tree-sitter-language-pack

Parse and extract code intelligence from 372 programming languages with tree-sitter — structure, imports, symbols, and syntax-aware chunking — using the local ts-pack CLI in your agent.

Install

From the marketplace (recommended)

Pending review for official Claude marketplace.

Self-host:

/plugin marketplace add xberg-io/tree-sitter-language-pack
/plugin install tree-sitter-language-pack@tree-sitter-language-pack

Kimi installation and compatibility

From a checkout of this repository, install with the Python Kimi CLI version used for native plugin validation:

uvx --from kimi-cli==1.51.0 kimi plugin install ./plugin

Native plugin installation was validated with Python Kimi CLI 1.51.0. The replacement @moonshot-ai/kimi-code 2.1.1 does not provide a plugin CLI subcommand; its interactive plugin loading has not been verified. These results do not establish compatibility with newer Kimi releases.

Binary requirement

The bundled MCP launcher (scripts/mcp-launch.sh) resolves a ts-pack binary automatically on first run: it reuses one already on PATH, then tries npx, then Homebrew, then a prebuilt download from the tool's latest GitHub release. No manual install is required to use the MCP server.

To install the ts-pack CLI yourself:

brew install xberg-io/tap/ts-pack
# or run it without a persistent install (the CLI proxy package self-installs the binary):
npx @xberg-io/ts-pack-cli --help
# or download a prebuilt binary from the latest GitHub release:
#   https://github.com/xberg-io/tree-sitter-language-pack/releases/latest
# or install from crates.io (binary is installed as `ts-pack`):
cargo install ts-pack-cli

Parser libraries download on demand the first time a language is used. For offline or CI runs, prefetch them:

ts-pack download --all          # every language
ts-pack download python rust    # specific languages

SDKs (optional)

pip install tree-sitter-language-pack                  # Python
npm install @xberg-io/tree-sitter-language-pack       # Node.js / TypeScript

Rust, Ruby, Go, Java, C#, PHP, Elixir, Dart, Kotlin (Android), Swift, Zig, and WebAssembly bindings are also published.

Skills shipped

MCP server

The plugin auto-registers an MCP server named tree-sitter-language-pack, launched via scripts/mcp-launch.sh (which execs ts-pack mcp). It exposes eight tools for parsing, analysis, and cache management; resources for language discovery; a code-analysis prompt; and language-name completions.

Tools (8):

• parse — syntax tree (s-expression or JSON), auto-detecting language from path or explicit.
• process — code intelligence: structure, imports, exports, symbols, docstrings, comments, diagnostics, chunks. Use all flag for all features.
• detect_language — identify language by path or content (the tool takes path and content only).
• list_languages — available, downloaded, or manifest languages; filter by name.
• info — show language availability and cache status.
• download — prefetch parsers: specific languages, groups, all, or fresh updates.
• cache_dir — return the cache directory path.
• clean_cache — remove all cached parsers.

Resources:

• ts-pack://languages — catalog of all known languages.
• ts-pack://languages/downloaded — currently cached languages.
• ts-pack://language/{name} — per-language metadata template.

Prompt: analyze-code (args: language, optional focus).

Completions: language-name autocomplete.

The launcher auto-installs a binary on first run (override with TS_PACK_LAUNCHER=auto|npx|brew|download). The mcp subcommand ships in a recent release of the tool; an older binary on PATH may need an upgrade to expose it. See the tree-sitter-language-pack-using-the-mcp-server skill for details.

CLI

ts-pack subcommands:

process flags: --structure, --imports, --exports, --comments, --symbols, --docstrings, --diagnostics, --all, --chunk-size <bytes>, --language <name>. With no feature flags it defaults to --structure --imports --exports.

There is no detect or validate subcommand: language detection is implicit in parse/process (from the file extension), and diagnostics come from process --diagnostics. Content-based detection is available in the SDK (detect_language_from_content).

