Mobi

This is a Model Context Protocol server that will allow agentic interfacing with a given instance of Mobi.
  • python

2

GitHub Stars

python

Language

6 months ago

First Indexed

2 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": {
    "inovexcorp-mobi-mcp": {
      "command": "python",
      "args": [
        "/Users/{username}/git/mobi-mcp/src/mobi-mcp.py"
      ],
      "env": {
        "MOBI_BASE_URL": "https://localhost:8443",
        "MOBI_PASSWORD": "admin",
        "MOBI_USERNAME": "admin",
        "MOBI_IGNORE_CERT": "true"
      }
    }
  }
}

You can connect an external MCP client to your Mobi instance through a dedicated MCP server. This bridge lets you issue structured commands, receive real-time updates, and perform automated tasks against Mobi using the Model Context Protocol.

How to use

To use this MCP server, configure your MCP client to connect via the provided stdio interface. The server runs a Python script that exposes Mobi interactions through MCP endpoints. You typically start the server in the background and point your client at the local stdio channel, then begin issuing authenticated MCP commands to search, fetch, or create Mobi records and assets.

Your client will interact with the server using the standard MCP workflow described by the client’s integration guide. You can leverage the following capabilities exposed by the server: searching the Mobi catalog, retrieving ontology and shapes data, creating ontology records, and managing branches on records. Ensure you supply the required environment variables so the MCP server can authenticate with your Mobi instance and securely communicate.

How to install

Prerequisites: you need Python 3.10 or higher and a running Mobi instance.

Step 1: Clone the MCP server repository and switch to its directory.

Step 2: Create a Python virtual environment.

Step 3: Activate the virtual environment.

Step 4: Install dependencies.

git clone <repository-url>
cd mobi-mcp

python3.12 -m venv .venv

# Activate the virtual environment
# macOS/Linux
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Configuration and usage notes

Configure the MCP server with your Mobi instance details. The following environment variables are required to run the server and connect to Mobi. You can set these in your runtime environment or in the process that launches the MCP server.

Environment variables shown in the example snippet.

{
  "mcpServers": {
    "mobi": {
      "command": "/Users/{username}/git/mobi-mcp/.venv/bin/python",
      "args": ["/Users/{username}/git/mobi-mcp/src/mobi-mcp.py"],
      "env": {
        "MOBI_BASE_URL": "https://localhost:8443",
        "MOBI_USERNAME": "admin",
        "MOBI_PASSWORD": "admin",
        "MOBI_IGNORE_CERT": "true"
      }
    }
  }
}

Security and notes

Keep your Mobi credentials secure. Use TLS in production and consider rotating credentials regularly. If you are testing with self-signed certificates, you may set MOBI_IGNORE_CERT to true for convenience, but disable this in production.

Available tools

record_search

Searches the Mobi catalog for records matching specified criteria, with support for offset, limit, search text, keywords, and types.

entity_search

Searches the Mobi catalog for records whose metadata contains a specified string, with optional filtering by types and keywords.

fetch_ontology_data

Fetches ontology data for a given ontology record IRI based on the record IRI obtained from searches.

get_shapes_graph

Retrieves the shapes graph for a specified record, with optional branch and commit identifiers.

create_ontology_record

Creates a new ontology record from RDF data and metadata, including optional Markdown description and keywords.

create_branch_on_record

Creates a new branch on an existing record with a title and description based on a reference commit.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational