Official Model Context Protocol (MCP) server for Figranium. Connects Claude, ChatGPT, and AI agents directly to Figranium tools and workflows.
- ✓Open-source license (GPL-3.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add figranium-mcp -- npx -y figranium-mcp{
"mcpServers": {
"figranium-mcp": {
"command": "npx",
"args": ["-y", "figranium-mcp"]
}
}
}Resumen de MCP Servers
# Figranium MCP Server
[](https://registry.modelcontextprotocol.io)
[](https://github.com/figranium/figranium-mcp/pkgs/container/figranium-mcp)
A Model Context Protocol (MCP) server for [Figranium](https://github.com/figranium/figranium) built using `@modelcontextprotocol/sdk`. This server allows LLM clients (like Claude Desktop, Cursor, and Manus AI) to discover, execute, inspect, schedule, and programmatically create Figranium automation tasks via standard STDIO transport.
## Table of Contents
- [Quick Start (Docker / OCI)](#quick-start-docker--oci)
- [Client Integration](#client-integration)
- [Claude Desktop](#claude-desktop)
- [Cursor IDE](#cursor-ide)
- [Manus AI / Registry Clients](#manus-ai--registry-clients)
- [Environment Variables](#environment-variables)
- [Server-Wide System Instructions](#server-wide-system-instructions)
- [Available Resources](#available-resources)
- [Available Tools](#available-tools)
- [Task Operations](#task-operations)
- [Execution Operations](#execution-operations)
- [Schedule Operations](#schedule-operations)
- [Rich Input Diagnostics & Self-Correction](#rich-input-diagnostics--self-correction)
- [Local Development & Source Build](#local-development--source-build)
---
## Quick Start (Docker / OCI)
No Node.js runtime or repository clone is required. The official container image is published on GitHub Container Registry (`ghcr.io`).
Zero-config npm usage is also supported:
```bash
npx -y figranium-mcp
```
For local development:
```bash
git clone https://github.com/figranium/figranium-mcp
dcd figranium-mcp
npm install
npm run build
```
```bash
docker pull ghcr.io/figranium/figranium-mcp:latest
```
## Environment Variables
The server requires the following environment variables to interact with your Figranium instance:
* `FIGRANIUM_BASE_URL`: The base URL of your Figranium server. Defaults to `http://localhost:11345`.
* `FIGRANIUM_API_KEY`: The API key generated from Figranium settings to authorize requests. This variable is required for startup.
If `FIGRANIUM_API_KEY` is missing, the server prints a clear setup message and exits gracefully.
---
## Client Integration
### Claude Desktop
Add the container configuration to your `claude_desktop_config.json`:
* **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
* **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
```json
{
"mcpServers": {
"figranium": {
"command": "npx",
"args": ["-y", "figranium-mcp"],
"env": {
"FIGRANIUM_BASE_URL": "http://localhost:11345",
"FIGRANIUM_API_KEY": "your_figranium_api_key_here"
}
}
}
}
```
> **Note for Local Hosts**: If your Figranium instance runs locally on your host machine,
> use `http://localhost:11345` when running via `npx`.
---
### Cursor Integration
Add the following to `~/.cursor/mcp.json`:
```json
{
"mcpServers": {
"figranium": {
"command": "npx",
"args": ["-y", "figranium-mcp"],
"env": {
"FIGRANIUM_BASE_URL": "http://localhost:11345",
"FIGRANIUM_API_KEY": "YOUR_API_KEY"
}
}
}
}
```
This lets Claude Desktop and Cursor launch the package directly without requiring a local build or a Docker bridge.
---
## Server-Wide System Instructions
The server initializes with embedded guidelines for LLM agents detailing the task lifecycle:
1. **Task Creation**: Structuring name, starting URL, execution mode (`scrape`, `agent`, or `headful`), and stealth mechanisms.
2. **Step Sequence Construction**: Ordering action steps (`navigate`, `wait_selector`, `click`, `type`, `javascript`) and execution flow.
3. **Selector Strategy**: Preferring robust ARIA, ID, and semantic class selectors with fallback strategies.
4. **Execution & Variables**: Injecting and overriding runtime context variables.
---
## Available Resources
### `figranium://schemas/task-v1.json`
* **MIME Type**: `application/json`
* **Description**: Exposes the complete JSON Schema specification of a Figranium task. Allows agents to dynamically inspect valid parameters and payload shapes.
---
## Available Tools
### Task Operations
* **`create_task`**: Create a complete, fully-configured Figranium automation task including sequential action steps, state variables, anti-bot stealth mechanisms, and optional scheduling.
* **`task_list`**: List all task IDs, names, and descriptions registered on the Figranium server.
* **`task_execute`**: Run a saved task by `taskId` with optional variable overrides.
### Execution Operations
* **`execution_list`**: Retrieve a summary of past task execution logs and statuses.
### Schedule Operations
* **`schedule_list`**: List all tasks with configured schedules.
* **`schedule_get_all_status`**: Retrieve overall scheduler state and metadata.
* **`schedule_get_status`**: Get active schedule details and next run time for a specific `taskId`.
* **`schedule_set`**: Create or update a cron or frequency schedule on a task.
* **`schedule_delete`**: Disable and remove a task schedule.
* **`schedule_describe`**: Validate and preview a schedule configuration without applying it.
---
## Rich Input Diagnostics & Self-Correction
If an invalid parameter payload is supplied to `create_task`, the server returns structured Zod diagnostic output (`isError: true`). This allows connected LLMs to analyze schema errors and attempt immediate self-correction.
Example response:
```text
Schema Validation Failed!
Detailed breakdown of validation errors:
- At Step Index 2 (action step #3), parameter "type" failed validation: Invalid enum value. Expected 'click' | 'type' | 'wait' ..., received 'clikc'
```
---
## Local Development & Source Build
If you wish to modify the source code or run without Docker:
### Prerequisites
* Node.js v18+
* npm v9+
### Build & Run
```bash
# Clone repository
git clone [https://github.com/figranium/figranium-mcp.git](https://github.com/figranium/figranium-mcp.git)
cd figranium-mcp
# Install dependencies and compile TypeScript
npm install
npm run build
# Watch mode for active development
npm run watch
```
### Testing with MCP Inspector
Inspect server tools and resources using the official MCP debugging suite:
```bash
npx @modelcontextprotocol/inspector npx -y figranium-mcp
```
Lo que la gente pregunta sobre figranium-mcp
¿Qué es figranium/figranium-mcp?
+
figranium/figranium-mcp es mcp servers para el ecosistema de Claude AI. Official Model Context Protocol (MCP) server for Figranium. Connects Claude, ChatGPT, and AI agents directly to Figranium tools and workflows. Tiene 1 estrellas en GitHub y su última actualización registrada es del 2026-08-05.
¿Cómo se instala figranium-mcp?
+
Puedes instalar figranium-mcp clonando el repositorio (https://github.com/figranium/figranium-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar figranium/figranium-mcp?
+
Nuestro agente de seguridad ha analizado figranium/figranium-mcp y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene figranium/figranium-mcp?
+
figranium/figranium-mcp es mantenido por figranium. La última actividad registrada en GitHub es del 2026-08-05, con 0 issues abiertos.
¿Hay alternativas a figranium-mcp?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega figranium-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/figranium-figranium-mcp)<a href="https://claudewave.com/repo/figranium-figranium-mcp"><img src="https://claudewave.com/api/badge/figranium-figranium-mcp" alt="Featured on ClaudeWave: figranium/figranium-mcp" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!