SDK

from tree_sitter_language_pack import process, ProcessConfig

result = process(source_code, ProcessConfig("python", symbols=True, docstrings=True))
for item in result.structure:  # ProcessResult is an object, not a dict
    print(item.kind, item.name, item.span.start_line)

import { process, detectLanguageFromPath } from "@xberg-io/tree-sitter-language-pack";

const lang = detectLanguageFromPath("src/app.ts");
const result = process(source, { language: lang ?? "typescript", structure: true, imports: true });

Configuration

ts-pack init writes a language-pack.toml pinning a cache directory and a language set:

cache_dir = ".ts-pack-cache"
languages = ["python", "rust", "typescript"]

Commit it to pin the parser set across a team or CI. The cache location can also be inspected with ts-pack cache-dir.

Examples

Parse a file into a syntax tree:

ts-pack parse src/main.rs

Extract structure and imports as JSON:

ts-pack process src/app.ts --structure --imports

Chunk a large file for an LLM:

ts-pack process big_module.py --chunk-size 2000

Versioning

The plugin version tracks the tree-sitter-language-pack core release (Cargo.toml). See CHANGELOG.md for release notes.

License

MIT. The upstream tree-sitter-language-pack library is also MIT-licensed.

See also

• Marketplace: this repo — /plugin marketplace add xberg-io/tree-sitter-language-pack
• Upstream: xberg-io/tree-sitter-language-pack

Generated runtime bundles

plugin/.ai-rulez/config.toml loads config.plugins.toml through the plugins layer; skills, commands and runtime adapters are authored alongside it. AI-Rulez 5.3.0 generates all eleven supported runtimes: Claude, Cursor, Codex, Gemini, Kimi, OpenCode, Factory, Hermes, Pi, Agent Plugins and Copilot. Codex ships both manifest layouts; repository-root Claude and Codex marketplace indexes point to the plugin bundle. Cursor also has a marketplace index.

Pi packages skills and prompts without MCP integration. Copilot packages skills and MCP configuration, but does not package slash commands or hooks. Hermes includes a Python package under .hermes/package; OpenCode and Pi share the npm package. The Agent Plugins manifest uses the stable 1.0 specification. Runtime capabilities differ; install the CLI before using skills in a runtime without MCP registration.

Run ai-rulez generate --plugin from the repository root to regenerate and ai-rulez verify --plugin to compare current source output and provenance. The release workflow packages every runtime into a deterministic archive, checksums, and marketplace metadata; npm and PyPI retain their existing publishing jobs.

Hermes runtime setup

Install the product CLI with MCP support and put it on Hermes' PATH before using the plugin. The Hermes adapter registers every bundled skill under the product namespace and provides tree_sitter_language_pack_call, which calls the selected native MCP tool with tool_arguments through a local stdio session. Select tool: "list_tools" first to inspect the server's exact request schemas. Hermes skills are selected explicitly; they are not automatically appended to the system prompt. Enable the plugin in Hermes configuration; project plugins also require HERMES_ENABLE_PROJECT_PLUGINS=true.

The bridge uses the installed CLI directly. The auto-installing launchers used by other MCP clients are not included in the Hermes Python wheel. Provider credentials are inherited from the environment, and are needed for provider-backed requests. Missing CLIs, unavailable tools and model preparation fail with an actionable request error. CLI result data remains untrusted document content.

Public Agent Skills

The repository-root skills/ directory contains the same generated skills and supporting resources as plugin/skills/. Install them independently of a plugin runtime:

npx skills add xberg-io/tree-sitter-language-pack --skill tree-sitter-language-pack

Edit plugin/.ai-rulez/skills, then run task plugin:generate to regenerate runtime bundles and synchronize the public export. task plugin:verify checks both projections; task plugin:skills:test verifies resource freshness, ownership and symlink protection. The public ownership manifest records SHA-256 hashes of every exported file.

Download integrity: the launcher currently relies on HTTPS for direct binary downloads. Verify release checksums separately when available before manually installing an archive.

Launcher and visual assets are authored in plugin/.ai-rulez/scripts/ and plugin/.ai-rulez/assets/; task plugin:generate copies them into the runtime bundle.