mcp-server-design

Estrelas0

Forks0

Atualizado4 de julho de 2026 às 01:04

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.

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

synthet

synthet/image-scoring-backend

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Desenvolvedores de softwareInformática e Matemática·SOC 15-1252

SKILL.md

readonly

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 an MCP server that exposes this project to AI agents (modules/mcp_server.py, mcp-server/)
Adding tools, resources, or prompts
Configuring .cursor/mcp.example.json

Procedure

Read the MCP specification and docs/technical/MCP_SEARCH_DISPATCH.md.
Pick a clear, stable server name and a tool-naming scheme (category.tool for compact dispatch).
Transport: stdio by default (is-be-mcp); optional SSE (is-be-live / WebUI). Pass secrets via environment variables, never CLI args.
Tools — validate every input with a schema (pydantic). Prefer compact search + dispatch over dozens of raw tools when the domain is large.
Separate read from write. Read-only tools are safe-by-default; write/side-effecting tools must require explicit confirmation (confirmed=True and ALLOWED_SIDE_EFFECT_ACTIONS allowlist).
Resources — expose read-only context (status, schema, recent events) — no secrets.
Prompts — ship reusable prompt templates for common workflows where helpful.
On a downstream/dependency failure: return structured diagnostics, do not throw opaque errors.
Test tool handlers with mocked dependencies (no live side effects in unit tests).
Regenerate inventory: python scripts/generate_mcp_tool_inventory.py --update-docs AGENTS.md.

Safety checks

No raw shell / file / network / arbitrary-code tools without an explicit approval policy.
All tool inputs validated against a schema.
Side-effecting tools gated behind confirmation + allowlist; execute_code requires ENABLE_MCP_EXECUTE_CODE=1. See .agent/SAFETY.md.

Done criteria

Tool list matches the published schemas; descriptions are accurate and current.
Secrets only via env; never logged or returned in tool output.
Build produces the server entrypoint referenced by your MCP config.
AGENTS.md inventory regenerated when the tool set changes.

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

Mais deste repositório

mesmo repositório

release-bump

synthet/image-scoring-backend

Bump semver + promote CHANGELOG Unreleased via compiled harness. Use for /release, version bumps, or tagging. Runs scripts/agent_skills/release_bump.py; LLM only when Unreleased is ambiguous. Never commit/push unless the user asks.

2026-07-280

image-scoring-mcp

synthet/image-scoring-backend

Vexlum Scoring MCP — compact search+dispatch on is-be-mcp / is-be-live and gallery is-ui-mcp / is-ui-live.

2026-07-250

agent-cli-hub

synthet/image-scoring-backend

Choose CLI tools and safe patterns before repo work. Install checklist, bounded search/read commands, and confirmation gates. Use when navigating the codebase, running shell commands, or setting up agent tooling on Windows, WSL2, or macOS.

2026-07-250

agent-data-config

synthet/image-scoring-backend

Inspect JSON, YAML, and API responses with jq, yq, dasel, curl, and httpie. Use for package.json, config.json, and backend health checks. Never output secrets or full credential-bearing config.

2026-07-250

agent-dev-tooling

synthet/image-scoring-backend

Backend build, test, lint, and verify workflows via WSL pytest, ruff, doctor, and docker compose. Use before claiming work complete or opening a PR. Do not invent ad hoc Python commands outside documented venvs.

2026-07-250

agent-search

synthet/image-scoring-backend

Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tree, bat, and structural search. Use when finding symbols, files, syntax patterns, or deciding which CLI search to use before reading or editing code.

2026-07-250

MCP server design

Use this skill when

Creating or extending an MCP server that exposes this project to AI agents (modules/mcp_server.py, mcp-server/)

Adding tools, resources, or prompts

Configuring .cursor/mcp.example.json

Procedure

Read the MCP specification and docs/technical/MCP_SEARCH_DISPATCH.md.

Pick a clear, stable server name and a tool-naming scheme (category.tool for compact dispatch).

Transport: stdio by default (is-be-mcp); optional SSE (is-be-live / WebUI). Pass secrets via environment variables, never CLI args.

Tools — validate every input with a schema (pydantic). Prefer compact search + dispatch over dozens of raw tools when the domain is large.

Separate read from write. Read-only tools are safe-by-default; write/side-effecting tools must require explicit confirmation (confirmed=True and ALLOWED_SIDE_EFFECT_ACTIONS allowlist).

Resources — expose read-only context (status, schema, recent events) — no secrets.

Prompts — ship reusable prompt templates for common workflows where helpful.

On a downstream/dependency failure: return structured diagnostics, do not throw opaque errors.

Test tool handlers with mocked dependencies (no live side effects in unit tests).

Regenerate inventory: python scripts/generate_mcp_tool_inventory.py --update-docs AGENTS.md.

Safety checks

No raw shell / file / network / arbitrary-code tools without an explicit approval policy.

All tool inputs validated against a schema.

Side-effecting tools gated behind confirmation + allowlist; execute_code requires ENABLE_MCP_EXECUTE_CODE=1. See .agent/SAFETY.md.

Done criteria

Tool list matches the published schemas; descriptions are accurate and current.

Secrets only via env; never logged or returned in tool output.

Build produces the server entrypoint referenced by your MCP config.

AGENTS.md inventory regenerated when the tool set changes.

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