Workday Studio MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| STUDIO_WORKSPACE_PATH | Yes | Absolute path to the Studio workspace folder containing your Studio projects (the same folder Eclipse opens). Alternatively, set workspace_path in config.json. |
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 |
|---|---|
| list_studio_projectsA | List all Workday Studio integration projects in the Eclipse workspace. Returns project names, paths, last modified times, and transform counts. |
| list_project_filesB | List all integration files in a specific Studio project. Focuses on ws/WSAR-INF/ where transforms and assembly files live. |
| read_integration_fileA | Read the content of a specific file in a Studio project. Use list_project_files first to find the correct path. |
| write_integration_fileA | Write or update a file in a Studio project. Validates XML well-formedness before writing. Creates a .bak backup by default. |
| search_studio_filesA | Full-text search across Studio project files. Searches line-by-line for a plain string (case-insensitive). Useful for finding where a specific Workday field, function, or namespace is used. |
| get_workspace_structureA | Get the directory tree of the workspace or a specific project. Useful for understanding the layout before reading files. |
| validate_xml_fileB | Validate an XML or XSLT file for well-formedness. Returns any parse errors with line/column numbers. |
| create_studio_projectA | Scaffold a new empty Workday Studio integration project in the Eclipse workspace. Creates the full project directory structure (.project, .classpath, .settings/, ws/WSAR-INF/) with a blank assembly.xml ready to open in Studio. |
| create_xsl_transformA | Scaffold a new blank XSLT 2.0 transform file in a project's ws/WSAR-INF/ directory. Creates the file with the correct Workday namespace declarations and a stub root template ready to edit. |
| create_peci_transformA | Generate an XSLT 2.0 transform that flattens Workday PECI (or PICOF) output into a delimited or fixed-width vendor file, written to ws/WSAR-INF/ of a Studio project. Use it for payroll, benefits, retirement or other vendor feeds built on the PECI/PICOF connectors. Call analyze_peci_output on a sample file first to discover the exact element paths and change flags in the tenant's output, then pass those paths as columns. Handles: namespace declarations, RFC 4180 CSV quoting, any delimiter, header row, CRLF/LF, fixed-width padding and truncation, date re-formatting, first-non-blank fallback chains, constants, event-code filters (HIR, TERM, DTA...), and change-only rows (peci:isAdded / isUpdated / isDeleted flags). See get_patterns topic "PECI and PICOF Output Transforms" for the design rules. |
| copy_file_from_projectB | Copy a file (typically an XSL transform) from one Studio project into another. The most common starting point when building a new integration based on an existing pattern. |
| rename_fileA | Rename a file within a Studio project. Cannot rename assembly.xml, assembly-diagram.xml, .project, or .classpath. |
| delete_fileA | Delete a file from a Studio project. Creates a .bak backup before deleting by default. Cannot delete assembly.xml, assembly-diagram.xml, .project, or .classpath. |
| list_assembly_stepsA | Parse assembly.xml and return all steps with their IDs, types, and routing. Much faster than reading the full file when you just need to understand the integration flow. |
| list_integration_paramsA | Parse assembly.xml and return the launch parameters and integration attributes defined on the StartHere (cc:workday-in) element. Use this to map requirements to the param/attribute list without reading the full assembly. |
| add_assembly_stepA | Insert a new step into assembly.xml. Optionally wire it after an existing step (updates the predecessor's routes-to automatically). The new step inherits the predecessor's original routes-to as its own routes-to. |
| get_step_type_referenceA | Returns documentation and XML examples for Workday Studio assembly step types. Use this before writing or modifying assembly.xml to get the correct XML schema for each step type. |
| lookup_soap_operationsA | Look up Workday SOAP web service operations for use in cc:workday-out-soap steps. Returns the valid application name, common operations, WSDL URL, and notes for a given service. Use this before writing a cc:workday-out-soap step to confirm the correct application name and what operations are available. Pass service_name="list" to see all 37 services grouped by category. |
