Skip to main content
Glama
Content Interviewer MCP

Content Interviewer MCP

by zuperRuslana

Content Interviewer MCP

Content Interviewer MCP is a local Python MCP server that discovers research topics, interviews you to uncover your unique perspective, and turns your insights into content such as short-form Reel scripts.

Project status

The MVP is complete and ready for local use with MCP-compatible clients such as Codex.

Related MCP server: instagram-research

Requirements

  • Python 3.11 or newer

  • SQLite with FTS5 support

Development setup

Create a virtual environment:

python3 -m venv .venv

Activate it:

source .venv/bin/activate

Install the project and its development dependencies:

python -m pip install -e ".[dev]"

Development checks

Run the tests:

python -m pytest

Run linting:

python -m ruff check .

Check that the source compiles:

python -m compileall -q src

Architecture

The initial version uses:

  • the official Python MCP SDK

  • Pydantic for input validation

  • SQLite for local persistence

  • SQLite FTS5 for full-text search

  • pytest for automated testing

  • Ruff for linting

  • STDIO for communication with Codex

The project starts as a local, single-user application. SQLite keeps private data local without requiring a separate database server. FTS5 provides the initial search implementation; embeddings will only be considered after the MVP demonstrates a need for them.

Project structure

src/
  content_interviewer/
    server.py
    config.py
    db/
      connection.py
      migrations/
      repositories/
    services/
    tools/
    schemas/
    utils/
    resources/
tests/
fixtures/
docs/
data/

Privacy

ChatGPT exports, SQLite databases, environment files, logs, and other private local data must not be committed to version control. The server must not log complete imported conversations or article bodies.

MVP boundaries

Version 0.1 does not include a web dashboard, multi-user accounts, remote deployment, embeddings, automatic social-media publishing, or live access to a ChatGPT account.

Available Tools

10 tools
add_articleA

Fetch, extract, and save one user-provided public article URL. Private and local network targets are rejected.

Inputs: url (required). Returns: object

import_chat_historyA

Import one explicitly selected ChatGPT conversations.json export into the local private database.

Inputs: file_path (required). Returns: object

list_topic_candidatesA

List recent unreviewed research articles for content-idea evaluation. Returns deterministic metadata and short excerpts.

Inputs: limit. Returns: object

manage_sourceC

Add, list, enable, or disable RSS research sources.

Inputs: action (required), url, name, source_id. Returns: object

refresh_sourcesA

Refresh enabled RSS sources and ingest unseen articles. Returns counts and article metadata, not article bodies.

Inputs: no named parameters. Returns: object

save_content_assetA

Save a versioned Reel script, LinkedIn draft, caption, or tutorial outline for a content idea.

Inputs: content (required), idea_id (required), asset_type (required). Returns: object

save_content_ideaC

Save a structured content idea for later development.

Inputs: angle (required), topic (required), audience (required), difficulty (required), +7 more. Returns: object

save_interview_answerB

Save Ruslana's confirmed answer to one focused interview question for a content idea.

Inputs: answer (required), idea_id (required), question (required). Returns: object

search_personal_contextA

Search imported conversations and notes for evidence of relevant personal experience.

Inputs: query (required), limit. Returns: object

update_content_statusC

Move a content idea through the allowed status workflow.

Inputs: idea_id (required), new_status (required). Returns: object

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct resource or workflow phase: personal context, content ideas, status updates, imports, articles, sources, topic candidates, interview answers, and assets. Even the three 'save' tools are clearly separated by noun and description.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun snake_case pattern, such as search_personal_context, refresh_sources, and save_content_asset. The naming conventions are uniform and predictable throughout the set.

    Tool Count5/5

    Ten tools is well within the ideal range for a specialized content workflow. Each tool covers a meaningful operation without redundancy or bloat.

    Completeness3/5

    The set covers ingestion, ideation, status management, and asset creation well, but there are notable gaps: no list/get tool for saved content ideas, no retrieval of saved interview answers or content assets, and no way to view full article bodies. These omissions create potential dead ends in the workflow.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables local-first Instagram reel production entirely over MCP, turning raw footage, URLs, or topics into finished reels with script generation, stock media, voiceover, and captions.
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to research short-form video niches, detect outliers, judge relevance, explore hooks, and generate script briefs through 24 tools.
      1 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables agents to research and analyze public short-form video content on Instagram Reels, TikTok, and YouTube Shorts for trend spotting, creator research, competitive briefs, and content ideation.
      1
      MIT