The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the 6DuckLearn MCP listing page.
Official public setup docs, registry metadata, and local connector package for 6DuckLearn integrations.
This repository contains two separate integrations: Hosted MCP lets Codex use 6DuckLearn tools; the AI Runtime Connector lets Agent Console send work to Codex, Hermes, or OpenClaw.
Use 6ducklearn as the local client key in Codex or Claude Code. The official MCP Registry name is com.6ducklearn/mcp, and the hosted endpoint is:
This repository is intentionally hosted-first. It does not contain the private 6DuckLearn SaaS backend, Supabase edge functions, service-role database access, billing logic, user memory store, or production deployment scripts.
From GitHub:
This configures the hosted 6DuckLearn MCP server in local Codex, adds the hosted OAuth compatibility header, and starts the OAuth login flow.
If a matching, authenticated 6ducklearn hosted entry already exists, the setup command keeps it in place and does not reopen OAuth. A different local or stdio entry is replaced, while a matching but signed-out entry resumes OAuth, so repeated setup stays deterministic without creating duplicates.
Manual fallback:
Do not use codex mcp add for this fallback: current Codex versions can start OAuth immediately from that command, before explicit scopes are supplied. Inspect the entry first with codex mcp get 6ducklearn --json:
~/.codex/config.toml.http_headers table.codex mcp remove 6ducklearn, then add the full block.Start only the explicitly scoped login:
Then open the MCP tool picker in Claude Code and authorize 6DuckLearn when prompted.
The npm packages @6ducklearn/mcp and @6ducklearn/connector are not published yet. Until npm publication is available, use the GitHub npx command above for copy/paste setup.
6ducklearncom.6ducklearn/mcp6DuckLearn MCPhttps://6ducklearn.com/mcphttps://6ducklearn.com/.well-known/oauth-authorization-serverhttps://6ducklearn.com/.well-known/oauth-protected-resource/mcpThe public Codex helper requests only mcp:read, mcp:write, and approval:request. Control-plane access and local-runtime authorization use separate, explicitly named flows; the hosted-MCP setup never requests approval:decide. A protected write is submitted to 6DuckLearn Inbox with a server-issued approval ID. The human decides there, then Codex calls resume_approved_write with only that ID to execute the locked request once.
6DuckLearn MCP gives connected agents account-authorized workflows for research, organization, reminders, portfolio review, knowledge retrieval, canvas creation, and Skill Builder discovery. Finance research includes bounded stock-research bundles and issuer-grounded Hong Kong credit-card evaluation when those capabilities are enabled for the connected account.
For the full public catalog, see MCP tool use cases. The catalog describes each tool by practical use case and example prompt without exposing private schemas or backend implementation details.
Finance-related capabilities are for research, organization, summaries, alerts, and user-authorized workflows. 6DuckLearn MCP is not an order-routing service or source of investment recommendations.
Ask for a stock bundle when you want the available value, timing, event, risk, saved-research, and portfolio inputs in one read-only response:
For Hong Kong credit cards, separate evidence lookup from evaluation:
query_credit_card_catalog never ranks cards. recommend_credit_cards evaluates only the currently published, source-linked catalog and may return a limited, stale, or insufficient-data status instead of a winner. Missing normalized fields remain disclosures; they are not permission to invent reward rates, eligibility, fees, or ranking evidence.
The connector is for users who want a local runtime bridge between 6DuckLearn and AI runtimes such as Codex, OpenClaw, or Hermes. The preferred setup path is OAuth from the 6DuckLearn web app.
After login, keep the connector process running when using a local runtime:
Most users should start from the hosted 6DuckLearn setup page rather than cloning this repository directly.
The official registry manifest lives in server.json. It is a hosted-only listing because the canonical 6DuckLearn MCP server runs at https://6ducklearn.com/mcp; the local connector is a runtime bridge, not a standalone stdio MCP server package.
Before publishing, validate the manifest and hosted endpoint:
Publish with domain-based authentication so the registry name can stay under the 6DuckLearn domain namespace:
The required HTTP proof must be served from https://6ducklearn.com/.well-known/mcp-registry-auth. After the official MCP Registry lists com.6ducklearn/mcp, request GitHub MCP Registry inclusion by emailing partnerships@github.com with the registry name, official registry URL, GitHub repository, website, hosted endpoint, and validation evidence. GitHub's MCP Registry is a separate curated surface, so listing there currently requires GitHub review rather than relying on automatic community registry sync.
Validation runs TypeScript build, connector tests, package dry-run, MCP Registry manifest checks, hosted MCP smoke checks, and a public-release secret scan.
Report security issues privately. See SECURITY.md.
Code is licensed under Apache-2.0. Documentation examples are licensed under CC BY 4.0. See TRADEMARK.md for 6DuckLearn brand usage.