Communication kit for package discovery

This page is a reusable kit for spreading duckdb-code across both human and agentic audiences. Beyond automated discovery, we maintain a communication package and a list of referencing places for duckdb-code. For the full picture of what you are registering, start from the documentation home.

One-time operator setup

Three one-time actions bring the release and documentation machinery online. They are account-level operator steps, performed once by a maintainer with the right access, not part of a normal pull request:

1. Create the PyPI project and Trusted Publisher. Register the duckdb-code project on PyPI, then add a Trusted Publisher pointing at this repository's deploy-pypi workflow and the pypi environment. OIDC Trusted Publishing means the workflow publishes with no long-lived API token.
2. Enable GitHub Pages with the Actions source. In the repository settings, set Pages to build from GitHub Actions so the deploy-vitepress workflow can publish documentation/.vitepress/dist to the project Pages URL.
3. Cut the first release. Push the first vYYMMDD tag to trigger deploy-pypi and publish the initial version.

Automated discovery

Two discovery conventions can be served from the project itself, so most venues can point at them rather than restate the content:

• AGENTS.md — an agent-facing Markdown file at the repository top level: AGENTS.md, usable jointly by crawling agents and by agentic IDEs. It is the agreed "README for agents" standard that most coding agents now read. See agents.md.

• llms.txt — a curated, Markdown index for LLMs served at the root of the documentation endpoint, when published. The convention, proposed by Jeremy Howard in 2024, is an H1 project name, a one-line blockquote summary, then H2 sections of annotated Markdown links; it curates rather than dumps, and it does not control crawling. See llmstxt.org.

Working a reference

Working on a new reference to duckdb-code consists of the following steps:

1. Scope a suitable registry or reference where it would make sense to list duckdb-code.
2. If this reference is already present in the table below and tagged complete, stop here. Consider another reference target.
3. candidate → on-going. Open a pull request that updates this page, mentioning what you are working on, then do whatever is necessary to register duckdb-code at the referencing site. Read the venue's current submission rules at its link in the table below (they drift), then prepare the submission from the registration package.
4. on-going. The submission is open and awaiting third-party review or merge. Record the pull-request or submission URL here next to the venue.
5. on-going → complete. Complete the pull request: update this page, then ask for a merge. Verify by loading the public listing, not by trusting the merge — confirm the entry resolves and the links in it work.

Keep this page honest: only mark a venue complete once its public listing is live and verified.

The registration package

Copy-paste these fields into any submission form, catalog entry, or pull request that helps referencing duckdb-code.

• Name: duckdb-code
• One-line pitch: A frugal, embeddable code-graph building block for agentic systems — tree-sitter impact analysis and structure explanation over a local DuckDB file, no external service.
• Description: duckdb-code indexes a repository into a single DuckDB file and answers structural questions — impact (the transitive reverse-dependency set of a symbol or file), explain (a symbol's structural neighbourhood), and report (index introspection) — with a local function call. The file bakes into the agent's own container image, so there is no external code-graph service to run. It parses Python and JavaScript/TypeScript with tree-sitter and also indexes Markdown link graphs, and it ships an MCP server (stdio and Streamable HTTP) exposing its query tools.
• Keywords: duckdb, code-graph, tree-sitter, impact-analysis, static-analysis, dependency-graph, agents, mcp, llm, codebase
• Install: pip install duckdb-code
• MCP tools: duckdb-code mcp exposes three query tools — impact(target, …), explain(target, …), and report() — over stdio (same-container subprocess) and Streamable HTTP (--transport http).
• License: MIT
• Links:
  • PyPI: https://pypi.org/project/duckdb-code/
  • Documentation: https://bernard357.github.io/duckdb-code/
  • Repository: https://github.com/bernard357/duckdb-code
  • Agent instructions: AGENTS.md

External references

Each venue is a place where the package can be discovered. Use the candidate → on-going → complete lifecycle. Every candidate requires a manual maintainer or agent action, pending third-party review. Moving to complete requires an accepted review.

Venue	Type	Status
PyPI	Package metadata	candidate
Official MCP registry	MCP server catalog	candidate
Docker MCP Catalog	MCP server catalog	candidate
awesome-mcp-servers	Curated awesome-list	candidate
awesome-static-analysis	Curated awesome-list	candidate

The candidates listed here are only suggestions. Please add any other reference you believe is worth the effort to spread duckdb-code.