Free cookie consent management tool by TermsFeed

Make Design Objects Available as MCP Tools

On This Page

Developers make existing Appian design objects available as MCP tools on Appian MCP Server so external AI applications can discover and use them through Model Context Protocol (MCP).

Appian MCP Server enforces the same object security, record-level security, and group membership as the Appian platform. Users only see tools they have permission to access.

Supported design objects

The following design objects are available as Model Context Protocol (MCP) tools:

  • Record types: External AI applications can read and query record data from synced record types. Record types that use direct data access or have a record-level security expression cannot be queried by external systems or agents.
  • Process models: External AI applications can start process models and check execution status.
  • Expression rules: External AI applications can evaluate expression rules with provided inputs.
  • AI agents: External AI applications can invoke Appian AI agents with a prompt and receive responses.

Enable a design object as an MCP tool

The enablement process differs by design object type. Process models, expression rules, and AI agents must be explicitly enabled through each object's properties.

Synced record types are available through the data fabric MCP tools by default and do not require individual enablement, but you can configure how the data fabric tools identify the record type.

Process models, expression rules, and AI agents

To make a process model, expression rule, or AI agent available as a Model Context Protocol (MCP) tool:

  1. Open the design object in Appian Designer.
  2. Open the object's properties dialog.
  3. Select Enable MCP Server Access.
  4. Review the Description field to ensure it clearly explains what the object does and when to use it. For guidance, see Write effective design object descriptions.
  5. Click OK.
  6. Give the service account at least Viewer permission to the object.

The design object is now discoverable and invocable by external AI applications connected to Appian MCP Server—no code changes or redesign required.

Record types

Synced record types are available through the data fabric MCP tools by default—you do not need to enable them individually.

Access to record type data is controlled entirely through security. For details on required permissions, see Appian MCP Server Security.

Tip:  Ensure each record type has a clear description since AI applications use them to decide when and how to use it. For guidance, see Write effective design object descriptions.

View or edit the SQL reference name

The data fabric MCP tools use a record type's SQL reference name to identify and query data. Appian generates a SQL reference name for each synced record type by default. You can view the current name or update it to a different unique name.

To view or edit the SQL reference name for a synced record type:

  1. In Appian Designer, open the record type.
  2. Click Settings > Properties.
  3. In the SQL Reference Name field, enter a new name. SQL reference names must be unique across the environment.
  4. Click SAVE CHANGES to close the properties.
  5. Click SAVE to save the record type settings.

Note:  When you deploy a synced record type, the SQL reference name is included in the deployment. If the name conflicts with a different record type in the target environment, the deployment fails. For details, see Record type SQL reference name conflicts.

How the generic tool architecture works

Appian MCP Server does not create a separate Model Context Protocol (MCP) tool definition for each design object you enable. Instead, Appian provides a fixed set of system tools that handle discovery and execution for all MCP-enabled design objects:

  1. An external AI application calls appian_search_tools to find available tools matching the user's request.
  2. The AI application calls appian_get_tool_schema to retrieve the full input and output schema for a specific tool.
  3. The AI application calls the appropriate invocation tool to execute the design object.

Developers do not define individual tool names or schemas. Appian generates the tool schema automatically from the design object's configuration (input variables, parameters, and data types).

Write effective design object descriptions

The design object's description is how AI applications decide when and how to use your tool. A well-written description directly affects whether the AI application selects your tool for a user's request.

A good tool description includes:

  • What the tool does: A clear statement of the tool's purpose.
  • When to use it: Context about when this tool is the right choice.
  • What inputs it expects: A brief mention of key inputs the tool requires.

For detailed guidance and examples, see Write Effective MCP Tool Descriptions.

Complex input types

When a process model or expression rule accepts inputs that use record types or custom data types (CDTs), Appian MCP Server sends the full nested schema to the AI application so it can construct the correct input structure.

The AI application receives:

  • Parameter names and types for each input.
  • Required versus optional designation for each parameter.
  • Nested field definitions for record types and CDTs.

Object design guidance

Process models

When enabling a process model as a Model Context Protocol (MCP) tool, process variables marked as inputs become tool parameters. The AI application provides values for these parameters when invoking the tool.

Caution:  Process models with start forms or synchronous user input tasks cannot complete through MCP. The tool call stalls until the process times out. A warning appears in the properties dialog when you enable a process model that contains these elements.

Design considerations for process model MCP tools:

  • Remove start form dependencies. Process models invoked through MCP cannot present forms to users. Remove start forms or create a separate version for MCP invocation.
  • Avoid synchronous user input tasks. Activities that wait for user input (such as attended tasks) block execution indefinitely through MCP.
  • Keep execution time reasonable. Long-running process models may time out before completion. Design MCP-invoked process models to complete without manual intervention.

Expression rules

When enabling an expression rule as a Model Context Protocol (MCP) tool, the rule's input parameters become tool parameters. The AI application provides values for these parameters when invoking the tool.

Design considerations for expression rule MCP tools:

  • Security behavior: If the expression rule queries objects the authenticated user lacks access to, the rule succeeds but returns null for inaccessible data. This behavior is consistent with standard platform behavior.
  • Timeout: Expression rules must complete within the execution timeout. Design rules that perform heavy computation or large data queries to complete efficiently.
  • Use cases: Expression rules work well as MCP tools for business logic, calculations, data transformations, and lookups.

AI agents

When enabling an AI agent as a Model Context Protocol (MCP) tool, external AI applications send a prompt to the Appian AI agent and receive the response.

Design considerations for AI agent MCP tools:

  • Permission requirement: The authenticated user must have permission to view the AI agent and all of its underlying tools.
  • Single-turn interaction: MCP invocations are single-turn. The external AI application sends one prompt and receives one response. Multi-turn conversations are not supported through MCP.
  • Context limitations: The AI agent receives only the prompt provided by the external AI application. Context from the user's conversation in the external AI application is not automatically passed to the Appian AI agent.

Filter design objects by MCP status

To find which design objects in your application are enabled as Model Context Protocol (MCP) tools:

  1. In Appian Designer, open your application.
  2. In the application, go to the Build view.
  3. In the All Objects pane, select MCP Enabled to show only MCP-enabled objects.

The filter displays all design objects in the application that have Make available as MCP tool enabled. Record types do not appear in this filter. They are available through the data fabric tools by default and do not require individual enablement.

How MCP tool configurations deploy

Model Context Protocol (MCP) tool configuration metadata is stored as part of the design object. When you deploy a design object to a new environment through a package:

  • MCP configuration travels with the object. If the target environment has Appian MCP Server enabled, the tool becomes available automatically.
  • Changes appear in Compare and Deploy. MCP-related configuration changes are visible during deployment review.
  • Disabled target environments preserve configuration. If Appian MCP Server is disabled in the target environment, the MCP tool configuration is preserved but inactive. The tool becomes available automatically when Appian MCP Server is enabled.

For more details on deployment, see Deploy MCP Tool Configurations.

Feedback