chatgpt2md
CLI tool that converts ChatGPT export (ZIP or conversations.json) into organized Markdown files and builds a full-text search index (Tantivy). It also provides an MCP server (stdio transport) with tools for searching and retrieving conversations for Claude Desktop/Claude Code.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Local-first design implies no network exposure; TLS is not applicable to stdio MCP but HTTPS is not part of the threat model. No authentication/scoping described for MCP tools (relies on local process permissions). Secret handling is not discussed; since it processes user exports locally, minimize logging of conversation contents. Dependency/security posture is not verifiable from README alone.
⚡ Reliability
Best When
You have a local ChatGPT data export and want local indexing + Claude integration via MCP without building/hosting your own search service.
Avoid When
You need a centralized hosted service, or you require strong guarantees about dependency security/release stability beyond what is documented in the README.
Use Cases
- • Convert personal ChatGPT history exports into Markdown vaults (e.g., Obsidian).
- • Search across a large ChatGPT export for specific topics/keywords.
- • Let Claude query and read local conversation history via MCP tools.
- • Create a year/month organized archive with message metadata in YAML frontmatter.
Not For
- • Serving shared/multi-tenant chat histories over a network to other users.
- • Use as a hosted SaaS or API (it appears to be local CLI).
- • Strict compliance use-cases that require documented security, audit logs, and data isolation guarantees from a server product.
Interface
Authentication
No user authentication described; MCP server is local (stdio) and relies on local filesystem paths supplied to the server.
Pricing
No pricing information provided; appears to be a local open-source CLI (MIT license per README).
Agent Metadata
Known Gotchas
- ⚠ MCP server expects correct absolute paths (manual setup); relative paths may fail depending on Claude Desktop/Code working directory.
- ⚠ If the index is not built (or built for different chat files), MCP search may return incomplete results.
- ⚠ Large exports may take time to convert and index; agent should wait for completion before connecting.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for chatgpt2md.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.