mcp-server-design

스타0

포크0

업데이트2026년 7월 4일 16:54

Design and implement an MCP server's tools, resources, and prompts with safe transport and input validation. Use when building or extending a Model Context Protocol server for agent integration.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

출처

synthet

synthet/image-scoring-gallery

GitHub 저장소 열기 Creator 저장소 보기

다운로드

MCP server design

Use this skill when

Creating or extending the gallery MCP server (mcp-server/, is-ui-mcp / is-ui-live)
Adding tools, resources, or prompts to mcp-server/action_registry.json
Configuring .cursor/mcp.example.json

Procedure

Read the MCP specification and backend docs/technical/MCP_SEARCH_DISPATCH.md.
Pick a clear, stable server name and action IDs (local.*, api.*, live.*).
Transport: stdio by default (is-ui-mcp); optional SSE (is-ui-live when Electron dev is running). Pass secrets via environment variables, never CLI args.
Tools — validate every input with a schema (Zod in mcp-server/). Prefer compact search + dispatch over dozens of raw tools.
Separate read from write. Read-only tools are safe-by-default; write/side-effecting tools must require explicit confirmation.
Resources — expose read-only context (gallery status, config) — no secrets.
On a downstream/dependency failure: return structured diagnostics (live_unavailable, api_unreachable), do not throw opaque errors.
Test tool handlers with mocked dependencies (no live side effects in unit tests).
Regenerate registry: cd mcp-server && npm run build:registry.

Safety checks

No raw shell / file / network / arbitrary-code tools without an explicit approval policy.
All tool inputs validated against a schema.
See .agent/SAFETY.md.

Done criteria

Action list matches mcp-server/action_registry.json; descriptions are accurate.
Secrets only via env; never logged or returned in tool output.
npm run build:registry succeeds.

References: MCP docs, backend docs/guides/setup/mcp-compact-servers.md.

이 저장소의 다른 Skills

같은 저장소

changelog-commit-push

synthet/image-scoring-gallery

Update CHANGELOG.md and package.json via compiled release_bump harness, then commit/push only when the user asks. Use for /release, changelog updates, or shipping gallery versions.

2026-07-280

gallery-electron-ts

synthet/image-scoring-gallery

Works in image-scoring-gallery on electron/db.ts contract, IPC, apiService, React/Vite, and alignment with sibling image-scoring-backend schema. Use for desktop app bugs, database.engine modes, API URL/port from webui.lock, or TypeScript changes under electron/ or src/. Triggers include Electron gallery, db.ts, IPC, apiService, config.api, PostgreSQL vs api engine, and Vite renderer.

2026-07-280

gallery-ui

synthet/image-scoring-gallery

React component patterns, CSS Modules styling, design tokens, virtualization, and UX constitution for the Driftara Gallery renderer. Use for src/ UI work, styling, FilterPanel/GalleryGrid/ImageViewer, or design:check—not electron/db unless coordinated with gallery-electron-ts.

2026-07-280

validate-implementation

synthet/image-scoring-gallery

Verify implementation against spec AC-n criteria via compiled harness. Use after /implement or /test-and-fix, before /pr-ready. Parses ACs and emits the report; LLM assigns Verified/Failed/Unknown when evidence is not a clean command exit.

2026-07-280

verification-before-completion

synthet/image-scoring-gallery

Use before claiming work is complete, fixed, passing, ready to commit, or ready for PR. Runs scripts/agent_skills/verification_before_completion.py for the claim→proof catalog; LLM interprets output. Never upgrade incomplete verification.

2026-07-280

image-scoring-mcp

synthet/image-scoring-gallery

Driftara Gallery MCP — is-ui-* router-first; backend triage via sibling is-be-mcp search+dispatch.

2026-07-250

name	mcp-server-design
description	Design and implement an MCP server's tools, resources, and prompts with safe transport and input validation. Use when building or extending a Model Context Protocol server for agent integration.

MCP server design

Use this skill when

Creating or extending the gallery MCP server (mcp-server/, is-ui-mcp / is-ui-live)
Adding tools, resources, or prompts to mcp-server/action_registry.json
Configuring .cursor/mcp.example.json

Procedure

Read the MCP specification and backend docs/technical/MCP_SEARCH_DISPATCH.md.
Pick a clear, stable server name and action IDs (local.*, api.*, live.*).
Transport: stdio by default (is-ui-mcp); optional SSE (is-ui-live when Electron dev is running). Pass secrets via environment variables, never CLI args.
Tools — validate every input with a schema (Zod in mcp-server/). Prefer compact search + dispatch over dozens of raw tools.
Separate read from write. Read-only tools are safe-by-default; write/side-effecting tools must require explicit confirmation.
Resources — expose read-only context (gallery status, config) — no secrets.
On a downstream/dependency failure: return structured diagnostics (live_unavailable, api_unreachable), do not throw opaque errors.
Test tool handlers with mocked dependencies (no live side effects in unit tests).
Regenerate registry: cd mcp-server && npm run build:registry.

Safety checks

No raw shell / file / network / arbitrary-code tools without an explicit approval policy.
All tool inputs validated against a schema.
See .agent/SAFETY.md.

Done criteria

Action list matches mcp-server/action_registry.json; descriptions are accurate.
Secrets only via env; never logged or returned in tool output.
npm run build:registry succeeds.

References: MCP docs, backend docs/guides/setup/mcp-compact-servers.md.