Skip to main content
Glama

Interview Prep AI — MCP Agent

An end-to-end interview coach that uses a real Model Context Protocol (MCP) server to ground an OpenAI agent in a candidate's resume and a target job description.

The project demonstrates MCP tool discovery, OpenAI Responses API tool calling, multi-step agent orchestration, document ingestion, deterministic evaluation logic, and a polished Streamlit UI.

What it does

  • Upload a resume (PDF, DOCX, TXT, or MD)

  • Upload or paste a job description

  • Analyze matched skills and priority gaps

  • Generate role-specific technical, behavioral, and system-design questions

  • Evaluate answers with a STAR, relevance, specificity, and quantified-impact rubric

  • Inspect every MCP call in an in-app activity trace

Related MCP server: four-leaf-mcp

Architecture

flowchart LR
    U[Candidate] --> UI[Streamlit UI]
    UI --> A[OpenAI Responses agent]
    A <-->|tool schemas and calls| C[MCP client]
    C <-->|stdio| S[FastMCP server]
    S --> R[(Resume)]
    S --> J[(Job description)]
    S --> G[Gap analysis]
    S --> Q[Question generator]
    S --> E[Answer evaluator]

This is intentionally a genuine client/server MCP design. The LLM discovers JSON schemas from the MCP server, decides which tools to call, and receives each result through the Responses API function-calling loop.

MCP tools

Tool

Purpose

get_resume()

Reads the uploaded resume

get_job_description()

Reads the target job description

analyze_skill_gaps()

Compares resume evidence with JD requirements

generate_interview_questions()

Produces targeted practice questions

evaluate_answer()

Scores an answer and returns a coaching rubric

Run locally

Prerequisites: Python 3.11+ and an OpenAI API key.

git clone https://github.com/YOUR_USERNAME/interview-prep-mcp.git
cd interview-prep-mcp
python -m venv .venv
source .venv/bin/activate       # Windows: .venv\Scripts\activate
pip install -e ".[dev]"
cp .env.example .env
# Add your OPENAI_API_KEY to .env
streamlit run app.py

The default is gpt-5.4-mini, chosen as a cost-conscious tool-calling model. Set OPENAI_MODEL in .env to use a different compatible model.

Test the MCP server

Run the unit tests without an API key:

pytest
ruff check .

Start the MCP server directly over stdio:

interview-prep-server

Privacy

Uploaded resume and JD text are stored only in .interview_prep/ on the local machine. That directory and .env are Git-ignored. Document text is sent to OpenAI only when the agent calls the relevant MCP tool during a workflow.

Design choices

  • Auditable orchestration: the UI displays the exact MCP tools used for each answer.

  • Testable core: skill comparison and answer scoring are deterministic; the LLM interprets and coaches rather than hiding all logic in a prompt.

  • No invented experience: the system prompt requires resume evidence before claims about the candidate.

  • Bounded agent loop: tool execution stops after eight rounds to prevent runaway calls.

Resume bullets

  • Built an MCP-based Interview Preparation Agent using Python and OpenAI's Responses API, enabling an LLM to dynamically access resumes, job descriptions, and evaluation tools for personalized interview workflows.

  • Implemented agentic tool-calling workflows for skill-gap analysis, targeted question generation, and rubric-based answer evaluation, with an auditable MCP activity trace.

Roadmap

  • Persist separate interview sessions in SQLite

  • Add voice answers and transcription

  • Export a preparation report as PDF

  • Add eval datasets for question quality and scoring consistency

  • Deploy the MCP server with authenticated Streamable HTTP transport

References

License

MIT

Available Tools

5 tools
analyze_skill_gapsB

Compare the uploaded resume and job description and return evidence-based skill coverage.

Inputs: no named parameters. Returns: result

evaluate_answerB

Score an interview answer against relevance, STAR structure, specificity, and impact.

Inputs: question (required), answer (required). Returns: result

generate_interview_questionsB

Generate 1–10 personalized technical, behavioral, and design interview questions.

Inputs: focus_areas (required), question_count. Returns: result

get_job_descriptionA

Read the target job description. Call before analyzing fit or generating questions.

Inputs: no named parameters. Returns: result

get_resumeA

Read the candidate's uploaded resume. Call before personalizing advice.

Inputs: no named parameters. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: data retrieval (get_resume, get_job_description), comparison (analyze_skill_gaps), question generation (generate_interview_questions), and answer evaluation (evaluate_answer). There is no overlap between tool responsibilities.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case (e.g., analyze_skill_gaps, get_resume). No mixing of conventions or vague verbs.

    Tool Count5/5

    With 5 tools covering data ingestion, analysis, generation, and evaluation, the count is well-scoped for an interview preparation assistant. Each tool earns its place without redundancy.

    Completeness4/5

    The tool set covers the core workflow: retrieve inputs, analyze gaps, generate questions, and evaluate answers. A minor gap is that there is no tool to generate specific improvement suggestions based on answer scores, but the existing evaluate_answer provides scoring that indirectly supports feedback.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      Our MCP Tools are designed to enhance AI-driven automated interview services by ensuring a seamless and contextually relevant candidate assessment process. These tools leverage advanced AI models to analyze responses, evaluate competencies, and provide real-time feedback, ma
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Job search assistant and interview prep inside any ai tool via MCP or public skill. Every tool you'll need for your job search in one product.
      15 npm
      8
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables MCP clients to analyze resumes for ATS compatibility, parse job descriptions, get optimization and roast-style critiques, and generate tailored resumes with shareable preview links.
      6
      57 npm
      MIT