taru-mcp 0.1.3 → 0.1.5

package/README.md

@@ -4,55 +4,88 @@ MCP server for [taru](https://taru.arupa.io) — connect Claude Code or Codex to
 
 Zero dependencies. Pure Node.js. Works with any MCP client.
 
-## Install
+## Quick Setup
 
-### Claude Code
+### macOS / Linux
 
 ```bash
-# 1. Install the package
-npm install taru-mcp
+curl -fsSL https://raw.githubusercontent.com/arupa-inc/taru-mcp/main/setup.sh | bash
+```
 
-# 2. Register MCP server
-claude mcp add taru -- npx taru-mcp --token xxv_your_token
+### Windows (PowerShell)
 
-# 3. Copy agent instructions to your project
-cp node_modules/taru-mcp/samples/CLAUDE.md ./CLAUDE.md
+```powershell
+irm https://raw.githubusercontent.com/arupa-inc/taru-mcp/main/setup.ps1 | iex
 ```
 
-### Codex (OpenAI)
+The script will ask you:
+1. **Project folder name** — creates the workspace directory
+2. **AI client** — Claude Code, Codex, or both
+3. **Workspace token** — taru workspace token (`xxv_...`). Can be entered later if you don't have it yet.
+
+It handles `npm init`, `taru-mcp` installation, agent file (`CLAUDE.md` / `AGENTS.md`) setup, and MCP registration automatically.
+
+Get your workspace token from the taru web console: **Settings > API Key**.
+
+## Manual Setup
+
+If the setup script doesn't work, follow these steps:
+
+### 1. Install
 
 ```bash
-# 1. Install the package
+mkdir my-project && cd my-project
+npm init -y
 npm install taru-mcp
+```
 
-# 2. Register MCP server
-codex mcp add taru -- npx taru-mcp --token xxv_your_token
+### 2. Copy agent instructions
 
-# 3. Copy agent instructions to your project
+```bash
+# For Claude Code
+cp node_modules/taru-mcp/samples/CLAUDE.md ./CLAUDE.md
+
+# For Codex
 cp node_modules/taru-mcp/samples/AGENTS.md ./AGENTS.md
 ```
 
-### Agent instructions
-
-The `samples/` directory contains ready-to-use instruction files:
+### 3. Register MCP server
 
-| File | For | Description |
-|------|-----|-------------|
-| `samples/CLAUDE.md` | Claude Code | Drop into your project root |
-| `samples/AGENTS.md` | Codex | Drop into your project root |
+```bash
+# Claude Code
+claude mcp add taru -- npx taru-mcp --url https://taru-api.arupa.io --token xxv_your_token
 
-These files teach the AI how to use taru tools, classify documents vs opinions, handle conflicts, and set confidence scores. **Copy the appropriate file to your project root** after installing.
+# Codex
+codex mcp add taru -- npx taru-mcp --url https://taru-api.arupa.io --token xxv_your_token
+```
 
-> **No package.json?** You can also copy the CLAUDE.md / AGENTS.md content directly from the [setup guide](https://taru.arupa.io/docs/setup).
+### 4. Or configure MCP manually
 
-## Options
+If `claude mcp add` doesn't work, create `.mcp.json` in your project root:
 
-| Flag | Env | Default | Description |
-|------|-----|---------|-------------|
-| `--workspace-id`, `-w` | `TARU_WORKSPACE_ID` | `00000000-...0001` | Workspace UUID |
-| `--token`, `-t` | `TARU_API_TOKEN` | — | API token (`xxv_...`) |
+```json
+{
+  "mcpServers": {
+    "taru": {
+      "command": "npx",
+      "args": ["taru-mcp", "--url", "https://taru-api.arupa.io", "--token", "xxv_your_token"]
+    }
+  }
+}
+```
 
-Get your API token from the taru web console: **Workspaces → Members → API Key**.
+For Claude Code global config (`~/.claude.json`):
+
+```json
+{
+  "mcpServers": {
+    "taru": {
+      "command": "npx",
+      "args": ["taru-mcp", "--url", "https://taru-api.arupa.io", "--token", "xxv_your_token"]
+    }
+  }
+}
+```
 
 ## Tools
 
@@ -65,8 +98,6 @@ Once connected, these MCP tools are available to the AI:
 | `store_document` | Store a document or opinion with auto-conflict detection |
 | `list_documents` | List all documents in the workspace |
 | `list_conflicts` | View pending knowledge conflicts |
-| `web_search` | Search the web via DuckDuckGo |
-| `web_fetch` | Fetch and extract text from a URL |
 | `rebalance` | Merge similar keywords, clean up orphan nodes |
 
 ## How it works

package/bin/taru-mcp.mjs

@@ -39,7 +39,9 @@ Examples:
 }
 
 url = url.replace(/\/+$/, "");
-const endpoint = `${url}/mcp/${workspaceId}`;
+// If workspace ID was explicitly provided, use the scoped endpoint; otherwise use token-based auto endpoint
+const hasExplicitWorkspace = args.some(a => a === "--workspace-id" || a === "-w") || env.TARU_WORKSPACE_ID;
+const endpoint = hasExplicitWorkspace ? `${url}/mcp/${workspaceId}` : `${url}/mcp`;
 const isHttps = endpoint.startsWith("https://");
 
