas_tool_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Interview Prep — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON INTERVIEW PREP →

Instant setup, no code required.

FULL CATALOGUE

All 17 Interview Prep tools

EXECUTE 1 tools

Execute parse_job_posting_tool Parse a job posting from a URL, raw HTML, or pasted text. Returns id + parsed fields.

WRITE 6 tools

Write generate_questions_tool Generate count interview questions using job + cv + research as context. Write save_research_note_tool Persist a research note for a prep session. Markdown content is fine. Write set_active_cv_tool Switch which CV other tools default to. Write set_model_tool Set the active model (persists to config). Requires the matching API key. Write start_interview_prep_tool Create a new interview prep session and return its id + metadata. Write submit_practice_answer_tool Submit an answer; returns evaluation (score + strengths + gaps + suggestion).

READ 10 tools

Read analyze_weak_areas_tool Summarize recurring gaps across practice sessions; recommends focus topics. Read get_active_model_tool Return the currently active model (provider + id) or None. Read get_practice_history_tool Return all practice sessions for an interview. Read get_research_tool Return all research notes for an interview, grouped by kind. Read list_cv_profiles_tool List all CVs with their is_active flag. Read list_interviews_tool Return all active interview prep sessions. Read list_models_tool List available models. Provider 'all' merges Gemini + OpenRouter (top 20). Read list_questions_tool Return previously generated questions for an interview. Read match_cv_to_job_tool Match a CV against a job posting. Returns score (0-100), strengths, gaps, summary. Read parse_cv_tool Parse a CV from a PDF or markdown file path. First CV becomes active automatically.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Interview Prep

How do I prevent bulk modifications through Interview Prep? +

The Interview Prep server has 6 write tools including generate_questions_tool, save_research_note_tool, set_active_cv_tool. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Interview Prep.

How many tools does the Interview Prep MCP server expose? +

17 tools across 3 categories: Execute, Read, Write. 10 are read-only. 7 can modify, create, or delete data.

How do I enforce a policy on Interview Prep? +

Register the Interview Prep MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Interview Prep tool call.

Deterministic rules across all 17 Interview Prep tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON INTERVIEW PREP →

Instant setup, no code required.

17 Interview Prep tools catalogued and risk-classified — across an index of 43,000+ MCP servers.