Friday MCP Server
Friday MCP 服务器
Friday 的后续 MCP 服务器,基于相同的 FastMCP 模式构建,但组织为具有自我扩展工作流的独立包。
它提供了什么
核心 MCP 服务器,具有 FastMCP 入口点和可重用的注册模块。
研究工具,用于网络搜索、URL 获取和实时世界新闻摘要。
工作区工具,用于在配置的工作区根目录下读取、写入、列出文件和执行命令。
自我扩展工具,允许 Friday 验证、安装、激活、停用、删除和回滚技能。
提示词和资源界面,以便客户端可以检查活动的技能目录,并获取用于研究或编写新技能的模板。
Related MCP server: local-skills-mcp
技能模型
技能是存储在 skills/installed/ 下带有 YAML 前置元数据的 Markdown 文档。
它们是数据驱动的提示词资产,而非任意的 Python 插件。
新技能可以从生成的 Markdown 创建,也可以从 URL 下载。
成功安装的技能默认自动激活。
重新安装现有技能会创建一个带时间戳的备份以供回滚。
每个已安装的技能都会记录来源、兼容性、校验和以及激活状态。
示例:
---
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.快速开始
uv sync --extra dev
cp .env.example .env
uv run friday-mcp-server默认情况下,服务器通过 stdio 运行。若要通过 SSE 运行:
FRIDAY_MCP_TRANSPORT=sse uv run friday-mcp-serverFriday 集成
将 Friday MCP 客户端指向此服务器的传输方式:
stdio 客户端:调用
uv run friday-mcp-serverSSE 客户端:使用
FRIDAY_MCP_TRANSPORT=sse运行并连接到/sse
服务器公开了以下功能:
fetch_url,search_web,get_world_newslist_workspace,read_file,write_file,run_bashlist_skills,get_skill,validate_skill_markdowninstall_skill_from_markdown,install_skill_from_urlactivate_skill,deactivate_skill,remove_skill,rollback_skillget_current_time,get_system_info,format_json,word_count
仓库布局
src/friday_mcp_server/
config.py
server.py
skill_store.py
prompts/
resources/
tools/
skills/
installed/
tests/开发
uv run pytestAvailable Tools
21 toolsactivate_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
Scored across 21 tools
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.
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.
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.
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.
Maintenance
Related MCP Connectors
Hosted MCP server for live public-data APIs and Skills for AI agents.
Hosted MCP server and Agent Skills for specs, engineering threads, and project memory.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Skills, agents and memory in the cloud, plus a gateway to your other MCP servers.
Related MCP Servers
- AlicenseAqualityDmaintenanceA general-purpose MCP server providing web search, persistent memory storage, and secure code execution capabilities. It enables AI agents to search the web, store and retrieve data, and run Python/JavaScript code in sandboxed environments.8MIT
- AlicenseAqualityBmaintenanceA universal MCP server that enables any LLM or AI agent to access expert skills from your local filesystem.3214 npm42MIT
- FlicenseNot gradedqualityFmaintenanceMCP server that gives any LLM a managed Docker workspace with live browser, terminal, code execution, document skills, and autonomous sub-agents.126-
- AlicenseNot gradedqualityCmaintenanceA self-hostable MCP server that turns a folder of skills into callable tools via MCP and REST APIs.3MIT