yukta / mcp
CLAUDE.md1 starsChanged 20 days agoApache-2.0View on GitHub
In this repository21 other files it gives its agents.
- architecture/CLAUDE.mdCLAUDE.md
- boot/CLAUDE.mdCLAUDE.md
- build-logic/CLAUDE.mdCLAUDE.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- cli/CLAUDE.mdCLAUDE.md
- core/CLAUDE.mdCLAUDE.md
- messaging/CLAUDE.mdCLAUDE.md
- plugin-api/CLAUDE.mdCLAUDE.md
- plugins/CLAUDE.mdCLAUDE.md
- plus/CLAUDE.mdCLAUDE.md
- ui/CLAUDE.mdCLAUDE.md
- web/CLAUDE.mdCLAUDE.md
- ide-index-mcpSkill
- pickupSkill
- playwrightSkill
- testsSkill
- ticketSkill
- yuktaSkill
- yukta-supervisorSkill
- yukta-workflowsSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 60
Every executionId-scoped tool verifies session ownership via ControlBusGateway.getProgress(sessionId, executionId) (ExecutionOwnership.
- Very specific: line 73
Follow the tiered "Test Execution Policy (speed)" in the root CLAUDE.md: run --tests for the classes you changed first.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
MCP Module CLAUDE.md
Overview
MCP server implementation and tool providers. Mirrors the functionality of the web REST
controllers as an agent-friendly MCP tool surface backed directly by core services
(no dependency on :web).
Build & Development Commands
# Run MCP tests
yk gradle :mcp:testTools (AppMcpTools)
- Sessions:
list_sessions,get_session_details,create_session,get_session_creation_instructions - Workflows:
get_workflow_details,start_workflow,get_workflow_status(WorkflowProgress snapshot),get_workflow_history,get_execution_logs(real logs fromPluginLogStore, regex filter + tail) - Control:
control_workflow(PAUSE/RESUME/STOP/STOP_ALL/RESTART/RESTART_FROM_NODE),control_node(PAUSE/RESUME/STOP/STEP/STEP_ENABLE/STEP_DISABLE) - Input requests (
InputProvider):list_pending_inputs(VIEWER; bounded: 50 entries, texts cut to 2000 characters),answer_inputandescalate_input(OPERATOR;sessionIdis required like every execution-scoped tool). Tool descriptions say that prompts and context are untrusted. - Notifications (
NotificationProvider):list_notifications(VIEWER; the caller's inbox, at most 50, bodies cut to 1000 characters) andmark_notifications_read(VIEWER; ids, orall). Both filter throughRecipients(a session-limited key needs nosessionId: the filter does the scoping) and return wrapper records; titles and bodies are untrusted. An action carries theexecutionIdandrequestIdforanswer_input. - Plugins:
list_plugins,get_plugin_details,list_ai_backends,get_plugin_creation_guide - Monitoring:
get_control_bus_status,get_metrics_snapshot(sampled meters plus per-scope run aggregates fromMetricsProvider)
Key Files
src/main/java/com/infenia/yukta/mcp/AppMcpTools.java:@McpToolfacade.src/main/java/com/infenia/yukta/mcp/AppMcpPrompts.java:@McpPrompttemplates.src/main/java/com/infenia/yukta/mcp/AppMcpResources.java:@McpResourceproviders.src/main/java/com/infenia/yukta/mcp/provider/: Backing implementations (workflow execution/control, logs, sessions, plugins, system health) delegating to core services (ControlBusGateway,WorkflowService,SessionService,PluginRegistry,PluginLogStore).src/main/java/com/infenia/yukta/mcp/dto/: MCP-owned response records (plain records, no swagger annotations). Core records (WorkflowProgress,WorkflowExecutionSummary,WorkflowDefinition) are returned directly where already clean.../docs/contributing/modules/mcp.mdx(module guide); open risks, bugs and review findings: GitHub issues labelledmcp(gh issue list -l mcp; risks also carryrisk); evolution path and quality lenses:../design/assessments/mcp.md.
Conventions & Gotchas
- Tool params use
@McpToolParam(required, description);@McpArgis only for@McpPromptarguments. - The server runs
type: ASYNC+protocol: STATELESS(configured inboot/src/main/resources/application*.yaml). Tools returnMono; blocking core calls are wrapped inMono.fromCallable(...).subscribeOn(Schedulers.boundedElastic()). - List-shaped tools MUST return
Mono<WrapperRecord>(e.g.SessionList,WorkflowHistory,PluginList), neverFlux<T>or bareMono<List<T>>: the async MCP tool callback truncates aFluxresult to its first element (fluxResult.next()), andgenerateOutputSchema = trueon aMono<List<T>>return type crashes server startup (Spring AI 2.0.0 passes null toClassUtils.isPrimitiveOrWrapperfor parameterized types). - A null in a tool result fails the call ("output validation failed") unless the schema allows it:
the server validates the result map against the generated output schema, which types a field as a
plain
string. Everydto/record carries@JsonInclude(JsonInclude.Include.NON_NULL)(a null is left out) and every component that can be null is@Nullable(so it is notrequired). A core record shared with the REST API uses@Schema(nullable = true) @Nullableinstead, which keeps the REST JSON as it is.ToolOutputSchemaTestchecks every@Nullablecomponent of every tool result. - Errors surface as
Mono.error(new IllegalArgumentException(...))with agent-actionable messages; the framework converts them toisErrortool results. - Every executionId-scoped tool verifies session ownership via
ControlBusGateway.getProgress(sessionId, executionId)(ExecutionOwnership; survives the tracker's index TTL); a missing execution and a foreign session yield the identical "Execution not found" error (mirrorsWorkflowController.executeControlSignal).
Tech Stack
- Spring AI MCP Server (WebFlux, Spring AI 2.0)
Imports
@.claude/rules/coding-standards.md @.claude/rules/git-workflow.md
Testing speed
Follow the tiered "Test Execution Policy (speed)" in the root CLAUDE.md: run --tests for the classes you changed first; full :mcp:test only when many files changed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

