Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问许可证需确认审计异常

agents-mcpAgent MCP 搜索

Agent Skill

agents-mcp 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

1,449

周安装

61

GitHub Stars

60

下载量

508
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:agents-mcp(Agent MCP 搜索)
来源仓库:https://github.com/vasilyu1983/ai-agents-public
仓库路径:skills/agents-mcp
安装命令:
npx skills add https://github.com/vasilyu1983/ai-agents-public --skill agents-mcp
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/vasilyu1983/ai-agents-public --skill agents-mcp

简介

agents-mcp 提供 Model Context Protocol 的决策参考和技术规范说明。

  • 适用于判断何时使用 MCP 服务器或直接调用 API,涵盖数据库、文件系统等领域。
  • 可作为技术选型指南,指导在 GitHub、Notion 等平台集成时的路径选择。
  • 需结合具体网络环境和认证机制评估接入可行性。
  • agents-mcp 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

MCP (Model Context Protocol) — Advisor & Reference

Specification: https://modelcontextprotocol.io/specification/2025-11-25 (November 2025)

When to Use MCP (Decision Tree)

ScenarioUse MCP?Why
Query PostgreSQL/MySQL/SQLiteYesOfficial servers exist, read-only by default
Access filesystem outside workspaceYesScoped allowlists, audit trail
GitHub/Linear/Slack/Notion integrationYesVendor MCP servers available
One-off HTTP API callNoUse WebFetch or Bash curl
Internal API with authMaybeBuild custom MCP server if repeated, otherwise direct call
Need write access to production DBCautionPrefer read-only; if writes needed, scope tightly

Rule of thumb: Use MCP when (1) an official/community server exists, (2) you need audit/permission control, or (3) you'll reuse the integration across sessions.

Quick Start (Local stdio via npx)

  1. Create or edit .claude/.mcp.json:
{
  "mcpServers": {
    "postgres": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-postgres"],
      "env": { "POSTGRES_URL": "${DATABASE_URL}" }
    }
  }
}
  1. Validate the connection:
export DATABASE_URL="postgresql://user:pass@localhost:5432/db"
claude mcp list
claude mcp get postgres

Common Tasks

Add a database connection

# PostgreSQL
claude mcp add postgres --env POSTGRES_URL=postgresql://user:pass@host:5432/db -- npx -y @modelcontextprotocol/server-postgres

# SQLite (local file)
claude mcp add sqlite -- npx -y @modelcontextprotocol/server-sqlite ./data/app.db

Add GitHub integration

claude mcp add github --env GITHUB_TOKEN=ghp_xxx -- npx -y @modelcontextprotocol/server-github

Add filesystem access (scoped)

# Read-only access to ./docs
claude mcp add docs-readonly --deny "mcp__filesystem__write_file" -- npx -y @modelcontextprotocol/server-filesystem ./docs

Add remote server (HTTP transport)

claude mcp add --transport http notion https://mcp.notion.com/mcp

Add PostHog MCP (EU/US + Codex fallback)

Use the region-matching PostHog MCP host:

  • EU workspaces: https://mcp-eu.posthog.com/mcp
  • US workspaces: https://mcp.posthog.com/mcp
# Codex streamable HTTP (default)
codex mcp add posthog --url https://mcp-eu.posthog.com/mcp
codex mcp login posthog

# If Codex fails at initialize with HTTP 500, use SSE bridge fallback
codex mcp remove posthog
codex mcp add posthog -- npx -y mcp-remote@latest https://mcp-eu.posthog.com/sse

The SSE bridge keeps PostHog available in Codex when streamable_http handshakes fail.

Permission Management

# Allow all tools from a server (wildcard)
claude mcp add --allow "mcp__postgres__*" postgres -- npx -y @modelcontextprotocol/server-postgres

# Allow specific tools only
claude mcp add --allow "mcp__postgres__query,mcp__postgres__list_tables" postgres -- npx -y @modelcontextprotocol/server-postgres

# Deny a specific tool
claude mcp add --deny "mcp__filesystem__write_file" filesystem -- npx -y @modelcontextprotocol/server-filesystem ./data

Build vs Use Decision

NeedRecommendation
Database query (PG/MySQL/SQLite)Use official server
GitHub/Linear/Slack/NotionUse vendor server
Custom internal APIBuild custom server (TypeScript recommended)
One-time data fetchDon't use MCP; use WebFetch
Browser automationUse Puppeteer MCP server

Build Custom MCP Server (Quick Start)

