ExD Accelerator MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ORG_ID | Yes | IMS Org ID (e.g., ...@AdobeOrg) | |
| CLIENT_ID | Yes | Adobe Developer Console: Client ID | |
| TENANT_ID | Yes | Tenant ID (e.g., acssandboxgdcthree) | |
| SANDBOX_NAME | Yes | Adobe Experience Platform sandbox name | |
| CLIENT_SECRET | Yes | Adobe Developer Console: Client Secret | |
| ITEM_CATALOG_ID | Yes | Decision catalog ID (e.g., xcore:decision-catalog:...) | |
| DECISIONING_SCHEMA_URI | Yes | Full URI of the decisioning schema (https://ns.adobe.com/...) | |
| DECISIONING_SCHEMA_ALT_ID | Yes | Alternate ID of the decisioning schema (e.g., _tenant.schemas.id) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| parse_csv_and_suggestA | Parse a product/offer CSV, infer XDM types for each column, and suggest schema fields, eligibility rules, and ranking formulas. Always call this first — no data is written. |
| create_offer_metadata_fieldgroupA | Create a new XDM fieldgroup from CSV column names and attach it to the ExD decisioning schema. Will check for an existing fieldgroup with the same name first. Requires confirmed: true to execute — previews first. |
| bulk_create_offersA | Bulk-create ExD offer items from CSV rows. Each row becomes one offer. Requires confirmed: true to execute — previews payloads first. Use dry_run: true to inspect full JSON payloads. |
| create_collectionA | Create an offer item collection with a filter constraint. Requires confirmed: true to execute. |
| create_eligibility_ruleC | Create a PQL eligibility rule for Experience Decisioning. Requires confirmed: true to execute. |
| create_ranking_formulaC | Create a ranking formula for Experience Decisioning. Requires confirmed: true to execute. |
| create_selection_strategyA | Wire a collection, eligibility rule, and ranking formula into a selection strategy. Requires confirmed: true to execute. |
| create_placementA | Create a channel placement for Experience Decisioning. Uses /exd-placements endpoint. Requires confirmed: true to execute. |
| get_offer_itemA | Look up a single offer item by its DPS ID. Read-only. |
| list_offer_itemsC | List all offer items in the ExD catalog with pagination. Read-only. |
| update_offer_itemC | Update fields on an existing offer item using JSON Patch operations. Requires confirmed: true to execute. |
| add_schema_fieldC | Add a single new field to an existing tenant fieldgroup. Requires confirmed: true to execute. |
| deprecate_schema_fieldA | Mark a custom tenant fieldgroup field as deprecated. The field remains but is flagged. For OOB Adobe fields use deprecate_oob_field. Requires confirmed: true to execute. |
| deprecate_oob_fieldA | Deprecate an OOB Adobe-managed field on the decisioning schema via a descriptor. Use for standard fields like itemDescription, itemName. For custom tenant fields use deprecate_schema_field. Requires confirmed: true. |
| detach_fieldgroupA | Safely remove a fieldgroup from the decisioning schema. Always shows a dry-run preview first. Requires confirmed: true to execute the removal. |
| get_setup_summaryA | Full read-only inventory of all ExD resources in the sandbox — offers, collections, rules, formulas, strategies, and placements. |
| lookup_decisioning_schemaB | Fetch the full resolved Personalized Offer Items decisioning schema — all fieldgroups, OOB fields, and custom tenant fields. Read-only. |
| list_schema_fieldgroupsB | List all tenant fieldgroups compatible with the Offer Item class. Read-only. |
| get_fieldgroupA | Fetch the full field definitions inside a specific fieldgroup by its altId. Read-only. |
| get_schema_audit_logB | Fetch the full audit log for the decisioning schema — every change ever made, newest first. Read-only. |
| list_schema_descriptorsC | List all descriptors on the decisioning schema — identity, deprecation, display name overrides, and relationships. Read-only. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 21 tools
Each tool targets a distinct resource and action, with clear separation between schema field operations, offer management, placement, rules, strategies, and CSV parsing. Even similar tools like deprecate_oob_field and deprecate_schema_field are explicitly differentiated by the type of field.
Tool names follow a consistent verb_noun pattern in snake_case, with verbs like create, get, list, update, deprecate, detach, parse, and bulk_create. The minor variation between get_, list_, and lookup_ is logically consistent with the cardinality of the result (single vs multiple).
At 21 tools, the count is slightly above the ideal 3-15 range, but the complexity of the ExD domain (schema management, multiple resource types, CSV parsing, auditing) justifies this number. Each tool serves a specific purpose without redundancy.
The tool set covers creation and reading for most resources, but lacks delete operations for offers, placements, rules, formulas, and strategies. Update is only available for offers. This leaves notable gaps that may require manual intervention or cause agent failures.