Adobe Sign workflows MCP server
Adobe Sign workflows let you build multi-step approval and signature processes with conditional routing, parallel approvals, and automated actions. An AI agent with access to Adobe Sign workflows can create approval chains, set up conditional logic to route documents based on business rules, automate downstream actions like CRM updates, and track approval progress. This integration is useful for finance teams building expense approval workflows, legal teams managing contract reviews, or HR teams automating offer letter sign-offs with multiple stakeholders.
Setting up an MCP server
This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.
Before you begin
You'll need:
- Access to AI Gateway with permission to create MCP servers
- API credentials for the application you're connecting (see the relevant application page for what to collect)
Create an MCP server
Find the API in the catalog
- Sign in to AI Gateway and select MCP Servers from the left navigation.
- Select New MCP Server.
- Search for the application you want to connect, then select it from the catalog.
Configure the server
- Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
- Enter a Description so your team knows what the server is for.
- Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
- Toggle Production mode on if this server will be used in a live workflow.
- Select Next.
Configure authentication
Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.
Configure security
- Set any Rate limits appropriate for your use case and the API's own limits.
- Enable Logging if you want AI Gateway to record requests and responses for auditing.
- Select Next.
Deploy
Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.
Connect to an AI client
Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:
Tips
- You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
- If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
- You can edit a server's name, description, timeout, and security settings after deployment without redeploying.
Authentication
Adobe Sign uses OAuth 2.0 for secure authentication. You'll need an Adobe Sign Business or Enterprise account with workflow creation permissions. Create an OAuth application in your Adobe Sign account and configure these endpoints:
- Authorization URL:
https://secure.{region}.adobesign.com/public/oauth/v2 - Token URL:
https://api.{region}.adobesign.com/oauth/v2/token
The scopes you'll need are workflow_read to view workflows, workflow_write to create and modify workflows, workflow_execute to start workflows, template_read and template_write to manage templates, and form_read and form_write to configure intake forms. Optional scopes include agreement_read for agreement context.
Available tools
These tools let you design, launch, and monitor multi-step approval workflows with conditional routing and automated actions.
| Tool | Description |
|---|---|
| Create workflow | Build a new multi-step approval or signature process |
| List workflows | Retrieve all workflows with filtering by use case or status |
| Get workflow details | View all steps, participants, conditions, and settings |
| Start workflow | Launch a workflow instance for a specific document or form |
| Get workflow status | Check progress and current step for a running workflow |
| List workflow instances | Retrieve all active and completed runs of a workflow |
| Get workflow participant | View the assigned approver or signer for a step |
| Add workflow step | Insert a new approval or signature stage into a workflow |
| Set condition | Add conditional logic to route based on form values or thresholds |
| Save as template | Convert a workflow into a reusable template for your team |
Tips
Design workflows with 3–5 steps maximum — overly complex approval chains cause delays and confusion for participants.
Use meaningful step names and descriptions (for example, "Manager Review" instead of "Step 2") so participants understand what they're approving.
Set realistic timeouts and escalation rules (for example, escalate to the manager's manager if no response within 3 days) to prevent bottlenecks.
Test conditional logic with edge cases (for example, the highest amount threshold and the lowest) before deploying to ensure routing works correctly.
Track workflow completion times and rejection reasons regularly to identify approval steps that consistently cause delays or rejections, then optimize those steps or provide additional guidance to participants.
Cequence AI Gateway