Guides¶
Step-by-step instructions for common tasks.
Adding a New System¶
Systems (adapters) are created and managed through the web UI.
Using the Adapter Generator (Recommended)¶
- Go to Systems → Create New System
- Click Adapter Generator
- Choose your source:
- OpenAPI/Swagger spec — Paste a URL, Adapterly discovers all endpoints
- HAR file — Record API calls in browser DevTools, upload the HAR file
- Manual — Define endpoints one by one
- Review the discovered endpoints and select which ones to import
- Configure authentication type and credentials
- Click Test Connection — the system becomes "confirmed" after first successful call
Manual Setup¶
- Go to Systems → Create New System
- Fill in system details (name, alias, industry)
- Add an Interface (base URL, auth type)
- Add Resources and Actions (endpoints)
- Enable MCP for the actions you want AI agents to access
Configuring Credentials¶
Each system requires credentials configured per account.
API Key Authentication¶
- Go to Systems → select system → Configure
- Select auth type: API Key
- Enter:
- Header name (e.g.,
X-API-Key,Authorization) - Key value
- Click Test Connection
Bearer Token Authentication¶
- Select auth type: Bearer Token
- Enter your pre-generated access token
- Click Test Connection
OAuth 2.0¶
- Select auth type: OAuth 2.0
- Enter:
- Token URL (e.g.,
https://api.example.com/oauth/token) - Username / Client ID
- Password / Client Secret
- Adapterly automatically obtains, caches, and refreshes tokens
- Click Test Connection
DRF Token Authentication¶
- Select auth type: DRF Token
- Enter username and password
- Adapterly obtains and caches the token automatically
Basic Authentication¶
- Select auth type: Basic
- Enter username and password
- Credentials are Base64-encoded automatically
Setting Up a Project¶
Projects scope which systems and tools are available to AI agents.
Creating a Project¶
- Go to Projects → Create New
- Enter project name and optional description
- Save the project
Adding Integrations¶
- Open the project
- Click Add Integration
- Select the system to include
- Repeat for each system this project needs
Restricting Tool Categories¶
- Open the project settings
- Under Allowed Categories, select which categories are permitted
- Tools outside these categories will be blocked for this project
Creating and Managing API Keys¶
Create an API Key¶
- Go to MCP Gateway → API Keys
- Click Create API Key
- Configure:
- Name - Descriptive name (e.g., "Claude - E18 Project")
- Mode - Safe (read-only) or Power (read/write)
- Project (optional) - Bind to a specific project
- Agent Profile (optional) - Apply a permission profile
- Copy the key (
ak_live_xxx) - shown only once
Manage Keys¶
- Revoke: Immediately disables the key
- Rotate: Create a new key and revoke the old one
- Keys are visible in MCP Gateway → API Keys
Deploying a Standalone Gateway¶
For on-premise or edge deployments, run Adapterly as a standalone Docker gateway.
Prerequisites¶
- Docker and Docker Compose installed
- Network access to the control plane (adapterly.ai) for initial sync
Setup¶
-
Clone the gateway package:
bash cd /opt/adapterly/adapterly-gateway docker compose up -d -
Open the Setup Wizard at
http://your-host:8080/setup/ -
Register with the control plane:
- Enter your control plane URL
- Authenticate with your account credentials
-
The gateway syncs adapter specs and API keys
-
Configure credentials:
- Enter system credentials directly in the gateway admin UI
-
Credentials never leave the gateway
-
Point AI agents to the gateway's MCP endpoint:
http://your-host:8080/mcp/v1/
Testing Connections¶
Connection Test¶
- Go to Systems → select your system → Configure
- Enter credentials
- Click Test Connection
- Green checkmark = success, system becomes "confirmed"
Testing via MCP¶
- Connect an AI agent with your API key
- Ask: "List all tools" or "List projects from [system]"
- Verify data is returned correctly