Agent skill
oe-mcp-bootstrap
Setup and verification for MCP tooling used in OpenEvent-AI (filesystem, Context7 docs, LSP/Pyright, Playwright). Use when onboarding a new developer/agent or when Codex/Claude cannot access LSP, browser automation, or docs.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/oe-mcp-bootstrap
SKILL.md
oe-mcp-bootstrap
Codex CLI (recommended MCP set)
Add servers (examples; adjust versions as needed):
-
Filesystem:
codex mcp add filesystem --env npm_config_cache=/tmp/codex-npm-cache -- npx -y @modelcontextprotocol/[email protected] .
-
Context7 (docs):
codex mcp add context7 --env npm_config_cache=/tmp/codex-npm-cache -- npx -y @upstash/[email protected] --transport stdio- Ensure
CONTEXT7_API_KEYis set in your shell and allowed byshell_environment_policy.
-
LSP (Pyright via LSP bridge):
- Generate an LSP config JSON that points to your local repo path:
python3 .codex/skills/oe-mcp-bootstrap/scripts/generate_lsp_config.py --out .codex/lsp.json --repo-root .(or the same script under.claude/skills/oe-mcp-bootstrap/)
- Add the server (example uses @axivo/mcp-lsp):
codex mcp add lsp --env npm_config_cache=/tmp/codex-npm-cache --env LSP_FILE_PATH=/abs/path/to/lsp.json -- npx -y @axivo/[email protected]
- Generate an LSP config JSON that points to your local repo path:
-
Playwright (browser automation):
codex mcp add playwright --env npm_config_cache=/tmp/codex-npm-cache -- npx -y @playwright/[email protected]
-
Web search (optional; vetted):
- Kindly web search MCP server (Python). Requires local Chromium plus a search provider (Serper/Tavily/SearXNG). Optional
GITHUB_TOKENimproves GitHub Issues content fetch. Use only after code review and least-privilege keys.
- Kindly web search MCP server (Python). Requires local Chromium plus a search provider (Serper/Tavily/SearXNG). Optional
Verify:
codex mcp list --json
Optional MCPs for maintenance & bug triage
- GitHub MCP (issues/PRs). Use read-only or least-privilege tokens.
- Sentry MCP (prod error triage). Use separate dev/prod tokens.
- Semgrep MCP (security findings).
- Supabase MCP (DB/auth/edge functions). Prefer read-only credentials for debugging.
Optional MCPs for codebase analysis & refactors
- RepoMapper MCP (repo map + prototypes). Requires local clone.
- FileScopeMCP (dependency-based file ranking). Requires local clone + build.
- Renamify MCP (safe multi-file renames).
- fast-filesystem-mcp: do not enable while CVE-2025-67364 is unpatched.
Security guardrails
- Prefer official or well-maintained servers; review third-party code before enabling.
- Reference servers are for dev/test only; do not assume production hardening.
- Avoid broad shell/exec or auto-install/remote-aggregator MCPs.
- Constrain Playwright MCP with allowlist/blocklist settings if available.
Claude Code
Use the equivalent Claude Code MCP configuration for:
- filesystem
- context7
- LSP bridge (Pyright)
- Playwright
- optional web search and triage servers above
Keep secrets out of the repo; use env vars (CONTEXT7_API_KEY, etc.).
Gemini CLI
Use the same MCP set if your Gemini tooling supports MCP. Keep secrets out of the repo.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?