Unity MCP Efficient
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| UNITY_MCP_RESULT_DB | No | SQLite result store path; use 'memory' for process-local storage. Defaults to OS user cache directory. | |
| UNITY_MCP_BACKEND_URL | No | Upstream MCP for Unity HTTP endpoint | http://127.0.0.1:8080/mcp |
| UNITY_MCP_OPERATION_TIMEOUT | No | Per-operation timeout in seconds | 60 |
| UNITY_MCP_EFFICIENT_TRANSPORT | No | Facade transport: stdio, http, or sse | stdio |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_capabilitiesC | Find operation names and only the argument hints needed next. |
| call_operationB | Execute once; request_id safely deduplicates retries of mutations. |
| get_resultB | Page, select, or search a prior result without repeating Unity work. |
| batch_operationsB | Run calls or local select/assert/poll/foreach/emit workflow steps. |
| inspect_unityC | Inspect Unity semantically; unchanged revisions return no repeated payload. |
| get_viewportB | Return one bounded inline viewport image for visual verification. |
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 6 tools
Each tool targets a distinct phase of interaction: discovery, execution, result retrieval, batching, semantic inspection, and visual verification. There is no meaningful overlap that would cause an agent to misselect between them.
All tool names follow a consistent verb_noun snake_case pattern: search_, call_, get_, batch_, inspect_, get_. This makes the set predictable and easy to navigate.
Six tools is a well-scoped count for an efficiency-focused server. Each tool earns its place and the set avoids both bloat and thinness.
The surface covers the main lifecycle well: discover capabilities, execute operations, retrieve results, batch workflows, inspect Unity state, and verify visually. Minor gaps exist, such as no explicit cancellation or full listing tool, but search_capabilities and batch_operations cover most practical needs.