{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-yepcode","slug":"yepcode","name":"YepCode","type":"mcp","url":"https://github.com/yepcode/mcp-server-js","page_url":"https://unfragile.ai/yepcode","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-yepcode__cap_0","uri":"capability://tool.use.integration.mcp.protocol.compliant.tool.exposure.for.yepcode.infrastructure","name":"mcp protocol-compliant tool exposure for yepcode infrastructure","description":"Implements the Model Context Protocol (MCP) specification via the YepCodeMcpServer class in src/server.ts, acting as a bridge that translates YepCode's cloud capabilities into standardized MCP tools consumable by AI platforms. The server maintains strict type safety through Zod schema validation and routes incoming MCP requests to appropriate tool handlers organized into five distinct categories: storage, environment variables, code execution, process execution, and dynamically discovered processes. This enables AI assistants like Claude Desktop or Cursor IDE to invoke YepCode operations through a unified, protocol-compliant interface.","intents":["Connect Claude Desktop or other MCP-compatible AI platforms to YepCode's sandbox infrastructure","Expose YepCode capabilities as standardized tools that AI systems can discover and invoke","Enable AI assistants to execute code, manage files, and control environment variables through MCP","Integrate YepCode processes into AI agent workflows via MCP tool definitions"],"best_for":["AI platform developers integrating YepCode as a backend execution environment","Teams building AI agents that need secure, sandboxed code execution capabilities","Claude Desktop and Cursor IDE users wanting YepCode integration"],"limitations":["Requires YEPCODE_API_TOKEN for authentication — cannot operate without valid credentials","MCP protocol overhead adds latency to each tool invocation compared to direct API calls","Tool discovery is static for built-in tools; dynamic process discovery happens at runtime only","No built-in request queuing or rate limiting — relies on upstream MCP client behavior"],"requires":["Node.js 18+ runtime","Valid YepCode API token (sk-c2E...RD format)","@modelcontextprotocol/sdk ^1.17.0","MCP-compatible AI platform (Claude Desktop, Cursor, or custom MCP client)"],"input_types":["MCP tool call requests with JSON-serialized parameters","Zod-validated schema objects for each tool category"],"output_types":["MCP tool result responses with structured JSON","Error responses with MCP-compliant error codes"],"categories":["tool-use-integration","mcp-server"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_1","uri":"capability://code.generation.editing.secure.sandboxed.code.execution.with.javascript.and.python.support","name":"secure sandboxed code execution with javascript and python support","description":"Exposes YepCode's cloud-based sandbox runtime through the run-code-tool-definitions.ts module, allowing AI systems to execute arbitrary JavaScript or Python code in an isolated, secure environment. The implementation leverages the @yepcode/run package to handle runtime isolation, package management (NPM and PyPI), and execution lifecycle. Code execution requests are validated through Zod schemas before being dispatched to YepCode's infrastructure, which manages resource limits, timeout enforcement, and output capture. This enables AI agents to execute generated code without exposing the host system to security risks.","intents":["Execute LLM-generated JavaScript or Python code in a secure, isolated sandbox","Allow AI agents to run code with access to NPM and PyPI packages without host system risk","Capture and return code execution output (stdout, stderr, return values) to the AI system","Enforce execution timeouts and resource limits on untrusted code"],"best_for":["AI agents that need to execute generated code as part of reasoning or task completion","Teams building code-generation workflows that require safe execution validation","Developers integrating YepCode as a backend for AI-powered code execution platforms"],"limitations":["Execution latency depends on YepCode infrastructure availability and network round-trip time","No direct access to host filesystem — sandboxed environment prevents file system operations outside YepCode storage","Timeout and resource limits are enforced by YepCode backend, not configurable per-request through MCP","Output capture limited to stdout/stderr; binary or streaming output not supported"],"requires":["Valid YEPCODE_API_TOKEN for authentication","Node.js 18+ for the MCP server itself","YepCode cloud account with active sandbox capacity","@yepcode/run ^1.8.0 package"],"input_types":["JavaScript code as string","Python code as string","Optional package dependencies (npm/pypi format)"],"output_types":["Execution result object with stdout, stderr, return value","Error messages with stack traces","Execution metadata (duration, status)"],"categories":["code-generation-editing","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_2","uri":"capability://data.processing.analysis.file.storage.management.through.mcp.tools","name":"file storage management through mcp tools","description":"Implements file operations (create, read, update, delete, list) through the storage-tool-definitions.ts module, exposing YepCode's file storage as MCP tools. Each storage operation is validated through Zod schemas and routed through the YepCodeMcpServer to YepCode's backend storage service. This allows AI systems to persist data, manage configuration