| get_patternsA | Serves the curated Studio knowledge base (docs/studio-integration-patterns.md) — hard-won cross-integration patterns that are NOT tied to a single step type. CALL THIS PROACTIVELY before: • hand-editing assembly-diagram.xml (swimlanes, @mixed EMF XPath indices, adding/removing/renaming diagram nodes, send-error placement) — the "Diagram Rules" section is the single largest body of gotchas and every rule prevents a scala.MatchError crash on diagram open • writing MVEL, XSLT, RAAS, outbound-HTTP, or document-storage logic • diagnosing a server log or a Common Error get_step_type_reference covers a SINGLE element; get_patterns covers the cross-cutting rules that span elements (diagram index math, swimlane layout, the three-entry add/remove rule, the verification script, MVEL idioms, etc.). USAGE: • No arguments → an index of every section and subsection (titles only). Start here, then drill in. • topic="Diagram Rules" → the full section (## or ### heading, partial match ok, case-insensitive). • topic="Insertion shift rule" → a single subsection. • search="swimlane" → every subsection whose heading or body mentions the term. |
| plan_integrationA | ⚠️ DO NOT CALL THIS TOOL without first gathering ALL design decisions from the user. Design questions you MUST ask before calling:
Once you have all answers, call with project_name + sub_flows + design_brief. The tool writes assembly.xml + assembly-diagram.xml with correct declarations pre-populated. |
| get_workflowA | Reports where an integration stands in its build lifecycle, and what to do next. CALL THIS FIRST when picking up an integration you did not just scaffold — it answers "what is done, what is still a stub, and what should I do now?" without reading the XML. THE LIFECYCLE (this MCP covers the first two phases):
State is read from /aidlc-docs/state.json, written by plan_integration and kept current by update_sub_flow and validate_assembly. If a project has no aidlc-docs/ (it predates the convention, or was built by hand), call again with retrofit=true to derive one from the existing assembly. Retrofit records only what the assembly proves — sub-flows and which are still TODO stubs. It marks the design brief as unrecorded rather than inventing one. |
| update_sub_flowA | Replaces the cc:steps body of a named sub-flow in assembly.xml. Use this to fill in a TODO stub generated by plan_integration. Finds <cc:async-mediation id="Do{sub_flow_id}"> and replaces its cc:steps content with steps_xml. Everything else on the async-mediation is preserved: routes-to, handle-downstream-errors, and the trailing cc:send-error. steps_xml format:
TOP-LEVEL ELEMENTS WARNING (Studio schema rule confirmed in multiple production builds): The following elements CANNOT appear inside steps_xml — they MUST be top-level elements placed directly inside cc:assembly, not inside cc:steps:
A .bak backup is written before every change. XML well-formedness is validated before the write is committed. To also change the routes-to on the async-mediation itself (e.g. from "EndGetWorkers" to "Splitter"), use write_integration_file for a full rewrite. |
| validate_assemblyA | Validates assembly.xml (and assembly-diagram.xml if present) against Studio-specific rules. assembly.xml checks: ERROR — XML comments present (shifts @mixed indices, breaks diagram connections) ERROR — Broken routes-to / routes-response-to (target id does not exist) ERROR — cc:workday-out-soap missing application= or version= ERROR — cc:workday-out-soap used for RAAS (must use cc:workday-out-rest) ERROR — cc:workday-out-rest missing extra-path= ERROR — cc:http-out missing endpoint= ERROR — cc:xslt-plus missing url= WARNING — vm:// endpoint references a local-in id that does not exist WARNING — url= references an XSL file not found in WSAR-INF INFO — TODO stubs still present (sub-flows not yet filled in) assembly-diagram.xml checks (when diagram file exists): ERROR — diagram href="assembly.xml#Id" points to an id no longer in assembly.xml (stale reference from a rename or delete — causes scala.MatchError on open) WARNING — renderable assembly element has no diagram entry (missing from visualProperties) Run this after update_sub_flow, any manual assembly edit, or any component rename/delete. Fix all ERRORs before opening in Studio. WARNINGs block testing, not diagram load. |
| rename_stepsA | Atomically renames a step ID in BOTH assembly.xml AND assembly-diagram.xml. WHY THIS EXISTS: Renaming an ID in only one file causes a scala.MatchError crash when Studio opens the diagram. This tool updates all references in a single operation: assembly.xml — id="OldID", routes-to="OldID", routes-response-to="OldID", endpoint vm:// paths containing /OldID assembly-diagram.xml — all href="assembly.xml#OldID" forms (visualProperties, connections source/target, swimlane elements) SAFE TO USE FOR: cc:async-mediation, cc:local-in, cc:local-out, cc:route, cc:splitter, cc:send-error, cc:workday-out-*, cc:http-out, cc:workday-in, and any other element with an id= attribute. Creates backups of both files before writing. Runs validate_assembly after. BATCH RENAMES: call once per ID — do not batch multiple renames into one call. |
