About

Imported from majiayu000/claude-skill-registry (skills/integration/mcp-setup-ingpoc-skills-3/SKILL.md). Install upstream with npx skills add majiayu000/claude-skill-registry --skill mcp-setup-ingpoc-skills-3. Copyright stays with the author.

MCP Setup

Name: mcp-setup
Author: majiayu000

Configure required MCP servers for agent-harness token efficiency and learning loops.

Required MCP Servers

Server	Purpose	API Key
`token-efficient`	CSV/log processing, sandbox execution (98% token savings)	None
`context-graph`	Semantic decision trace search	Voyage AI

Setup Instructions

Quick setup - Run scripts/setup-all.sh in your project directory:

cd /path/to/your/project
bash ~/.claude/skills/mcp-setup/scripts/setup-all.sh

This will:

Create mcp/ folder in your project
Clone and build token-efficient MCP
Clone and install context-graph MCP
Prompt for Voyage AI API key
Generate .mcp.json in project root

Manual setup (if needed):

1. Install token-efficient MCP in `mcp/`

mkdir -p mcp
git clone https://github.com/gurusharan/token-efficient-mcp.git mcp/token-efficient-mcp
cd mcp/token-efficient-mcp
npm install
npm run build

2. Install context-graph MCP in `mcp/`

git clone https://github.com/gurusharan/agent-harness.git mcp/context-graph-mcp
cd mcp/context-graph-mcp/context-graph-mcp  # or just mcp/context-graph-mcp
pip install -r requirements.txt

3. Create `.mcp.json` in project root

{
  "mcpServers": {
    "token-efficient": {
      "command": "node",
      "args": ["mcp/token-efficient-mcp/dist/index.js"]
    },
    "context-graph": {
      "command": "uv",
      "args": ["--directory", "mcp/context-graph-mcp", "run", "python", "server.py"],
      "env": {
        "VOYAGE_API_KEY": "your_key_here"
      }
    }
  }
}

4. Restart Claude Code

After setup, restart Claude Code to load MCP servers.

Verification

After setup, test:

# Via context-graph MCP
context_store_trace(decision="Test setup", category="general")
context_list_categories()

Troubleshooting

Issue	Solution
`module 'chromadb' not found`	`pip install chromadb`
`VOYAGE_API_KEY not found`	Set env var or add to mcp.json env
Tools not available	Restart Claude Code
`srt: command not found`	Install token-efficient MCP

Scripts

Script	Purpose
`scripts/setup-all.sh`	Use this - Auto-detects paths, sets up both MCP servers
`scripts/verify-setup.sh`	Check if MCP servers are working
`scripts/install-token-efficient.sh`	Standalone token-efficient MCP installer

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/majiayu000-claude-skill-registry-mcp-setup-ingpoc-skills-3/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

majiayu000-claude-skill-registry-mcp-setup-ingpoc-skills-3.ocm.jsonjson

{
  "ocm": "1",
  "id": "majiayu000-claude-skill-registry-mcp-setup-ingpoc-skills-3",
  "kind": "skill",
  "name": "mcp-setup",
  "description": "Use when setting up MCP servers for the first time or verifying MCP configuration. Ensures token-efficient and context-graph MCP servers are properly installed and configured with API keys.",
  "publisher": "majiayu000",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "coding"
    ],
    "tags": [
      "skill-md",
      "mcp",
      "setup",
      "installation",
      "configuration",
      "voyager-ai",
      "token-efficient",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Use when setting up MCP servers for the first time or verifying MCP configuration. Ensures token-efficient and context-graph MCP servers are properly installed and configured with API keys."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/majiayu000/claude-skill-registry",
      "path": "skills/integration/mcp-setup-ingpoc-skills-3/SKILL.md",
      "ref": "a16e8e7bdddc9a7406a56f51e520cef7a8646208",
      "url": "https://github.com/majiayu000/claude-skill-registry/blob/a16e8e7bdddc9a7406a56f51e520cef7a8646208/skills/integration/mcp-setup-ingpoc-skills-3/SKILL.md",
      "key": "majiayu000/claude-skill-registry/skills/integration/mcp-setup-ingpoc-skills-3/SKILL.md"
    }
  },
  "instructions": "# MCP Setup\n\nConfigure required MCP servers for agent-harness token efficiency and learning loops.\n\n## Required MCP Servers\n\n| Server | Purpose | API Key |\n|--------|---------|---------|\n| `token-efficient` | CSV/log processing, sandbox execution (98% token savings) | None |\n| `context-graph` | Semantic decision trace search | Voyage AI |\n\n## Setup Instructions\n\n**Quick setup** - Run `scripts/setup-all.sh` in your project directory:\n\n```bash\ncd /path/to/your/project\nbash ~/.claude/skills/mcp-setup/scripts/setup-all.sh\n```\n\nThis will:\n1. Create `mcp/` folder in your project\n2. Clone and build t",
  "cost": {
    "context_tokens": 614
  }
}

Fetch it by URL: GET /api/v1/registry/majiayu000-claude-skill-registry-mcp-setup-ingpoc-skills-3/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.