Servidor MCP sucesor de Friday, construido sobre el mismo patrón FastMCP pero organizado como un paquete independiente con un flujo de trabajo de autoextensión.
Servidor MCP central con puntos de entrada FastMCP y módulos de registro reutilizables.
Herramientas de investigación para búsqueda web, obtención de URL y resúmenes de noticias mundiales en tiempo real.
Herramientas de espacio de trabajo para leer, escribir, listar y ejecutar comandos dentro de una raíz de espacio de trabajo configurada.
Herramientas de autoextensión que permiten a Friday validar, instalar, activar, desactivar, eliminar y revertir habilidades.
Superficies de prompts y recursos para que los clientes puedan inspeccionar el catálogo de habilidades activas y obtener plantillas para investigar o crear nuevas habilidades.
Related MCP server: local-skills-mcp
Las habilidades son documentos markdown con metadatos YAML almacenados en skills/installed/.
Son activos de prompt basados en datos, no plugins de Python arbitrarios.
Se pueden crear nuevas habilidades a partir de markdown generado o descargarse desde una URL.
Las instalaciones exitosas se activan automáticamente por defecto.
Reinstalar una habilidad existente crea una copia de seguridad con marca de tiempo para revertir.
Cada habilidad instalada registra la procedencia, compatibilidad, suma de verificación y estado de activación.
Ejemplo:
---
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.uv sync --extra dev
cp .env.example .env
uv run friday-mcp-serverPor defecto, el servidor se ejecuta sobre stdio. Para ejecutar sobre SSE en su lugar:
FRIDAY_MCP_TRANSPORT=sse uv run friday-mcp-serverApunte un cliente MCP de Friday al transporte de este servidor:
Clientes stdio: invoque uv run friday-mcp-server
Clientes SSE: ejecute con FRIDAY_MCP_TRANSPORT=sse y conéctese a /sse
El servidor expone:
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
src/friday_mcp_server/
config.py
server.py
skill_store.py
prompts/
resources/
tools/
skills/
installed/
tests/uv run pytestActivate an installed skill.
Inputs: skill_id (required).
Deactivate an installed skill.
Inputs: skill_id (required).
Normalize skill validation failures for the client.
Inputs: error_text (required). Returns: result
Fetch the raw text of a URL, truncated to the configured limit.
Inputs: url (required). Returns: result
Pretty-print a JSON string.
Inputs: data (required). Returns: result
Return the current date and time in ISO 8601 format.
Inputs: no named parameters. Returns: result
Get the full installed content and metadata for a skill.
Inputs: skill_id (required).
Return basic information about the server host.
Inputs: no named parameters.
Fetch a multi-source snapshot of world headlines.
Inputs: no named parameters. Returns: result
Install a skill from markdown front matter and instructions.
Inputs: markdown (required), source, activate.
Download, validate, install, and optionally activate a skill from a URL.
Inputs: url (required), activate.
List installed skills and their activation state.
Inputs: active_only. Returns: result
List files and directories under the configured workspace root.
Inputs: path, max_depth. Returns: result
Read a file from the workspace with optional line slicing.
Inputs: path (required), start_line, end_line. Returns: result
Remove a skill and keep a rollback backup.
Inputs: skill_id (required).
Restore the latest or selected backup of a skill.
Inputs: skill_id (required), backup_file.
Run a bash command within the workspace root.
Inputs: command (required), timeout, working_dir.
Search the web with DuckDuckGo and return the top results.
Inputs: query (required), max_results. Returns: result
Validate a candidate skill document before installation.
Inputs: markdown (required).
Count characters, words, and lines in a block of text.
Inputs: text (required).
Write a file within the workspace.
Inputs: path (required), content (required), overwrite.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
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.
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.
