* Add support for multiple Unity instances
* fix port detection
* add missing unity_instance parameter
* add instance params for resources
* Fix CodeRabbit review feedback
- Fix partial framed response handling in port discovery
Add _recv_exact() helper to ensure complete frame reading
Prevents healthy Unity instances from being misidentified as offline
- Remove unused default_conn variables in server.py (2 files)
Fixes Ruff F841 lint error that would block CI/CD
- Preserve sync/async nature of resources in wrapper
Check if original function is coroutine before wrapping
Prevents 'dict object is not awaitable' runtime errors
- Fix reconnection to preserve instance_id
Add instance_id tracking to UnityConnection dataclass
Reconnection now targets the same Unity instance instead of any available one
Prevents operations from being applied to wrong project
- Add instance logging to manage_asset for debugging
Helps troubleshoot multi-instance scenarios
🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix CodeRabbit feedback: reconnection fallback and annotations safety
Address 3 CodeRabbit review comments:
1. Critical: Guard reconnection fallback to prevent wrong instance routing
- When instance_id is set but rediscovery fails, now raises ConnectionError
- Added 'from e' to preserve exception chain for better debugging
- Prevents silently connecting to different Unity instance
- Ensures multi-instance routing integrity
2. Minor: Guard __annotations__ access in resource registration
- Use getattr(func, '__annotations__', {}) instead of direct access
- Prevents AttributeError for functions without type hints
3. Minor: Remove unused get_type_hints import
- Clean up unused import in resources/__init__.py
All changes applied to both Server/ and MCPForUnity/ directories.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix instance sorting and logging issues
- Fix sorting logic for instances without heartbeat data: use epoch timestamp instead of current time to properly deprioritize instances with None last_heartbeat
- Use logger.exception() instead of logger.error() in disconnect_all() to include stack traces for better debugging
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* update uv.lock to prepare for merging into main
* Restore Python 3.10 lockfiles and package list_unity_instances tool
* Deduplicate Unity instance discovery by port
* Scope status-file reload checks to the active instance
* refactor: implement FastMCP middleware for session-based instance routing
Replaces module-level session_state.py with UnityInstanceMiddleware class
that follows FastMCP best practices. Middleware intercepts all tool calls
via on_call_tool hook and injects active Unity instance into request state.
Key changes:
- Add UnityInstanceMiddleware class with on_call_tool hook
- Tools now use ctx.get_state("unity_instance") instead of direct session_state calls
- Remove unity_instance parameter from all tool schemas to prevent LLM hallucination
- Convert list_unity_instances tool to unity_instances resource (read-only data)
- Update error messages to reference unity://instances resource
- Add set_state/get_state methods to DummyContext test helper
- All 67 tests passing (55 passed, 5 skipped, 7 xpassed)
Architecture benefits:
- Centralized session management in middleware
- Standard FastMCP patterns (middleware + request state)
- Cleaner separation of concerns
- Prevents AI hallucination of invalid instance IDs
* fix: convert resource templates to static resources for discoverability
Convert MCP resources from URI templates with query parameters to static
resources to fix discoverability in MCP clients like Claude Code.
Changes:
- Remove {?force_refresh} from unity://instances
- Remove {?unity_instance} from mcpforunity://menu-items
- Remove {?unity_instance} from mcpforunity://tests
- Keep {mode} path parameter in mcpforunity://tests/{mode} (legitimate)
Root cause: Query parameters {?param} trigger ResourceTemplate registration,
which are listed via resources/templates/list instead of resources/list.
Claude Code's ListMcpResourcesTool only queries resources/list, making
templates undiscoverable.
Solution: Remove optional query parameters from URIs. Instance routing is
handled by middleware/context, and force_refresh was cache control that
doesn't belong in resource identity.
Impact: Resources now discoverable via standard resources/list endpoint and
work with all MCP clients including Claude Code and Cursor.
Requires FastMCP >=2.13.0 for proper RFC 6570 query parameter support.
* feat: improve material properties and sync Server resources
Material Property Improvements (ManageAsset.cs):
- Add GetMainColorPropertyName() helper that auto-detects shader color properties
- Tries _BaseColor (URP), _Color (Standard), _MainColor, _Tint, _TintColor
- Update both named and array color property handling to use auto-detection
- Add warning messages when color properties don't exist on materials
- Split HasProperty check from SetColor to enable error reporting
This fixes the issue where simple color array format [r,g,b,a] defaulted to
_Color property, causing silent failures with URP Lit shader which uses _BaseColor.
Server Resource Sync:
- Sync Server/resources with MCPForUnity/UnityMcpServer~/src/resources
- Remove query parameters from resource URIs for discoverability
- Use session-based instance routing via get_unity_instance_from_context()
* fix: repair instance routing and simplify get_unity_instance_from_context
PROBLEM:
Instance routing was failing - scripts went to wrong Unity instances.
Script1 (intended: ramble) -> went to UnityMCPTests ❌
Script2 (intended: UnityMCPTests) -> went to ramble ❌
ROOT CAUSE:
Two incompatible approaches for accessing active instance:
1. Middleware: ctx.set_state() / ctx.get_state() - used by most tools
2. Legacy: ctx.request_context.meta - used by script tools
Script tools were reading from wrong location, middleware had no effect.
