Skip to main content

MCP Server

The MCP Server is the bridge that lets an AI assistant talk to Automation Hub.

It does not replace Automation Hub. It does not create random actions on its own. It gives the AI assistant a controlled set of approved actions, such as searching for automations, running one, checking progress, and reading results.

The Basic Idea

AI Assistant
Receives a request from the user
MCP Server
Checks which Automation Hub actions are available
Automation Hub
Runs the selected automation and records the result
Simple: the MCP Server is the controlled doorway between AI conversations and real automation work.

What the MCP Server Does

It helps the AI...Plain-English meaning
Discover automationsFind what jobs are available
Understand automationsRead what a job does and what inputs it needs
Start automationsRun the selected job with the right information
Monitor executionsCheck whether the job is running, completed, failed, or paused
Manage executionsPause, resume, or stop a run when appropriate
Return resultsGive the final outcome back to the AI assistant

Why It Exists

AI assistants need boundaries when they interact with business systems. The MCP Server provides those boundaries.

Without the MCP ServerWith the MCP Server
AI may need custom integration for every actionAI uses one clear set of approved tools
Actions may be inconsistentEvery action follows Automation Hub rules
Results may be hard to trackRuns are recorded in Automation Hub history
Permissions may be difficult to manageAccess can follow platform governance

What Happens When a User Makes a Request

User Request
"Run the monthly sales report"
Find Job
The AI asks the MCP Server which automation matches
Check Inputs
The AI confirms required details, such as month or recipient
Run and Monitor
Automation Hub runs the job and the AI checks progress

What Administrators Care About

AreaWhat to confirm
AvailabilityThe MCP Server is running and reachable by approved AI clients
PermissionsUsers can only run automations they are allowed to use
EnvironmentThe server points to the correct Automation Hub services
MonitoringHealth checks and logs are available
SecuritySecrets and credentials are managed safely

What Users Care About

Users usually do not need to know how the MCP Server is configured. They only need to know that it lets the AI assistant:

  • Find the right automation
  • Ask for missing information
  • Start the job
  • Report progress
  • Explain the final result

Server Health

Administrators can check whether the MCP Server is available through its health check. A healthy server means the AI bridge is running and ready to receive approved tool requests.

StatusMeaning
HealthyThe AI bridge is available
UnavailableAI assistants may not be able to run or monitor automations
MisconfiguredThe bridge may be running but unable to reach Automation Hub services

Good Setup Practices

Use clear environments

  • Keep development, QA, and production settings separate

Protect credentials

  • Store passwords, API keys, and service URLs securely

Monitor the bridge

  • Check health and logs so AI requests do not fail silently

Start with a small set of automations

  • Enable AI access for well-understood automations first

Review run history

  • Every AI-started automation should be traceable in Automation Hub

MCP Servers in AI Hub

The concepts above describe the MCP bridge in general. In practice, an agent reaches an external MCP server through an entry you register in the AI Hub part of Global Configurator. Each registered server is a stored document, and the AI Agent node references it by id through toolsConfig.mcpServers[].

Stored Server Fields

FieldTypeDefaultDescription
namestring--Unique server name; a duplicate returns 409
urlstring--The MCP server endpoint
descriptionstring--What the server provides
authTypestringNONEHow the server authenticates: NONE, BEARER, API_KEY, BASIC, or CUSTOM
authConfigmap{}Credentials for the chosen auth type; sensitive values are Vault-encrypted
statusstringUNKNOWNONLINE, OFFLINE, or UNKNOWN
toolCountint0Number of tools found at the last discovery
discoveredToolsobject[][]Each tool as { name, description, inputSchema }
tagsstring[][]Free-form labels for search
lastCheckedAttimestamp--When discovery last ran

Authentication Types

authTypeWhat authConfig holds
NONENo credentials
BEARERA bearer token
API_KEYA named apiKey and its placement
BASICA username and password
CUSTOMCustom headers or fields the server requires

Credential Encryption

Sensitive authConfig values are protected with Vault Transit encryption before they are stored:

  • Sensitive keys — token, apiKey, apikey, password, secret, clientSecret, privateKey — and nested header values are encrypted.
  • Values already prefixed with vault: are treated as pre-encrypted and skipped.
  • A normal read of the server never returns decrypted credentials. Decryption happens only for the internal, service-to-service call that actually contacts the server.

Tool Discovery

Registering a server does not automatically list its tools. Discovery is an explicit action:

Discover
POST /ai-hub/mcp-servers/:id/discover
Validate
connectivity-validator runs the JSON-RPC handshake
List Tools
initialize, then tools/list returns the tool set
Store
discoveredTools, toolCount, and status are saved

The discover action delegates to connectivity-validator, which performs the MCP JSON-RPC initialize call followed by tools/list. Discovery is considered successful only when the validator reports status == "success" and no step is marked FAILED. The result updates discoveredTools, toolCount, status, and lastCheckedAt.

note

The discover action replaces the old /{id}/test endpoint, which was a stub that always returned SUCCESS. That stub has been removed — use discover to get real tool data and a real reachability check.

For the fields of each discovered tool and how tools become callable, see MCP Tools Reference.