agentrigs
+ submit rig
~ / rigs / digitarald / mcp-frontend-starter

digitarald/mcp-frontend-starter

No description.

↗ GitHub ★ 20 mit updated 1.6y ago project Copilot
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~6.2k tokens
Heavy · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ claude mcp add Playwright -- npx @executeautomation/playwright-mcp-server
$ claude mcp add Memory -e MEMORY_FILE_PATH=YOUR_MEMORY_FILE_PATH -- npx -y @modelcontextprotocol/server-memory
$ claude mcp add Perplexity -e PERPLEXITY_<redacted> -- docker run -i --rm -e PERPLEXITY_<redacted>

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ claude mcp add Playwright -- npx @executeautomation/playwright-mcp-server
$ claude mcp add Memory -e MEMORY_FILE_PATH=YOUR_MEMORY_FILE_PATH -- npx -y @modelcontextprotocol/server-memory
$ claude mcp add Perplexity -e PERPLEXITY_<redacted> -- docker run -i --rm -e PERPLEXITY_<redacted>

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

MCP servers (3)

serversourceest. tokens
@executeautomation/playwright-mcp-server · "Playwright" npm 2.5k
Memory (knowledge graph) · "Memory"
env: MEMORY_FILE_PATH
 npm 2.6k
Perplexity
env: PERPLEXITY_API_KEY
 docker 1.0k

Similar rigs

HermeticOrmus/claude-code-guide
Complete guide to Claude Code as a system-wide assistant — setup, workflows, advanced patterns
★ 8 project Claude Code 1 mcp 2 skills 5d ago
Pragmatist 3.1k tok ·
cbolden15/claude-code-config-manager
A powerful configuration management tool for Claude Code and Auto-Claude projects. CCM serves as the single source of truth for agent personas, MCP servers, model profiles, and project settings across multiple machines.
★ 1 setup Claude Code 4 mcp 9mo ago
Pragmatist 15.8k tok ·
samjtro/claude
personal claude code config
★ 1 project 4 mcp 1.3y ago
Pragmatist 7.2k tok ·
smartmemory/stratum
State machine dispatch server for AI agent workflows. Typed YAML specs, MCP server (stratum-mcp), and Python library (stratum-py) — postconditions, retries, gates, and auditable execution traces for Claude Code and Codex.
★ 1 project Claude CodeCodex 6 mcp 1 agents 4 hooks today
MCP Hoarder 22.5k tok ·
copied ✓