When no existing server fits your needs, build a custom one:

mkdir my-mcp-server && cd my-mcp-server
npm init -y
npm install @modelcontextprotocol/sdk

Minimal TypeScript server (src/index.ts):

import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { CallToolRequestSchema, ListToolsRequestSchema } from "@modelcontextprotocol/sdk/types.js";

const server = new Server(
  { name: "my-server", version: "1.0.0" },
  { capabilities: { tools: {} } }
);

// Define tools
server.setRequestHandler(ListToolsRequestSchema, async () => ({
  tools: [{
    name: "my_tool",
    description: "What this tool does",
    inputSchema: {
      type: "object",
      properties: { query: { type: "string" } },
      required: ["query"]
    }
  }]
}));

// Handle tool calls
server.setRequestHandler(CallToolRequestSchema, async (request) => {
  if (request.params.name === "my_tool") {
    const result = await doWork(request.params.arguments);
    return { content: [{ type: "text", text: JSON.stringify(result) }] };
  }
  throw new Error(`Unknown tool: ${request.params.name}`);
});

const transport = new StdioServerTransport();
await server.connect(transport);

Register in .claude/.mcp.json:

{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["tsx", "./my-mcp-server/src/index.ts"],
      "env": { "API_KEY": "${MY_API_KEY}" }
    }
  }
}

Full guide: references/mcp-custom.md (TypeScript + Python, resources, prompts, testing, deployment)

Production Guardrails (Required)

  • Assume tool outputs are untrusted (prompt injection). Sanitize/structure before reuse.
  • Default to least privilege: read-only DB, scoped filesystem allowlists, minimal tool allowlists.
  • Keep secrets out of .mcp.json; inject via env vars or a secret manager at runtime.
  • Add timeouts, retries, and rate limits; log all tool invocations for audit.

Troubleshooting

IssueSolution
"Server not found"Check claude mcp list; verify package installed
"Permission denied"Add --allow for specific tools
"Connection refused"Verify env vars, check network access
"500 Internal Server Error" on initialize (streamable HTTP)For PostHog in Codex, switch to SSE bridge: npx -y mcp-remote@latest https://mcp-eu.posthog.com/sse
Slow responsesCheck server logs, add timeout config
"Tool output too large"Use pagination or limit queries

What To Read Next

TaskResource
Choose an existing serverreferences/mcp-servers.md
Build a custom serverreferences/mcp-custom.md
Implementation patterns (DB/API/filesystem)references/mcp-patterns.md
Security hardening (OAuth, scopes, injection defense)references/mcp-security.md
Templatesassets/database/, assets/filesystem/, assets/api/, assets/deployment/
Curated linksdata/sources.json

Related Skills

SkillPurpose
agents-subagentsCreating agents that use MCP tools
agents-hooksAutomating MCP server startup/validation
ops-devops-platformDeploying MCP servers in CI/CD

Operational Reliability Addendum (Feb 2026)

MCP Health Gate (Run Before Data Work)

For each MCP server used in a task, run:

  1. Presence: codex mcp list
  2. Auth state: codex mcp get <server> or equivalent
  3. Minimal smoke test: one low-cost read/list call

Only proceed to analysis/query work after all 3 pass.

Transport/Auth Fallback Playbook

If login/initialize fails:

  1. verify endpoint region (EU vs US),
  2. verify transport support (streamable HTTP vs SSE bridge),
  3. retry with documented fallback transport,
  4. re-run health gate.

MCP Incident Note Template

When MCP setup fails, report in one block:

  • server name,
  • endpoint/transport used,
  • exact failure message,
  • next fallback attempted,
  • final status.

Auth Error Escalation (1-Retry Max)

When an MCP tool call fails with an auth/token error:

  1. Retry once after re-authenticating (codex mcp login <server> or equivalent).
  2. If the retry also fails, stop immediately and notify the user with:

- server name, - exact error message, - what was attempted.

  1. Do not loop retries — auth failures that survive one re-auth are environment/config issues that require human intervention.

Unbounded auth retry loops waste context window and block productive work.

Reuse Rule

Cache working MCP connection settings per session and avoid repeated re-login/reconfigure unless health gate fails.

Fact-Checking

  • Use web search/web fetch to verify current external facts, versions, pricing, deadlines, regulations, or platform behavior before final answers.
  • Prefer primary sources; report source links and dates for volatile information.
  • If web access is unavailable, state the limitation and mark guidance as unverified.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.24%
按下载量换算184

Claude

30.34%
按下载量换算154

Cursor

17.59%
按下载量换算89

Gemini CLI

9.5%
按下载量换算48

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills