Model Context Protocol (MCP)

Model Context Protocol (MCP) is an open standard developed by Anthropic that provides a unified, structured protocol for AI assistants, coding agents, and IDEs to interact with external automation tools and systems.

Developer Preview: Model Context Protocol (MCP) integration is currently available for workspace developers and engineering preview accounts. This guide details the architecture, tool specifications, and integration models.

Glow supports MCP across two complementary architectures:

Connect external AI assistants (Cursor, Claude Desktop, Zed, Claude Code) to discover, inspect, and trigger automations directly from your IDE.

Glow as an MCP Server

Equip visual AI Agent steps with external tool servers (Postgres MCP, GitHub MCP, custom internal APIs).

Glow as an MCP Client

Server Architecture & Protocol Flow

When an authorized AI client connects to Glow’s MCP server, the protocol negotiates capabilities and establishes a secure JSON-RPC channel. The gateway authenticates every tool invocation against workspace policies before dispatching it to the execution engine:

Access & Permission Model

MCP access is governed by scoped developer tokens with explicit capability boundaries:

Permission Scope	Granted Operations	Security Policy
`mcp:read`	Read-only discovery: `list_workflows`, `get_workflow_schema`, `get_execution_status`.	Cannot trigger executions or modify workspace state.
`mcp:execute`	Execution capabilities: `execute_workflow`, `test_step`.	Strictly limited to the authenticated workspace.

Security Guarantees: - Scoped Bearer token authentication with cryptographic verification. - Tenant isolation: Access strictly limited to your authorized workspace. - Audit visibility: Sandboxed executions tagged with an MCP test badge. - Zero credential leakage: Real secrets and OAuth tokens are never exposed in tool schemas.

Example Developer Interactions

When connected to an MCP server, an AI assistant interprets natural language instructions and executes structured tool calls:


"Show me all active workflows in my workspace."
→ Calls list_workflows(status="live")


"What inputs does the 'Support Ticket Triage' workflow require?"
→ Calls get_workflow_schema(workflowId="flow_84920481")


"Run the 'Lead Enrichment' workflow for customer [email protected]."
→ Calls execute_workflow(workflowId="flow_84920481", payload={ customer_email: "[email protected]" })


"Test step 2 (HTTP Request) in isolation with mock input { ticket_id: 104 }."
→ Calls test_step(workflowId="flow_84920481", stepNumber=2, mockedInputs={ ... })

MCP Server: Tool Reference

The Glow MCP server exposes five primary tools organized by operational function:

Tool	Scope	Purpose
`list_workflows`	`mcp:read`	Discover available workflows, trigger types, and status.
`get_workflow_schema`	`mcp:read`	Inspect trigger parameter schemas, variables, and step layout.
`execute_workflow`	`mcp:execute`	Trigger a workflow execution with custom JSON payload.
`get_execution_status`	`mcp:read`	Poll live run progress, duration, and step-level outputs.
`test_step`	`mcp:execute`	Run a single action step in a sandbox with mock predecessor inputs.

1. `list_workflows`

Returns a list of workflows available in the authenticated workspace.

Parameters

Parameter	Type	Required	Default	Description
`status`	`string`	No	`"all"`	Filter by status: `"live"`, `"draft"`, or `"all"`.
`search`	`string`	No	`null`	Keyword filter matching workflow name or description.
`limit`	`integer`	No	`50`	Maximum number of workflow summaries to return (1–100).

Tool Call


{
  "name": "list_workflows",
  "arguments": {
    "status": "live",
    "search": "Support"
  }
}

2. `get_workflow_schema`

Fetches the complete structural schema for a workflow, including required trigger parameters, mapped variables, and step sequences.

Parameters

Parameter	Type	Required	Description
`workflowId`	`string`	Yes	The unique identifier of the workflow (e.g. `flow_84920481`).

Tool Call


{
  "name": "get_workflow_schema",
  "arguments": {
    "workflowId": "flow_84920481"
  }
}

3. `execute_workflow`

Triggers a workflow run with a supplied JSON payload and returns an execution tracking ID.

