본문으로 건너뛰기
cccskills
무료GitHub에 공개

mcp-configurator

Configure MCP servers, which expose tools to AI agents, in a holaOS workspace. The skill updates workspace.yaml for remote or local servers, environment variable references, and tool permissions, then checks that the configuration follows the workspace format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

원문원문 설명 보기

Add or update workspace MCP servers using holaOS mcp_registry syntax.

실행 점수 미검증

설치 방법 보기

이럴 때 유용합니다

  • Adding a remote MCP server
  • Updating a local MCP server configuration
  • Restricting which tools an agent can use
  • Registering tools implemented in the workspace

포함된 파일(1)

  • SKILL.md3.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

MCP Configurator

Use this skill when the task is to add, remove, or update MCP access in a holaOS workspace.

Core Rules

  1. Edit workspace.yaml at the workspace root. Do not create mcp.json, .cursor/mcp.json, claude_desktop_config.json, or another generic MCP config unless the user explicitly asks for that format.
  2. Workspace-level MCP lives under mcp_registry.
  3. Tool ids in mcp_registry.allowlist.tool_ids must use strict server.tool syntax.
  4. Omitting mcp_registry.allowlist.tool_ids or setting it to [] means all discovered tools from enabled configured servers stay available for that run.
  5. Mixed mode is valid: some servers can be constrained by explicit allowlisted tool ids while other enabled servers stay discover-all.
  6. This embedded skill is guidance only. When the user asks to add MCP to a workspace, update the target workspace config instead of writing new files under runtime/harnesses/src/embedded-skills/.

Remote Server Shape

Use this shape for remote HTTP MCP servers:

mcp_registry:
  servers:
    context7:
      type: remote
      url: https://mcp.context7.com/mcp
      enabled: true
      timeout_ms: 30000
      headers:
        CONTEXT7_API_KEY: "{env:CONTEXT7_API_KEY}"
  allowlist:
    tool_ids:
      - context7.lookup
      - context7.search

Header values must be either:

  • a literal secret value
  • or {env:ENV_VAR_NAME}

This is invalid:

headers:
  CONTEXT7_API_KEY: "{env:ctx7sk-live-abc123}"

That is a placeholder-shaped literal secret, not an environment-variable reference.

Local Server Shape

Use this shape for local stdio MCP servers:

mcp_registry:
  servers:
    my_server:
      type: local
      command:
        - npx
        - -y
        - "@acme/my-mcp"
      enabled: true
      timeout_ms: 30000
      environment:
        MY_SERVER_API_KEY: "{env:MY_SERVER_API_KEY}"

Local MCP commands must be a non-empty list of command tokens.

Workspace Tool Catalog Shape

Use mcp_registry.catalog for workspace-local tools implemented inside the repo:

mcp_registry:
  servers:
    workspace:
      type: local
  catalog:
    workspace.echo:
      module_path: tools.echo
      symbol: echo_tool
  allowlist:
    tool_ids:
      - workspace.echo

Notes:

  • mcp_registry.servers.workspace must stay local.
  • The runtime owns the actual workspace MCP host command, so do not try to wire a custom command for workspace.
  • Each workspace.<tool> allowlist entry must have a matching mcp_registry.catalog entry.

App-Managed MCP

If the MCP tools come from a workspace app's app.runtime.yaml mcp.tools, prefer the app-managed flow:

  • keep the app manifest correct
  • let the runtime reconcile mcp_registry.servers.<app_id> and mcp_registry.allowlist.tool_ids
  • do not hand-maintain those generated entries unless the task explicitly requires it

Verification

  1. Re-open workspace.yaml and confirm the final shape is mcp_registry, not a generic MCP config format.
  2. Confirm every allowlisted tool id is server.tool.
  3. Confirm every referenced server id exists under mcp_registry.servers.
  4. Confirm placeholder syntax is {env:ENV_VAR_NAME} when environment indirection is intended.
  5. Remember that MCP config changes take effect on the next run, not retroactively inside the already running harness session.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Build holaOS apps for connecting external services or managing work through a dashboard. The skill uses shared SDK building blocks for stored records, actions, and synchronization, with the dashboard and agent tools working on the same data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Building an external service integration
  • Creating a CRM dashboard
  • Building a content planning workspace
holaboss-ai/holaOS1.1만2026년 8월 21일 업데이트

Analyze audience demographics and engagement to identify distinct groups, understand what they want, and prioritize valuable segments. Turn those findings into recommendations for content topics, formats, posting times, and tone, while explaining limits in the data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Identify distinct groups within an audience
  • Prioritize groups that engage or convert
  • Plan topics and formats for each audience group
holaboss-ai/holaOS1.1만2026년 8월 21일 업데이트

Guide an agent through efficient use of an embedded browser by choosing targeted actions, searches, and waits. Reduce repeated tool calls and unnecessary page snapshots, while using more detailed inspection when the target or result remains unclear.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Act on known buttons or fields with fewer browser calls
  • Locate a known target on a large page
  • Wait for navigation or downloads to finish
holaboss-ai/holaOS1.1만2026년 8월 21일 업데이트

Validate workflows and reproduce issues in an embedded browser. Distinguish application problems from incorrect targets, missing waits, or session state, then report the shortest reliable reproduction steps with only the evidence needed to support the finding.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Reproducing a browser workflow failure
  • Checking for regressions after a fix
  • Distinguishing timing issues from application failures
holaboss-ai/holaOS1.1만2026년 8월 21일 업데이트

Build the user interface for a holaOS app whose data resources are already connected through the SDK. Choose a feed, table, kanban board, form, or calendar layout using shared components and workspace styling.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Display scheduled items in a chronological feed
  • Show CRM contacts or tickets in a table
  • Organize issues by status on a kanban board
holaboss-ai/holaOS1.1만2026년 8월 21일 업데이트

Package workspace skills and their required service integrations into one named, installable capability. Create a manifest that references existing skills, install the capability, and report which integrations still need to be connected.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

  • Bundle multiple skills for a shared outcome
  • Declare required external service integrations
  • Create a manifest that references existing skills
holaboss-ai/holaOS1.1만2026년 8월 21일 업데이트

holaboss-ai의 스킬 모두 보기

이 스킬의 문제 신고