Content Interviewer MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Content Interviewer MCP Interview me about my morning routine and turn my insights into 3 Reel script ideas."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 .venvActivate it:
source .venv/bin/activateInstall the project and its development dependencies:
python -m pip install -e ".[dev]"Development checks
Run the tests:
python -m pytestRun linting:
python -m ruff check .Check that the source compiles:
python -m compileall -q srcArchitecture
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 toolsadd_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
Scored across 10 tools
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.
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.
Ten tools is well within the ideal range for a specialized content workflow. Each tool covers a meaningful operation without redundancy or bloat.
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
Related MCP Connectors
Discover and research viral social content on TikTok, Instagram Reels, and YouTube Shorts.
Evidence-backed video and Reel ideas for a YouTube channel or confirmed public Instagram account.
Run interviews with real customers and retrieve evidence-backed product findings.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables 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.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables local research of public Instagram Reels through a dashboard, CLI, and 22 MCP tools, with optional Codex or Claude Code analysis.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to research short-form video niches, detect outliers, judge relevance, explore hooks, and generate script briefs through 24 tools.1 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables 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.1MIT