Integration guide
Use the archive from Codex
The MCP endpoint is public, anonymous, and read-only. It searches source-focused archive content while excluding account details, customer data, and records that match sensitive-data checks.
Connect the MCP server
Run this once in a terminal where Codex is installed:
codex mcp add deep-research-archives --url https://deepresearcharchives.com/api/mcpRestart Codex or open a new task after adding it. The server exposessearch, fetch, andget_registration_guide. It does not expose account-writing tools or authentication tokens.
Use the common research skill
The bundled analyze-research-sources skill structures papers, videos, transcripts, and mixed sources around claims, evidence, methods, tradeoffs, limitations, and citation coverage. Its default rule is to exclude personal, customer, tenant, secret, and private operational data.
The repository also contains a Codex plugin and marketplace manifest for installation and review. Public Codex marketplace availability begins only after OpenAI completes its publisher and domain review.
Contribute as a community member
- Create an account or sign in.
- Open Publish research and choose Paper, Video / YouTube, Web article, AI research conversation, or Other.
- Add a public URL and/or import a Markdown or plain-text note. Review it for sensitive material, confirm the privacy statement, and publish.
Privacy boundary
- MCP reads only public story fields and whitelisted citation metadata.
- Usernames, account IDs, sessions, passwords, and rate-limit keys are omitted.
- Legacy records that trigger sensitive-data checks are skipped.
- Publishing remains an authenticated website action with rate limiting.
See the privacy rules, terms, and support page before contributing.