 stderr.write(`[taru-mcp] endpoint: ${endpoint}\n`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "taru-mcp",
-  "version": "0.1.3",
+  "version": "0.1.5",
   "description": "MCP server for taru knowledge graph — connect Claude Code or Codex to your team's shared brain",
   "bin": {
     "taru-mcp": "./bin/taru-mcp.mjs"
@@ -9,6 +9,7 @@
   "files": [
     "bin/",
     "samples/",
+    "setup.sh",
     "README.md"
   ],
   "keywords": [
@@ -21,7 +22,7 @@
   ],
   "repository": {
     "type": "git",
-    "url": "https://github.com/carl/taru-mcp"
+    "url": "https://github.com/arupa-inc/taru-mcp"
   },
   "license": "MIT",
   "engines": {

package/samples/AGENTS.md

@@ -9,8 +9,6 @@ You have access to the taru MCP server — a research knowledge graph with tempo
 - store_document: Store extracted knowledge (handles embedding + graph)
 - list_documents: List all documents with status and confidence
 - list_conflicts: View pending knowledge conflicts
-- web_search: Search the web (DuckDuckGo)
-- web_fetch: Fetch text content from a URL
 - rebalance: Clean up the knowledge graph (merge keywords, remove orphans)
 
 ### Rules

package/samples/CLAUDE.md

@@ -9,8 +9,6 @@ You have access to the taru MCP server — a research knowledge graph with tempo
 - store_document: Store extracted knowledge (handles embedding + graph)
 - list_documents: List all documents with status and confidence
 - list_conflicts: View pending knowledge conflicts
-- web_search: Search the web (DuckDuckGo)
-- web_fetch: Fetch text content from a URL
 - rebalance: Clean up the knowledge graph (merge keywords, remove orphans)
 
 ### Rules

package/setup.sh

@@ -0,0 +1,120 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# taru MCP setup script
+# Usage:
+#   curl -fsSL https://raw.githubusercontent.com/arupa-inc/taru-mcp/main/setup.sh | bash
+
+URL="https://taru-api.arupa.io"
+
+echo ""
+echo "  🌳 taru MCP Setup"
+echo ""
+
+# 1. Ask project folder name
+read -rp "Project folder name: " FOLDER </dev/tty
+if [ -z "$FOLDER" ]; then
+  echo "Error: folder name is required"
+  exit 1
+fi
+
+if [ -d "$FOLDER" ]; then
+  echo "==> Directory '$FOLDER' already exists, using it."
+else
+  mkdir -p "$FOLDER"
+  echo "==> Created '$FOLDER'"
+fi
+cd "$FOLDER"
+
+# 2. Ask client type
+echo ""
+echo "Which AI client do you use?"
+echo "  1) Claude Code"
+echo "  2) Codex"
+echo "  3) Not sure (copies both CLAUDE.md and AGENTS.md)"
+echo ""
+read -rp "Choose [1/2/3]: " CLIENT_CHOICE </dev/tty
+
+case "$CLIENT_CHOICE" in
+  1) CLIENT="claude" ;;
+  2) CLIENT="codex" ;;
+  *) CLIENT="both" ;;
+esac
+
+# 3. Ask token (skippable)
+echo ""
+read -rp "Workspace token (xxv_..., press Enter to add later): " TOKEN </dev/tty
+
+# Check npm
+if ! command -v npm &>/dev/null; then
+  echo "Error: 'npm' not found. Install Node.js first."
+  exit 1
+fi
+
+# Init & install
+if [ ! -f "package.json" ]; then
+  echo "==> Initializing package.json..."
+  npm init -y --silent > /dev/null 2>&1
+fi
+
+echo "==> Installing taru-mcp..."
+npm install taru-mcp --silent
+
+# Copy agent files
+copy_agent_file() {
+  local file="$1"
+  if [ -f "$file" ]; then
+    echo "==> $file already exists, appending taru instructions..."
+    echo "" >> "$file"
+    cat "node_modules/taru-mcp/samples/$file" >> "$file"
+  else
+    cp "node_modules/taru-mcp/samples/$file" "./$file"
+    echo "==> Created $file"
+  fi
+}
+
+if [ "$CLIENT" = "claude" ]; then
+  copy_agent_file "CLAUDE.md"
+elif [ "$CLIENT" = "codex" ]; then
+  copy_agent_file "AGENTS.md"
+else
+  copy_agent_file "CLAUDE.md"
+  copy_agent_file "AGENTS.md"
+fi
+
+# Register MCP server
+register_mcp() {
+  local cli="$1"
+  local token_args=""
+  if [ -n "$TOKEN" ]; then
+    token_args=" --token $TOKEN"
+  fi
+
+  if command -v "$cli" &>/dev/null; then
+    echo "==> Registering MCP server with $cli..."
+    $cli mcp add taru -- npx taru-mcp --url "$URL"$token_args
+  else
+    echo "==> '$cli' not found, skipping MCP registration."
+    echo "    Run this later: $cli mcp add taru -- npx taru-mcp --url $URL$token_args"
+  fi
+}
+
+if [ "$CLIENT" = "claude" ]; then
+  register_mcp "claude"
+elif [ "$CLIENT" = "codex" ]; then
+  register_mcp "codex"
+else
+  register_mcp "claude"
+  register_mcp "codex"
+fi
+
+echo ""
+echo "  ✅ Setup complete!"
+echo ""
+echo "  Project: $(pwd)"
+[ "$CLIENT" = "claude" ] || [ "$CLIENT" = "both" ] && echo "  Agent file: ./CLAUDE.md"
+[ "$CLIENT" = "codex" ] || [ "$CLIENT" = "both" ] && echo "  Agent file: ./AGENTS.md"
+[ -n "$TOKEN" ] && echo "  Token: configured" || echo "  Token: not set yet (add via settings)"
+echo ""
+echo "  Open this folder in your AI client to start growing the tree."
+echo ""