Parameters

Parameter	Type	Required	Default	Description
`workflowId`	`string`	Yes	—	Target workflow ID.
`payload`	`object`	Yes	—	JSON data dictionary passed to the trigger step.
`correlationId`	`string`	No	`null`	Optional tracking identifier for log correlation.
`mode`	`string`	No	`"live"`	Run mode: `"live"` (published version) or `"draft"`.

Tool Call


{
  "name": "execute_workflow",
  "arguments": {
    "workflowId": "flow_84920481",
    "payload": {
      "customer_email": "[email protected]",
      "ticket_subject": "Payment API returned 504",
      "ticket_body": "Transactions timed out during checkout."
    },
    "correlationId": "ticket-4812"
  }
}

4. `get_execution_status`

Queries the execution state and individual step outputs of an active or finished run.

Parameters

Parameter	Type	Required	Default	Description
`executionId`	`string`	Yes	—	Execution ID returned from `execute_workflow`.
`includeStepOutputs`	`boolean`	No	`true`	When `true`, includes step-level `result` objects.

Tool Call


{
  "name": "get_execution_status",
  "arguments": {
    "executionId": "exec_9a8f234b01e"
  }
}

5. `test_step` (Isolated Sandbox Test)

Executes a single step in complete isolation, using real workspace credentials and optional mock data representing predecessor steps.

Parameters

Parameter	Type	Required	Description
`workflowId`	`string`	Yes	ID of the workflow containing the step.
`stepNumber`	`integer`	Yes	Step number to execute (e.g. `2`).
`mockedInputs`	`object`	No	Dictionary mapping predecessor step numbers to mock output objects.

Key Sandbox Capabilities

No cascade execution: Steps wired after the test target are not run.
Authentic authentication: The step uses configured workspace integrations and secrets securely.
Audit tracking: Test executions are logged in Activity and tagged with an MCP test badge.

Tool Call


{
  "name": "test_step",
  "arguments": {
    "workflowId": "flow_84920481",
    "stepNumber": 2,
    "mockedInputs": {
      "1": {
        "ticket_subject": "504 Gateway Timeout during checkout",
        "ticket_body": "Payment endpoint stopped responding."
      }
    }
  }
}

Glow as an MCP Client

In addition to serving tools to external AI clients, Glow automations can consume external MCP tool servers to empower visual AI Agent steps:

External Server Registration: Connect remote MCP servers in workspace settings with remote endpoint URLs and authentication headers.
Agent Tool Assignment: Toggle external tool servers on inside the AI Agent step’s Tools panel.
Autonomous Reasoning: During workflow runs, the agent discovers and invokes external tools dynamically to fulfill user goals.

What’s Next?

👉 REST API & Webhooks →: Standard REST endpoints for programmatic workflow execution.
AI Agent Step: Build multi-turn autonomous reasoning workflows on the visual canvas.
Secrets and Variables: Secure management for API keys and credentials.

Model Context Protocol (MCP)

Server Architecture & Protocol Flow

Access & Permission Model

Example Developer Interactions

MCP Server: Tool Reference

1. `list_workflows`

Tool Call

Response JSON

2. `get_workflow_schema`

Tool Call

Response JSON

3. `execute_workflow`

Tool Call

Response JSON

4. `get_execution_status`

Tool Call

Response JSON

5. `test_step` (Isolated Sandbox Test)

Tool Call

Response JSON

Glow as an MCP Client

What’s Next?

Model Context Protocol (MCP)

Server Architecture & Protocol Flow

Access & Permission Model

Example Developer Interactions

MCP Server: Tool Reference

1. list_workflows

Tool Call

Response JSON

2. get_workflow_schema

Tool Call

Response JSON

3. execute_workflow

Tool Call

Response JSON

4. get_execution_status

Tool Call

Response JSON

5. test_step (Isolated Sandbox Test)

Tool Call

Response JSON

Glow as an MCP Client

What’s Next?

1. `list_workflows`

2. `get_workflow_schema`

3. `execute_workflow`

4. `get_execution_status`

5. `test_step` (Isolated Sandbox Test)