files, and organize code artifacts within the YepCode workspace without requiring direct filesystem access. The tool definitions include metadata about supported operations and parameter constraints.","intents":["Persist generated code, configuration, or data artifacts in YepCode workspace storage","Read previously stored files to provide context for subsequent AI operations","Manage file organization (create directories, list contents) within YepCode workspace","Update or delete stored files as part of AI-driven workflows"],"best_for":["AI agents that need persistent storage for generated artifacts across multiple invocations","Teams building code generation or data processing workflows with YepCode","Developers integrating YepCode as a backend for AI-powered file management"],"limitations":["Storage operations are asynchronous and subject to YepCode backend latency","No built-in versioning or rollback — overwrites are permanent unless manually managed","File size limits enforced by YepCode backend (not documented in MCP layer)","No direct filesystem path access — all operations must go through YepCode storage abstraction"],"requires":["Valid YEPCODE_API_TOKEN for authentication","YepCode workspace with active storage quota","Node.js 18+ for MCP server"],"input_types":["File path (string)","File content (string or binary)","Directory path for listing operations"],"output_types":["File content (string or binary)","File metadata (size, created/modified timestamps)","Directory listing with file metadata","Operation status (success/failure)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_3","uri":"capability://automation.workflow.environment.variable.management.with.workspace.isolation","name":"environment variable management with workspace isolation","description":"Manages workspace environment variables through the env-vars-tool-definitions.ts module, allowing AI systems to read, set, and delete environment variables within the YepCode workspace scope. Variables are stored in YepCode's backend and validated through Zod schemas before being applied. This enables AI agents to configure runtime behavior, manage secrets (with appropriate security considerations), and pass data between code execution invocations without exposing variables to the host system. The implementation maintains strict workspace isolation — variables are scoped to the authenticated workspace only.","intents":["Configure environment variables for code execution without exposing them to the host system","Store and retrieve configuration values (API keys, database URLs, feature flags) within YepCode workspace","Pass data between multiple code execution invocations through persistent environment state","Allow AI agents to dynamically adjust runtime configuration based on execution results"],"best_for":["AI agents executing code that requires configuration or secrets management","Teams building multi-step workflows where environment state must persist across invocations","Developers integrating YepCode as a backend for AI-powered automation platforms"],"limitations":["Variables are stored in YepCode backend, not encrypted at rest (security depends on YepCode infrastructure)","No built-in secret rotation or expiration — manual management required","Environment variable changes are asynchronous and may have propagation delay to code execution","No audit logging of variable access or modification through MCP layer"],"requires":["Valid YEPCODE_API_TOKEN for authentication","YepCode workspace with environment variable storage enabled","Node.js 18+ for MCP server"],"input_types":["Variable name (string)","Variable value (string)","Variable key for deletion operations"],"output_types":["Variable value (string)","List of all environment variables (names only, values redacted for security)","Operation status (success/failure)"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_4","uri":"capability://tool.use.integration.dynamic.mcp.tool.generation.from.yepcode.processes","name":"dynamic mcp tool generation from yepcode processes","description":"Automatically discovers and generates MCP tool definitions from tagged YepCode processes at runtime through the get-execution-tool-definition.ts module. The YepCodeMcpServer scans the authenticated workspace for processes marked with specific tags and dynamically creates tool definitions that expose those processes as invocable MCP tools. Each generated tool includes parameter schemas derived from the process definition, enabling AI systems to discover and invoke custom YepCode processes without requiring manual tool registration. This pattern allows users to extend YepCode capabilities by creating processes that are automatically exposed to AI systems.","intents":["Expose custom YepCode processes as discoverable MCP tools without manual registration","Allow AI systems to invoke user-defined YepCode processes as part of agent workflows","Enable dynamic tool discovery — new processes become available to AI systems automatically","Create reusable, parameterized workflows that AI agents can invoke with different inputs"],"best_for":["Teams building custom YepCode processes that should be accessible to AI agents","Developers extending YepCode with domain-specific automation that AI systems should discover","Organizations wanting to expose internal YepCode workflows to AI-powered applications"],"limitations":["Process discovery happens at MCP server startup — new processes require server restart to be discovered","Parameter schema generation depends on process