What environment variables are required?
A valid GitHub token must be set as `GITHUB_TOKEN`, `GH_TOKEN`, or `GITHUB_PERSONAL_ACCESS_TOKEN` for all tools to work.
@Excoriate
基本情報
Deno/TypeScript MCP Server providing context related to Terragrunt documentation.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-terragrunt-docs": {
"command": "deno",
"args": [
"run",
"-A",
"main.ts"
]
}
}
}Retrieve all documentation categories from Terragrunt docs.
List all docs in a specific category.
Read a specific doc from a category.
Retrieve and merge all docs in a category into one response.
Retrieve all open issues from Terragrunt GitHub repo.
A Model Context Protocol (MCP) server built with Deno and TypeScript that exposes tools and resources for AI agents to query Terragrunt documentation and GitHub issues. It provides LLMs and MCP clients with up-to-date information about Terragrunt, helping them generate accurate IaC configurations.
Clone the repository, install Deno, and set a GitHub token as the GITHUB_TOKEN, GH_TOKEN, or GITHUB_PERSONAL_ACCESS_TOKEN environment variable. Run using deno run -A main.ts or via Docker/Podman. For Claude Desktop, add a configuration entry pointing to deno run -A main.ts (or the JSR package or Docker image) with the token in the env block.
A valid GitHub token must be set as `GITHUB_TOKEN`, `GH_TOKEN`, or `GITHUB_PERSONAL_ACCESS_TOKEN` for all tools to work.
Add a configuration entry to `claude_desktop_config.json` using Deno, Docker, or JSR, including the `GITHUB_TOKEN` environment variable.
Yes. Build the image with `docker build -t mcp-terragrunt-docs .` and run it with `docker run -e GITHUB_TOKEN=ghp_xxx... mcp-terragrunt-docs`.
The server provides five tools: `list-doc-categories`, `list-all-docs-by-category`, `read-document-from-category`, `read-all-docs-from-category`, and `get-all-open-issues`.
Yes. All tools require a GitHub token. You can use `GITHUB_TOKEN`, `GH_TOKEN`, or `GITHUB_PERSONAL_ACCESS_TOKEN`.

One permissioned folder your team and your AI agents both log into.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

Model Context Protocol Servers
コメント