| delete_assembly_stepA | Atomically deletes a step from BOTH assembly.xml AND assembly-diagram.xml. WHY THIS EXISTS: Removing an element from assembly.xml alone leaves dangling diagram href references (element/source/target/elements), which crash Studio with scala.MatchError when the diagram opens. This tool mirrors the removal across both files in a single operation: assembly.xml — the element block itself (self-closing or paired tag) assembly-diagram.xml — the visualProperties block wrapping the element href, every connections block whose source OR target points at the deleted step (by id OR by @mixed positional ref), and swimlane elements membership lines For a TOP-LEVEL element it also re-numbers all higher @mixed positional indices in the diagram by -2 (removing one element plus its preceding whitespace shifts every subsequent EMF XPath index down by two). SAFETY: Refuses to delete a step that other steps still route to (routes-to, routes-response-to, or a vm:// endpoint naming a cc:local-in) unless force=true — rewire or delete the callers first, or pass force and fix the reported references afterwards. Creates backups of both files before writing. Runs validate_assembly after. BATCH DELETES: call once per step ID — do not batch multiple deletes into one call. |
| parse_server_logA | Parses a Workday server log (server-{eventId}.log) and returns a focused summary: integration status, duration, deduplicated errors/warnings, execution timeline, and any XSLT cc:log messages. The raw log is 10-15k lines of framework boilerplate and XML config dumps (which contain plaintext credentials and are never surfaced). This tool extracts the signal and suppresses the noise. If log_path is omitted, searches ~/Downloads for the most recently modified server-*.log file. |
| analyze_peci_outputA | Inventory a sample Workday PECI or PICOF output XML file (downloaded from an integration event and saved in the project) before writing or changing its XSLT. Returns: detected connector type and namespace, worker and effective-change counts, event code distribution, and every element path with its occurrence count, change-flag counts (isAdded / isUpdated / isDeleted / priorValue) and a ready-to-use XPath relative to peci:Effective_Change or peci:Worker — feed those straight into create_peci_transform. Values are MASKED by default because these files contain employee PII. Set show_sample_values=true only for test-tenant data. |
| log_learningA | CALL THIS AUTOMATICALLY whenever you discover a new Workday Studio pattern, schema rule, gotcha, or workaround during a build session — even if the user did not ask you to log it. This is how the team's shared knowledge base grows. Examples of when to call this: a build fails with an error not already in the step-type reference, Studio silently rejects an element, MVEL throws an unexpected exception, a diagram crashes on open, a workaround fixes something with no documented cause. Do NOT call it for things already documented in get_step_type_reference or docs/studio-integration-patterns.md. PUBLIC-REPO RULE — GENERALIZE EVERY FIELD: learnings.md is published in a public repository used across clients. Never include client integration IDs (use INT999), project names, tenant or environment names (use ), custom field names, or run/log identifiers. Describe provenance generically ("verified in a live run", "observed in a production build") — the technical pattern is the value, not where it came from. |
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 28 tools
Most tools map to distinct resources and actions (project ops, file ops, step ops, knowledge lookup, diagnostics), and the boundary between get_step_type_reference (single element) and get_patterns (cross-cutting rules) is spelled out explicitly. The remaining overlap is in the assembly-editing trio — write_integration_file, add_assembly_step, and update_sub_flow all mutate assembly.xml — and in validate_xml_file vs validate_assembly, but the descriptions give clear guidance on when each applies.
Every tool follows a verb_noun snake_case pattern (create_studio_project, read_integration_file, add_assembly_step, validate_assembly, rename_steps, parse_server_log). Resource scoping is signaled consistently through the noun (file vs step vs project). No camelCase or stylistic outliers.
28 tools is on the heavy side, though the surface spans several genuinely large sub-domains (project scaffolding, file management, assembly/diagram editing, curated knowledge base, log and PECI analysis). A few tools feel like they could collapse into a smaller set — e.g. rename_file/delete_file vs rename_steps/delete_assembly_step, and three separate assembly mutation entry points.
The lifecycle is well covered: scaffold, read/write files, add/rename/delete steps with diagram synchronization, validate, inspect state, and diagnose logs. Gaps are minor — no tool to delete or archive a Studio project, no backup restore/undo, and parameters are only listed, never added or edited outside of plan_integration.