Pega MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Pega MCP Server show me the details and available actions for case C-501"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pega-mcp-server
Generic TypeScript MCP server for Pega case operations with definition-driven tool registration.
Purpose
This project provides an MCP tool layer for reading and mutating cases in a flexible way. Tool wiring is metadata-based, so adding tools does not require editing server registration logic.
Related MCP server: CaseMargin MCP Server
Supported MCP Tools
pega.get_casesInput: optional
limitReturns:
{ ok: true, data: { cases: [...] } }
pega.get_caseInput:
caseId, optionalviewType,pageName,originChannelReturns:
{ ok: true, data: { case: ... } }
pega.get_case_actionsInput:
caseId, optionaloriginChannelReturns:
{ ok: true, data: { actions: ... } }
pega.get_case_viewsInput:
caseId,viewId, optionaloriginChannelReturns:
{ ok: true, data: { view: ... } }
pega.attach_document_to_caseInput:
caseId,fileName,mimeType,fileContentBase64Returns:
{ ok: true, data: ... }
pega.submit_case_actionInput:
caseId,action, optionalcontentReturns:
{ ok: true, data: ... }
All tools return a standard failure format:
{
"ok": false,
"error": {
"code": "INVALID_INPUT | NOT_FOUND_OR_FORBIDDEN | INTERNAL_ERROR",
"message": "Human-readable explanation",
"suggestion": "Optional recovery guidance"
}
}Environment Variables
Required:
PEGA_BASE_URL(for examplehttps://your-pega-instance.example.com/prweb)PEGA_CLIENT_IDPEGA_CLIENT_SECRETPEGA_TOKEN_URL(for examplehttps://your-pega-instance.example.com/prweb/PRRestService/oauth2/v1/token)
Optional:
PEGA_CASES_API_BASE_PATH(default:/api/v1)Common v2 path when base URL includes
/prweb:/api/application/v2Some deployments use app context:
/PRAuth/app/work-manager/api/application/v2
PEGA_CASES_LIST_DATA_VIEW(default:D_pyMyWorkList)Used as a fallback for
pega.get_caseswhenGET /casesis not supported (HTTP 405)Endpoint shape:
POST <PEGA_CASES_API_BASE_PATH>/data_views/<dataViewId>
PEGA_ENABLED_TOOLScomma-separated tool names to allowlistExample:
pega.get_case,pega.get_case_actions
PEGA_DISABLED_TOOLScomma-separated tool names to blocklistExample:
pega.submit_case_action,pega.attach_document_to_case
Run Locally
npm install
cp .env.example .env
npm run devBuild
npm run build
npm startTest
npm testExample Outputs
pega.get_cases
{
"ok": true,
"data": {
"cases": [
{
"ID": "C-501",
"caseType": "Insurance Claim",
"status": "Pending Documents"
}
]
}
}pega.get_case
{
"ok": true,
"data": {
"case": {
"ID": "C-501",
"caseType": "Insurance Claim",
"status": "Pending Documents",
"uiResources": {
"root": {
"type": "page"
}
}
}
}
}Detailed request/response contracts:
Available Tools
6 toolspega.attach_document_to_caseAttach Document To CaseA
Use this tool to attach files or URLs to an existing case. Required input: caseId. Attachment input mode 1: attachments array payload. Attachment input mode 2: fileName + fileContentBase64 (optional mimeType) for upload-then-attach flow. Returns: { ok: true, data: } on success. Standard failure format: { ok: false, error: { code, message, suggestion? } }.
Inputs: caseId (required), attachments, fileName, mimeType, +2 more.
pega.get_caseGet CaseA
Use this tool to fetch one case by identifier. Required input: caseId. Optional inputs: viewType, pageName, originChannel. Constraint: pageName requires viewType. Returns: { ok: true, data: { case: } } on success. Standard failure format: { ok: false, error: { code, message, suggestion? } }.
Inputs: caseId (required), viewType, pageName, originChannel.
pega.get_case_actionsGet Case ActionsA
Use this tool to discover available actions for a case or fetch a specific action definition. Required input: caseId. Optional inputs: actionId, viewType, excludeAdditionalActions, originChannel. Returns: { ok: true, data: { actions: } } on success. Standard failure format: { ok: false, error: { code, message, suggestion? } }.
Inputs: caseId (required), actionId, viewType, excludeAdditionalActions, +1 more.
pega.get_casesGet CasesB
Use this tool to list cases. Optional input: limit. Returns: { ok: true, data: { cases: [...] } } on success. Standard failure format: { ok: false, error: { code, message, suggestion? } }.
Inputs: limit.
pega.get_case_viewsGet Case ViewsA
Use this tool to retrieve metadata for a specific case view. Required inputs: caseId, viewId. Optional input: originChannel. Returns: { ok: true, data: { view: } } on success. Standard failure format: { ok: false, error: { code, message, suggestion? } }.
Inputs: caseId (required), viewId (required), originChannel.
pega.submit_case_actionSubmit Case ActionB
Use this tool to execute an action on an existing case. Required inputs: caseId, action. Optional inputs: content, pageInstructions, attachments, eTag, viewType, pageName, originChannel. Returns: { ok: true, data: } on success. Standard failure format: { ok: false, error: { code, message, suggestion? } }.
Inputs: caseId (required), action (required), eTag, content, +5 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: attaching documents, fetching a single case, discovering actions, listing cases, retrieving view metadata, and submitting actions. The descriptions clearly differentiate between case retrieval, action management, and document handling functions.
All tools follow a perfect verb_noun pattern with consistent snake_case naming: attach_document_to_case, get_case, get_case_actions, get_cases, get_case_views, and submit_case_action. The naming convention is predictable and follows the same structure throughout.
Six tools is well-scoped for a case management system, covering core operations like CRUD for cases, action discovery/execution, document attachment, and view retrieval. Each tool earns its place without being overwhelming or insufficient.
The toolset provides excellent coverage for case lifecycle management with get/create/update (via submit_action) operations, action discovery/execution, and document attachment. Minor gaps include no explicit case creation tool (though submit_action might cover this) and no case deletion capability, but agents can work around these limitations.
Related MCP Connectors
Manage tickets, run agents and workflows, query tables, and search workspace knowledge.
Governed retail, FMCG, and CPG operational tools: runs, cases, approvals, audit-ready execution.
Every Canopy public API operation as a tool, run as you after a browser sign-in or on an API key.
17 pay-per-call web, finance, legal and onchain tools for AI agents. USDC on Base via x402/MPP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables interaction with Salesforce data and services via custom MCP tools, including account analytics, opportunity queries, case creation, and AI agent invocation.4-

CaseMargin MCP Serverofficial
AlicenseAqualityCmaintenanceExposes support case reasoning tools — generate structured case briefs and check escalation readiness from any MCP-compatible AI client.276 npm1MIT- FlicenseNot gradedqualityDmaintenanceEnables AI agents to retrieve customer, order, ticket, policy, and agreement information, and to prepare or execute state-changing support actions like escalations and follow-ups with confirmation and access control.-
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to manage SAP Sales Cloud V2 cases through MCP tools, supporting listing, retrieving, creating, and updating case records.-