Skip to main content
Glama
Friday MCP Server

Friday MCP Server

Friday MCP 서버

Friday의 후속 MCP 서버로, 동일한 FastMCP 패턴을 기반으로 구축되었으며 자체 확장 워크플로우를 갖춘 독립형 패키지로 구성되었습니다.

제공 기능

  • FastMCP 진입점과 재사용 가능한 등록 모듈을 갖춘 핵심 MCP 서버.

  • 웹 검색, URL 가져오기, 실시간 세계 뉴스 요약을 위한 연구 도구.

  • 구성된 작업 공간 루트 내에서 파일을 읽고, 쓰고, 나열하고, 명령을 실행하기 위한 작업 공간 도구.

  • Friday가 스킬을 검증, 설치, 활성화, 비활성화, 제거 및 롤백할 수 있도록 하는 자체 확장 도구.

  • 클라이언트가 활성 스킬 카탈로그를 검사하고 연구 또는 새로운 스킬 작성을 위한 템플릿을 얻을 수 있는 프롬프트 및 리소스 인터페이스.

Related MCP server: local-skills-mcp

스킬 모델

스킬은 skills/installed/ 아래에 저장된 YAML 프론트 매터가 포함된 마크다운 문서입니다.

  • 임의의 파이썬 플러그인이 아닌 데이터 기반 프롬프트 자산입니다.

  • 새로운 스킬은 생성된 마크다운에서 만들거나 URL에서 다운로드할 수 있습니다.

  • 성공적으로 설치된 스킬은 기본적으로 자동 활성화됩니다.

  • 기존 스킬을 재설치하면 롤백을 위해 타임스탬프가 찍힌 백업이 생성됩니다.

  • 각 설치된 스킬은 출처, 호환성, 체크섬 및 활성화 상태를 기록합니다.

예시:

---
id: web-research
name: Web Research
version: 1.0.0
description: Gather and compare information from multiple current sources.
capabilities:
  - search
  - citation
min_server_version: 0.1.0
---
Use web search to gather multiple sources before drawing conclusions.
Prefer primary or official sources when possible.

빠른 시작

uv sync --extra dev
cp .env.example .env
uv run friday-mcp-server

기본적으로 서버는 stdio를 통해 실행됩니다. SSE를 통해 실행하려면:

FRIDAY_MCP_TRANSPORT=sse uv run friday-mcp-server

Friday 통합

Friday MCP 클라이언트를 이 서버의 전송 방식에 연결하세요:

  • stdio 클라이언트: uv run friday-mcp-server 호출

  • SSE 클라이언트: FRIDAY_MCP_TRANSPORT=sse로 실행하고 /sse에 연결

서버는 다음을 노출합니다:

  • fetch_url, search_web, get_world_news

  • list_workspace, read_file, write_file, run_bash

  • list_skills, get_skill, validate_skill_markdown

  • install_skill_from_markdown, install_skill_from_url

  • activate_skill, deactivate_skill, remove_skill, rollback_skill

  • get_current_time, get_system_info, format_json, word_count

저장소 구조

src/friday_mcp_server/
  config.py
  server.py
  skill_store.py
  prompts/
  resources/
  tools/
skills/
  installed/
tests/

개발

uv run pytest

Available Tools

21 tools
activate_skillC

Activate an installed skill.

Inputs: skill_id (required).

deactivate_skillC

Deactivate an installed skill.

Inputs: skill_id (required).

explain_skill_errorD

Normalize skill validation failures for the client.

Inputs: error_text (required). Returns: result

fetch_urlB

Fetch the raw text of a URL, truncated to the configured limit.

Inputs: url (required). Returns: result

format_jsonB

Pretty-print a JSON string.

Inputs: data (required). Returns: result

get_current_timeA

Return the current date and time in ISO 8601 format.

Inputs: no named parameters. Returns: result

get_skillC

Get the full installed content and metadata for a skill.

Inputs: skill_id (required).

get_system_infoB

Return basic information about the server host.

Inputs: no named parameters.

get_world_newsA

Fetch a multi-source snapshot of world headlines.

Inputs: no named parameters. Returns: result

install_skill_from_markdownC

Install a skill from markdown front matter and instructions.

Inputs: markdown (required), source, activate.

install_skill_from_urlB

Download, validate, install, and optionally activate a skill from a URL.

Inputs: url (required), activate.

list_skillsC

List installed skills and their activation state.

Inputs: active_only. Returns: result

list_workspaceB

List files and directories under the configured workspace root.

Inputs: path, max_depth. Returns: result

read_fileC

Read a file from the workspace with optional line slicing.

Inputs: path (required), start_line, end_line. Returns: result

remove_skillB

Remove a skill and keep a rollback backup.

Inputs: skill_id (required).

rollback_skillC

Restore the latest or selected backup of a skill.

Inputs: skill_id (required), backup_file.

run_bashC

Run a bash command within the workspace root.

Inputs: command (required), timeout, working_dir.

search_webB

Search the web with DuckDuckGo and return the top results.

Inputs: query (required), max_results. Returns: result

validate_skill_markdownC

Validate a candidate skill document before installation.

Inputs: markdown (required).

word_countA

Count characters, words, and lines in a block of text.

Inputs: text (required).

write_fileC

Write a file within the workspace.

Inputs: path (required), content (required), overwrite.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 21 tools

    Disambiguation4/5

    Tools are grouped into clear categories (skill management, workspace, utilities) with distinct purposes. Only minor potential overlap between search_web and get_world_news (both fetch external info) but descriptions differentiate them.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with underscores, e.g., activate_skill, fetch_url, get_current_time. Verbs are descriptive and noun targets are clear, making the set predictable.

    Tool Count4/5

    21 tools is slightly above typical range (3-15) but each tool serves a well-defined purpose and covers a broad domain (skills, workspace, utilities) without redundancy. Could be trimmed slightly but still reasonable.

    Completeness4/5

    The tool set covers essential skill lifecycle (install, activate, deactivate, remove, rollback) and workspace operations (read/write/list). Minor gaps like direct skill content update are missing, but rollback and reinstall compensate. Utility tools add breadth.

    Related MCP Connectors

    Related MCP Servers