definition completeness — poorly defined processes may generate incomplete tool schemas","No built-in versioning for process tools — breaking changes to process signatures may break AI agent workflows","Tool naming and documentation depend on YepCode process metadata — inconsistent metadata leads to poor AI discoverability"],"requires":["Valid YEPCODE_API_TOKEN for authentication","YepCode processes created and tagged in the workspace","Process definitions must include parameter schemas for tool generation","Node.js 18+ for MCP server"],"input_types":["Process parameters as defined in YepCode process schema","Input data matching process parameter types"],"output_types":["Process execution result","Output data as defined in process schema","Execution metadata (duration, status)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_5","uri":"capability://automation.workflow.multi.deployment.model.support.local.remote.docker","name":"multi-deployment model support (local, remote, docker)","description":"Supports multiple deployment patterns through configuration options in README.md and package.json entry points, enabling the MCP server to run as a local Node.js process, remote HTTP service, or containerized Docker deployment. The server can be configured via environment variables (YEPCODE_API_TOKEN, YEPCODE_MCP_OPTIONS) and URL query parameters for remote deployments. This flexibility allows teams to integrate YepCode into different AI platform architectures — Claude Desktop uses local stdio transport, while custom platforms may use HTTP or other transport mechanisms. The implementation maintains consistent tool behavior across all deployment models.","intents":["Deploy YepCode MCP server locally for Claude Desktop integration","Run YepCode MCP server as a remote HTTP service for custom AI platform integration","Containerize YepCode MCP server for Kubernetes or cloud deployment","Configure server behavior through environment variables without code changes"],"best_for":["Teams integrating YepCode with Claude Desktop (local deployment)","Organizations building custom AI platforms requiring remote MCP server","DevOps teams deploying YepCode MCP in containerized environments","Developers needing flexible deployment options for different use cases"],"limitations":["Local deployment requires Node.js 18+ on the client machine","Remote deployment requires network connectivity and introduces latency compared to local execution","Docker deployment requires container orchestration knowledge and infrastructure","Configuration through environment variables may be insufficient for complex deployment scenarios"],"requires":["Node.js 18+ for local/remote deployment","Docker and container runtime for Docker deployment","Valid YEPCODE_API_TOKEN environment variable","Network connectivity for remote deployments"],"input_types":["Environment variables (YEPCODE_API_TOKEN, YEPCODE_MCP_OPTIONS)","URL query parameters for remote configuration","Docker environment variables and volume mounts"],"output_types":["MCP server process (stdio for local, HTTP for remote)","Docker container with running MCP server"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_6","uri":"capability://safety.moderation.zod.schema.based.request.validation.and.type.safety","name":"zod schema-based request validation and type safety","description":"Enforces strict type safety across all MCP tool invocations through Zod schema validation in src/types.ts and individual tool definition files. Every incoming MCP request is validated against its corresponding Zod schema before being dispatched to YepCode infrastructure, preventing malformed requests from reaching the backend. The type system is defined in TypeScript with Zod runtime validation, providing both compile-time type checking and runtime safety. This approach catches invalid inputs early and provides clear error messages to AI systems when requests don't match expected schemas.","intents":["Validate all MCP tool parameters before execution to prevent invalid requests","Provide clear error messages when AI systems invoke tools with incorrect parameters","Ensure type safety across the MCP server implementation","Enable automatic schema generation for MCP tool discovery"],"best_for":["Teams building robust MCP servers that need strict input validation","Developers integrating YepCode where parameter validation is critical","Organizations requiring type-safe AI tool integration"],"limitations":["Zod validation adds ~5-10ms overhead per tool invocation","Schema validation errors may be opaque to AI systems if error messages aren't well-designed","Complex nested schemas may be difficult for AI systems to understand from schema alone"],"requires":["zod ^3.24.2 package","TypeScript 4.5+ for type checking","Node.js 18+ runtime"],"input_types":["JSON-serialized MCP tool parameters","Zod schema definitions"],"output_types":["Validated parameter objects","Zod validation errors with field-level details"],"categories":["safety-moderation","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_7","uri":"capability://safety.moderation.structured.error.handling.with.mcp.compliant.error.codes","name":"structured error handling with mcp-compliant error codes","description":"Implements structured error handling throughout the MCP server that returns MCP-compliant error codes and messages when tool invocations fail. The error handling strategy is defined in src/server.ts and applied consistently across all tool categories. Errors from YepCode backend operations are caught, transformed