FIX:
1. Updated get_unity_instance_from_context() to read from ctx.get_state()
2. Removed legacy request_context.meta code path (98 lines removed)
3. Single source of truth: middleware state only
TESTING:
- Added comprehensive test suite (21 tests) covering all scenarios
- Tests middleware state management, session isolation, race conditions
- Tests reproduce exact 4-script failure scenario
- All 88 tests pass (76 passed + 5 skipped + 7 xpassed)
- Verified fix with live 4-script test: 100% success rate
Files changed:
- Server/tools/__init__.py: Simplified from 75 lines to 15 lines
- MCPForUnity/UnityMcpServer~/src/tools/__init__.py: Same simplification
- tests/test_instance_routing_comprehensive.py: New comprehensive test suite
* refactor: standardize instance extraction and remove dead imports
- Standardize all 18 tools to use get_unity_instance_from_context() helper
instead of direct ctx.get_state() calls for consistency
- Remove dead session_state imports from with_unity_instance decorator
that would cause ModuleNotFoundError at runtime
- Update README.md with concise instance routing documentation
* fix: critical timezone and import bugs from code review
- Remove incorrect port safety check that treated reclaimed ports as errors
(GetPortWithFallback may legitimately return same port if it became available)
- Fix timezone-aware vs naive datetime mixing in unity_connection.py sorting
(use timestamp() for comparison to avoid TypeError)
- Normalize all datetime comparisons in port_discovery.py to UTC
(file_mtime and last_heartbeat now consistently timezone-aware)
- Add missing send_with_unity_instance import in Server/tools/manage_script.py
(was causing NameError at runtime on lines 108 and 488)
All 88 tests pass (76 passed + 5 skipped + 7 xpassed)
---------
Co-authored-by: Sakura <sakurachan@qq.com>
Co-authored-by: Claude <noreply@anthropic.com>
* deps: add tomli>=2.3.0 dependency to UnityMcpServer package
* feat: dynamically fetch package version from pyproject.toml for telemetry
* Add pydantic
* feat: add resource registry for MCP resource auto-discovery
* feat: add telemetry decorator for tracking MCP resource usage
* feat: add auto-discovery and registration system for MCP resources
* feat: add resource registration to MCP server initialization
* feat: add MCPResponse model class for standardized API responses
* refactor: replace Debug.Log calls with McpLog wrapper for consistent logging
* feat: add test discovery endpoints for Unity Test Framework integration
We haven't connected them as yet, still thinking about how to do this neatly
* Fix server setup
* refactor: reduce log verbosity by changing individual resource/tool registration logs to debug level
* chore: bump mcp[cli] dependency from 1.15.0 to 1.17.0
* refactor: remove Context parameter and add uri keyword argument in resource decorator
The Context parameter doesn't work on our version of FastMCP
* chore: upgrade Python base image to 3.13 and simplify Dockerfile setup
* fix: apply telemetry decorator before mcp.tool to ensure proper wrapping order
* fix: swap order of telemetry and resource decorators to properly wrap handlers
* fix: update log prefixes for consistency in logging methods
* Fix compile errors
* feat: extend command registry to support both tools and resources
* Run get tests as a coroutine because it doesn't return results immediately
This works but it spams logs like crazy, maybe there's a better/simpler way
* refactor: migrate from coroutines to async/await for test retrieval and command execution
* feat: add optional error field to MCPResponse model
* Increased timeout because loading tests can take some time
* Make message optional so error responses that only have success and error don't cause Pydantic errors
* Set max_retries to 5
This connection module needs a lookover. The retries should be an exponential backoff and we could structure why it's failing so much
* Use pydantic model to structure the error output
* fix: initialize data field in GetTestsResponse to avoid potential errors
* Don't return path parameter
* feat: add Unity test runner execution with structured results and Python bindings
* refactor: simplify GetTests by removing mode filtering and related parsing logic
* refactor: move test runner functionality into dedicated service interface
* feat: add resource retrieval telemetry tracking with new record type and helper function
* fix: convert tool functions to async and await ctx.info calls
* refactor: reorganize menu item functionality into separate execute and get commands
An MCP resource for retrieval, and a simple command to execute. Because it's a resource, it's easier for the user to see what's in the menu items
* refactor: rename manage_menu_item to execute_menu_item and update tool examples to use async/await
We'll eventually put a section for resources
* Revert "fix: convert tool functions to async and await ctx.info calls"
This reverts commit 012ea6b7439bd1f2593864d98d03d9d95d7bdd03.
* fix: replace tomllib with tomli for Python 3.10 compatibility in telemetry module
* Remove confusing comment
* refactor: improve error handling and simplify test retrieval logic in GetTests commands
* No cache by default
* docs: remove redundant comment for HandleCommand method in ExecuteMenuItem
* Copy UnityMcpBridge into a new MCPForUnity folder
This is to close#284
* refactor: rename UnityMcpBridge directory to MCPForUnity in docs
* chore: rename UnityMcpBridge directory to MCPForUnity across workflow files
* chore: rename UnityMcpBridge directory to MCPForUnity across all files
* refactor: update import paths from UnityMcpBridge to MCPForUnity across test files
* fix: update module import paths to use MCPForUnity instead of UnityMcpBridge
* chore: update unity-mcp package path to MCPForUnity directory
* feat: add OneTimeSetUp to initialize CommandRegistry before tests run
Hopefully fix the CI failures
* Apply recent fix to new folder
* Temporarily trigger tests to see if CI works
* Revert "Temporarily trigger tests to see if CI works"
It works!
This reverts commit 8c6eaaad07545cef047769f2c52fe506545a8161.
dsarno
Marcus Sanatan