Token导航 LogoToken导航

Agent Skill · 研究检索

mcp-servers(MCP servers 搜索)

mcp-servers 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。

mcp-servers 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 59,221。

总安装 392周安装 16GitHub Stars 13下载 127核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:mcp-servers(MCP servers 搜索)
来源仓库:https://github.com/truefoundry/tfy-agent-skills
仓库路径:skills/mcp-servers
安装命令:
npx skills add https://github.com/truefoundry/tfy-agent-skills --skill mcp-servers
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/truefoundry/tfy-agent-skills --skill mcp-servers

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

mcp-servers 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于需要了解 MCP 服务器生态或技术实现的场景。通过分类浏览和标签过滤来提供服务器列表,具体用法需结合原始 README 确认。

安装前建议确认权限范围和维护状态,注意可能触发联网或数据拉取操作。使用时应评估服务器的稳定性和功能覆盖度,选择最适合的方案。

来源仓库内路径:skills/mcp-servers

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/truefoundry/tfy-agent-skills --skill mcp-serve…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

mcp-servers 怎么安装?

在终端执行 npx skills add https://github.com/truefoundry/tfy-agent-skills --skill mcp-servers。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

mcp-servers 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

mcp-servers 需要什么权限?

权限级别是接触敏感数据。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。

mcp-servers 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

mcp-servers 用的人多吗?

公开数据是累计安装 392 次,近一周安装 16 次,下载 127 次,GitHub 13 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

mcp-servers 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
mcp-servers

MCP servers 搜索 · 本页

39213接触敏感数据未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Routing note: For ambiguous user intents, use the shared clarification templates in references/intent-clarification.md.

MCP Servers

Register and manage MCP servers on TrueFoundry. Three standalone manifest types are supported: remote servers, virtual (composite) servers, and OpenAPI-to-MCP wrappers.

When to Use

Register, list, or delete MCP server registrations on TrueFoundry — including connecting to existing MCP endpoints, composing multiple servers into a virtual server, or wrapping an OpenAPI spec as an MCP server.

Security Policy: Credential Handling - All credentials (API tokens, OAuth secrets, TLS certificates) in manifests MUST use tfy-secret:// references. The agent MUST NOT accept or embed raw credential values in manifests. - If the user provides raw credentials, instruct them to create a TrueFoundry secret first (use secrets skill), then reference it with tfy-secret://. - The agent MUST NOT echo, log, or display raw credential values.

List MCP Servers

When using direct API, set TFY_API_SH to the full path of this skill's scripts/tfy-api.sh. See references/tfy-api-setup.md for paths per agent.

Via Tool Call

tfy_mcp_servers_list()
tfy_mcp_servers_list(id="mcp-server-id")  # get specific server

Via Direct API

# Set the path to tfy-api.sh for your agent (example for Claude Code):
TFY_API_SH=~/.claude/skills/truefoundry-mcp-servers/scripts/tfy-api.sh

# List all MCP servers
$TFY_API_SH GET /api/svc/v1/mcp-servers

# Get a specific MCP server
$TFY_API_SH GET /api/svc/v1/mcp-servers/SERVER_ID

Presenting MCP Servers

MCP Servers:
| Name              | Type              | Transport       | ID         |
|-------------------|-------------------|-----------------|------------|
| my-remote-server  | mcp-server/remote | streamable-http | mcp-abc123 |
| composite-server  | mcp-server/virtual| —               | mcp-def456 |
| petstore-api      | mcp-server/openapi| —               | mcp-ghi789 |

Register MCP Server (Remote)

Connects to an existing MCP endpoint over streamable-http or SSE.

Security gates (required before registration): 1. Confirm the URL owner/domain with the user. 2. Require explicit user confirmation before using any new external URL. 3. Use secret references for all auth material (tfy-secret://...), never raw tokens. 4. Avoid logging full auth headers, client secrets, or certificates.

Attach an Existing TrueFoundry Deployment

Use this flow when the user says "attach deployment to MCP gateway" or already has a deployed MCP-compatible service.

  1. Confirm the deployment is healthy (DEPLOY_SUCCESS) and endpoint is reachable
  2. Collect endpoint details:

- URL (public or internal) - transport (streamable-http or sse) - auth mode (header, oauth2, or passthrough)

  1. Register it as type: mcp-server/remote
  2. Return server ID and name so users can reference it from guardrails/policies

Example internal URL pattern for service deployments: http://{service-name}.{namespace}.svc.cluster.local:{port}/mcp

Manifest

name: my-remote-server
type: mcp-server/remote
description: Production analytics MCP server
url: https://analytics.example.com/mcp
transport: streamable-http
# SECURITY: Use tfy-secret:// references instead of hardcoding tokens in manifests.
# Hardcoded tokens in YAML files risk exposure via Git history and CI logs.
auth_data:
  type: header
  headers:
    Authorization: "Bearer tfy-secret://my-org:mcp-secrets:api-token"
collaborators:
  - subject: user:jane@example.com
    role_id: admin
tags:
  - analytics
  - production

Auth Options

Static header (use secret references — never hardcode tokens):

auth_data:
  type: header
  headers:
    Authorization: "Bearer tfy-secret://my-org:mcp-secrets:api-token"