into MCP error responses with appropriate error codes, and returned to the AI system with context about what failed. This enables AI systems to understand and potentially recover from errors rather than receiving opaque failure messages.","intents":["Return structured error responses that AI systems can interpret and act upon","Provide context about why tool invocations failed (authentication, validation, backend errors)","Enable AI agents to implement error recovery strategies based on error codes","Debug integration issues by providing detailed error information"],"best_for":["Teams building AI agents that need to handle tool invocation failures gracefully","Developers debugging YepCode MCP integration issues","Organizations requiring reliable error reporting from AI tool invocations"],"limitations":["Error messages may expose internal YepCode implementation details if not carefully sanitized","AI systems may not understand all MCP error codes without documentation","Backend errors may be difficult to diagnose if YepCode doesn't provide detailed error context"],"requires":["@modelcontextprotocol/sdk ^1.17.0 for MCP error code definitions","Node.js 18+ runtime"],"input_types":["Errors from YepCode backend operations","Validation errors from Zod schemas"],"output_types":["MCP error responses with error codes","Error messages with context about the failure"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-yepcode__cap_8","uri":"capability://safety.moderation.api.token.authentication.with.workspace.scoping","name":"api token authentication with workspace scoping","description":"Implements authentication through YEPCODE_API_TOKEN environment variable that is validated when the YepCodeMcpServer initializes. The token (format: sk-c2E...RD) authenticates all requests to YepCode's infrastructure and scopes all operations to the authenticated workspace. The authentication is handled by the YepCodeApi, YepCodeRun, and YepCodeEnv service classes in src/server.ts, which use the token to establish authenticated connections to YepCode backend services. This ensures that all file storage, code execution, environment variables, and process invocations are scoped to the authenticated user's workspace.","intents":["Authenticate MCP server to YepCode infrastructure using API token","Scope all operations to the authenticated user's workspace","Prevent unauthorized access to YepCode resources","Enable multi-user deployments where each server instance uses different credentials"],"best_for":["Teams deploying YepCode MCP server in production environments","Organizations requiring workspace isolation between different AI systems","Developers integrating YepCode with security-sensitive applications"],"limitations":["API token must be stored in environment variables — no built-in secret management","Token rotation requires server restart — no dynamic credential refresh","No fine-grained access control — token grants access to all workspace resources","Token compromise exposes entire workspace to unauthorized access"],"requires":["Valid YepCode API token (obtainable from YepCode Settings > API credentials)","YEPCODE_API_TOKEN environment variable set before server startup","Network connectivity to YepCode infrastructure"],"input_types":["API token string (sk-c2E...RD format)"],"output_types":["Authenticated connection to YepCode services","Workspace-scoped access to all YepCode resources"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":30,"verified":false,"data_access_risk":"high","permissions":["Node.js 18+ runtime","Valid YepCode API token (sk-c2E...RD format)","@modelcontextprotocol/sdk ^1.17.0","MCP-compatible AI platform (Claude Desktop, Cursor, or custom MCP client)","Valid YEPCODE_API_TOKEN for authentication","Node.js 18+ for the MCP server itself","YepCode cloud account with active sandbox capacity","@yepcode/run ^1.8.0 package","YepCode workspace with active storage quota","Node.js 18+ for MCP server"],"failure_modes":["Requires YEPCODE_API_TOKEN for authentication — cannot operate without valid credentials","MCP protocol overhead adds latency to each tool invocation compared to direct API calls","Tool discovery is static for built-in tools; dynamic process discovery happens at runtime only","No built-in request queuing or rate limiting — relies on upstream MCP client behavior","Execution latency depends on YepCode infrastructure availability and network round-trip time","No direct access to host filesystem — sandboxed environment prevents file system operations outside YepCode storage","Timeout and resource limits are enforced by YepCode backend, not configurable per-request through MCP","Output capture limited to stdout/stderr; binary or streaming output not supported","Storage operations are asynchronous and subject to YepCode backend latency","No built-in versioning or rollback — overwrites are permanent unless manually managed","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.43,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:04.690Z","last_scraped_at":"2026-05-03T14:00:15.503Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=yepcode","compare_url":"https://unfragile.ai/compare?artifact=yepcode"}},"signature":"J4iCTBKqosVs9ZCC4R/zYmH9/KAHK35R/1RuZRktMlU9GhDiAbEkRJhJpxGmcSkyJfU3f4kJ3Z9Ne/hN5p+uBw==","signedAt":"2026-06-21T01:54:50.185Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/yepcode","artifact":"https://unfragile.ai/yepcode","verify":"https://unfragile.ai/api/v1/verify?slug=yepcode","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}