A [Model Context Protocol (MCP)](modelcontextprotocol.io) server built with Deno and TypeScript, designed to provide contextual information related
MCP Terragrunt Docs becomes available to MCP clients through the mcp terragrunt docs mcp server. A Model Context Protocol (MCP) server built with Deno and TypeScript, designed to provide contextual information related to Terragrunt.
A Model Context Protocol (MCP) server built with Deno and TypeScript, designed to provide contextual information related to Terragrunt.
This server acts as an MCP provider, exposing tools and resources that allow AI agents or other MCP clients to query information about Terragrunt documentation and development information, such as GitHub issues.
Once connected, the assistant can call these 5 tools directly:
list-doc-categories — Retrieve all documentation categories from Terragrunt docslist-all-docs-by-category — List all docs in a specific categoryread-document-from-category — Read a specific doc from a categoryread-all-docs-from-category — Retrieve and merge all docs in a category into one responseget-all-open-issues — Retrieve all open issues from Terragrunt GitHub repoSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 3 environment variables: GITHUB_TOKEN, GITHUB_PERSONAL_ACCESS_TOKEN, YOUR_TOKEN. Keep credentials in your client's env block or a secrets manager rather than committing them.
Knowledge and memory servers address the most frustrating trait of language models — walking into every conversation with no recollection of the last one. MCP Terragrunt Docs sits in that group, and the shape of its toolset — list-doc-categories, list-all-docs-by-category, read-document-from-category among others — tells you what it is really for. Worth comparing against the other knowledge memory servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| list-doc-categories | Retrieve all documentation categories from Terragrunt docs. |
| list-all-docs-by-category | List all docs in a specific category. |
| read-document-from-category | Read a specific doc from a category. |
| read-all-docs-from-category | Retrieve and merge all docs in a category into one response. |
| get-all-open-issues | Retrieve all open issues from Terragrunt GitHub repo. |
#### Using Docker
```json
{
"mcpServers": {
"terragrunt_docs": {
"command": "docker",
"args": [
"run",
"-e", "GITHUB_TOKEN=<YOUR_TOKEN>", "mcp-terragrunt-docs"
],
"env": {
"GITHUB_TOKEN": "<YOUR_TOKEN>"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| GITHUB_TOKEN | Credential the server authenticates with. | Yes |
| GITHUB_PERSONAL_ACCESS_TOKEN | Credential the server authenticates with. | Yes |
| YOUR_TOKEN | Credential the server authenticates with. | Yes |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.