{"id":"isuzu-shiranui-unitymcp","name":"UnityMCP","homepage":"https://deepwiki.com/isuzu-shiranui/UnityMCP/1-overview","repo_url":"https://github.com/isuzu-shiranui/UnityMCP","category":"ai-ml","subcategories":[],"tags":["unity","mcp","model-context-protocol","csharp","typescript","editor-integration","tcp","ai-assistants"],"what_it_does":"UnityMCP provides an integration framework that connects an external AI client (via MCP) to a Unity Editor project. It includes a TypeScript MCP server/client component and a C# Unity Editor plugin that routes MCP tool/resource/prompt calls over TCP to Unity, where extensible command/resource handlers are auto-discovered and executed.","use_cases":["Let an MCP-capable assistant control Unity editor actions via tools (commands)","Expose Unity project/package/assembly information as MCP resources for analysis","Provide reusable prompt templates through MCP prompts (TypeScript side)","Build custom handler extensions for AI-assisted workflows in Unity"],"not_for":["Production deployments where security boundaries are unclear (e.g., untrusted handler/code execution)","Environments that require HTTPS-only or TLS-protected remote access to the server","Use cases needing REST/GraphQL/SDK-style HTTP APIs or webhooks"],"best_when":"You control the Unity project and network environment (local/dev usage) and want an MCP-to-Unity bridge with extensible handlers.","avoid_when":"You need hardened auth, encryption-in-transit, or you plan to load untrusted third-party handlers or enable code-execution capabilities without review.","alternatives":["Use direct Unity editor scripting (custom tool UIs) without MCP","Build a custom MCP server that talks to Unity via your own transport layer","Use Unity automation frameworks (e.g., editor scripting + RPC/HTTP) tailored to your assistant"],"af_score":55.5,"security_score":26.0,"reliability_score":27.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:43:57.067836+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication mechanism is described. Connection is configured by host/port and communicates over TCP; security appears to rely on network-level controls and user trust."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"MIT-licensed open source framework; README does not describe pricing."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":55.5,"security_score":26.0,"reliability_score":27.5,"mcp_server_quality":70.0,"documentation_accuracy":70.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":95.0,"rate_limit_clarity":0.0,"tls_enforcement":10.0,"auth_strength":15.0,"scope_granularity":0.0,"dependency_hygiene":55.0,"secret_handling":60.0,"security_notes":"TCP-based communication is configured with host/port and no authentication/TLS is described in the README. The project warns that sample code may include arbitrary code execution and that handlers with code_execute should be disabled or reviewed for production use. Additional risk: auto-discovery/loading of handlers increases the importance of only installing trusted handlers and restricting who can modify the codebase.","uptime_documented":0.0,"version_stability":45.0,"breaking_changes_history":30.0,"error_recovery":35.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Transport appears to be TCP between external Node/TypeScript component and Unity plugin; ensure correct host/port and firewall rules.","Handler discovery is automatic; mis-placed or incorrectly implemented handlers can result in missing tools/resources.","Some handlers may include code-execution capabilities (README warns about code_execute), which can be dangerous for autonomous agents."]}}