Signavio

Exposes Signavio API operations as MCP tools for AI assistants, enabling automation of workspace tasks.

javascript

GitHub Stars

javascript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "willpowell8-signavio-mcp": {
      "command": "node",
      "args": [
        "/path/to/signavio/mcp-server.js"
      ],
      "env": {
        "SIGNAVIO_EMAIL": "your-email@example.com",
        "SIGNAVIO_TENANT": "your-tenant-id",
        "SIGNAVIO_BASE_URL": "https://api.eu.signavio.cloud.sap",
        "SIGNAVIO_PASSWORD": "your-password"
      }
    }
  }
}

You can run a Signavio MCP Server that exposes Signavio API operations as MCP tools for AI assistants. This enables automated workflows and AI-driven interactions with your Signavio workspace, using a single server that you start, configure, and query from MCP clients.

How to use

Prepare your MCP client to connect to the Signavio MCP Server by configuring an MCP connection that uses a local (stdio) server setup. You will run the MCP server locally and point your client to the exact command and environment variables described below. With the server running, you can invoke tools such as authentication, folder operations, dictionary management, model operations, and full-text search to automate Signavio tasks.

Once the server is running, you can access its tools through your MCP client by referencing the configured server name. Use the authentication tool to establish a session, then perform actions like creating folders, updating models, exporting models, and searching the dictionary. Your MCP client will pass requests to the Signavio API via the local server, which handles all API interactions and translations.

How to install

Prerequisites you need before installation are: Node.js v14 or higher, npm or yarn, and a Signavio account with API access. You also need your Signavio tenant ID (Workspace ID).

Step by step install and run sequence you should follow:

# Install dependencies
npm install

# Start the MCP server
npm start

# Or run the server directly if you have the entry file
node mcp-server.js

# Optional: run tests to verify MCP server functionality
npm test

Available tools

signavio_authenticate

Authenticate with Signavio API to obtain a valid session token or access key.

signavio_get_root_folders

Retrieve the root folders in the current Signavio workspace.

signavio_get_folder_contents

List contents of a specified folder by ID.

signavio_create_folder

Create a new folder in a specified parent.

signavio_update_folder

Rename or update folder description.

signavio_move_folder

Move a folder to a new parent or into trash.

signavio_delete_folder

Permanently delete a folder.

signavio_search_dictionary

Search dictionary/glossary entries.

signavio_get_dictionary_entry

Retrieve a specific dictionary entry.

signavio_create_dictionary_entry

Create a new dictionary entry.

signavio_update_dictionary_entry

Update an existing dictionary entry.

signavio_delete_dictionary_entry

Delete a dictionary entry.

signavio_get_dictionary_categories

Get all dictionary categories.

signavio_get_dictionary_category

Get a specific dictionary category.

signavio_create_dictionary_category

Create a new dictionary category.

signavio_get_model

Get model metadata.

signavio_get_model_revisions

Get all revisions of a model.

signavio_export_model

Export a model in json, BPMN 2.0 XML, PNG, or SVG.

signavio_create_model

Create a new model/diagram.

signavio_update_model

Update a model, creating a new revision.

signavio_move_model

Move a model to a different folder.

signavio_publish_model

Publish models to the Collaboration Hub.

signavio_search

Full-text search across all content types.

Built by

VeilStrat

AI signals for GTM teams