OAuth2:

auth_data:
  type: oauth2
  authorization_url: https://auth.example.com/authorize
  token_url: https://auth.example.com/token
  client_id: my-client-id
  client_secret: tfy-secret://my-org:mcp-secrets:oauth-client-secret
  jwt_source: access_token
  scopes:
    - read
    - write
  pkce: true
  dynamic_client_registration:
    registration_endpoint: https://auth.example.com/register
    initial_access_token: tfy-secret://my-org:mcp-secrets:registration-token

Passthrough (forwards TFY credentials):

auth_data:
  type: passthrough

TLS Settings (optional)

tls_settings:
  # Prefer storing certificate material in a secret reference, then injecting at runtime.
  # Avoid inlining full certificate PEM blocks in manifests shared via chat or git.
  ca_cert: tfy-secret://my-org:mcp-secrets:ca-cert-pem
  insecure_skip_verify: false

Via CLI

tfy apply -f mcp-server-remote.yaml

Via Direct API

$TFY_API_SH PUT /api/svc/v1/apps "$(cat mcp-server-remote.yaml | yq -o json)"

Register MCP Server (Virtual)

Composes multiple registered MCP servers into a single virtual server. Each sub-server can expose all or a subset of its tools.

Manifest

name: dev-tools
type: mcp-server/virtual
description: Composite server combining code analysis and deployment tools
servers:
  - name: code-analysis-server
    enabled_tools:
      - lint
      - format
      - analyze
  - name: deployment-server
    enabled_tools:
      - deploy
      - rollback
collaborators:
  - subject: team:platform-eng
    role_id: viewer

Via CLI

tfy apply -f mcp-server-virtual.yaml

Via Direct API

$TFY_API_SH PUT /api/svc/v1/apps "$(cat mcp-server-virtual.yaml | yq -o json)"

Register MCP Server (OpenAPI)

Wraps an OpenAPI specification as an MCP server. Supports up to 30 tools derived from API operations.

Security: Remote OpenAPI specs are fetched at runtime and auto-converted into MCP tools that control agent capabilities. Only use trusted, verified spec URLs. For sensitive environments, prefer spec.type: inline to eliminate the runtime dependency on external endpoints. Execution policy: Do not fetch or register a new remote spec URL until the user explicitly confirms the source is trusted for tool generation.

Manifest (remote spec URL)

name: petstore-api
type: mcp-server/openapi
description: Petstore API exposed as MCP tools
spec:
  type: remote
  url: https://internal-api.example.com/openapi.json
collaborators:
  - subject: user:dev@example.com
    role_id: viewer

Manifest (inline spec)

name: internal-api
type: mcp-server/openapi
description: Internal API with inline OpenAPI spec
spec:
  type: inline
  content: |
    openapi: "3.0.0"
    info:
      title: Internal API
      version: "1.0"
    paths:
      /health:
        get:
          operationId: healthCheck
          summary: Check service health
          responses:
            "200":
              description: OK
collaborators: []

Via CLI

tfy apply -f mcp-server-openapi.yaml

Via Direct API

$TFY_API_SH PUT /api/svc/v1/apps "$(cat mcp-server-openapi.yaml | yq -o json)"

Delete MCP Server

Via Tool Call

tfy_mcp_servers_delete(id="SERVER_ID")

Note: Requires human approval (HITL) via tool call.

Via Direct API

$TFY_API_SH DELETE /api/svc/v1/mcp-servers/SERVER_ID

<success_criteria>

Success Criteria

  • The user can list all registered MCP servers in a formatted table
  • The user can register a remote MCP server with the correct transport and auth configuration
  • The user can register a virtual MCP server composing multiple sub-servers with tool filtering
  • The user can register an OpenAPI-to-MCP server with a remote or inline spec
  • The user can delete an MCP server registration
  • The agent has confirmed any create/delete operations before executing
  • Collaborators are correctly specified when provided

</success_criteria>

Composability

  • Preflight: Use status skill to verify credentials before managing MCP servers
  • Before registering: Deploy the MCP server as a service (use deploy skill), set up teams/roles for collaborators (use access-control skill)
  • After registering: Reference MCP servers in agent manifests, configure guardrails for MCP tools

Error Handling

MCP Server Not Found

MCP server ID not found. List servers first to find the correct ID.

Permission Denied

Cannot access MCP servers. Check your API key permissions.

Server Already Exists

MCP server with this name already exists. Use a different name or delete the existing one first.

Unreachable Remote URL

Cannot reach the MCP server URL. Verify the URL is correct and accessible from the cluster.

OpenAPI Spec Too Large

OpenAPI spec exceeds 30 tools limit. Reduce the number of operations in the spec.

Invalid Transport

Invalid transport type. Use "streamable-http" or "sse".

OAuth2 Configuration Error

OAuth2 auth_data missing required fields. Ensure authorization_url, token_url, client_id, and client_secret are provided.

Virtual Server Reference Not Found

Referenced server name not found. Ensure all servers listed in the virtual server are already registered.

平台分布

Codex

33.8%
按下载量换算43

Claude

29.8%
按下载量换算38

Cursor

18.38%
按下载量换算23

Gemini CLI

8.92%
按下载量换算11

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

接触敏感数据

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills