{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github_mcp-gts360-django-mcp-server","slug":"mcp-gts360-django-mcp-server","name":"django-mcp-server","type":"mcp","url":"https://github.com/gts360/django-mcp-server","page_url":"https://unfragile.ai/mcp-gts360-django-mcp-server","categories":["mcp-servers"],"tags":["agentic-ai","ai","django","modelcontextprotocol"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github_mcp-gts360-django-mcp-server__cap_0","uri":"capability://tool.use.integration.mcp.protocol.bridge.for.django.applications","name":"mcp protocol bridge for django applications","description":"Implements the Model Context Protocol specification as a Django extension, translating between standardized MCP protocol messages (tools, resources, prompts) and Django application functionality. Uses a layered architecture with transport abstraction (HTTP/STDIO), session management, and a metaclass-based tool registry that auto-discovers and registers tools during application startup. Enables any MCP-compatible client (Claude AI, Google ADK, custom agents) to invoke Django operations through typed tool interfaces.","intents":["Enable AI agents to interact with my Django app without building custom APIs","Expose Django models and views as discoverable tools for MCP clients","Build agentic workflows that read/write to my Django database through standard MCP protocol","Integrate Claude or other AI agents with my existing Django application"],"best_for":["Django developers building agentic AI integrations","Teams deploying AI agents that need structured access to Django apps","Developers migrating from REST APIs to standardized MCP protocol"],"limitations":["Requires Django 3.2+ and Python 3.9+; no support for legacy Django versions","MCP protocol overhead adds latency compared to direct REST calls; not suitable for sub-100ms response requirements","Session management is stateless by default; requires external persistence for multi-turn agent conversations","STDIO transport limited to local/containerized deployments; HTTP transport requires careful authentication setup"],"requires":["Django 3.2+","Python 3.9+","MCP SDK (Python or language-specific client)","FastMCP framework (underlying dependency)","WSGI or ASGI application server"],"input_types":["MCP tool call requests with typed parameters","MCP resource requests","MCP prompt templates"],"output_types":["MCP tool results (JSON-serialized)","MCP resources (CSV, JSON documents)","MCP prompt responses"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_1","uri":"capability://tool.use.integration.declarative.tool.registration.via.mcptoolset.pattern","name":"declarative tool registration via mcptoolset pattern","description":"Provides a metaclass-based tool registration system where developers define tools by subclassing MCPToolset and decorating methods with @mcp_tool. The metaclass automatically discovers decorated methods at class definition time, extracts type hints and docstrings to generate MCP-compatible schemas, and registers tools in a central registry. Tools are exposed to MCP clients with full type information, parameter validation, and automatic serialization of return values.","intents":["Define custom AI-accessible functions in my Django app with minimal boilerplate","Expose business logic as typed MCP tools without writing schema definitions","Create reusable tool collections organized by domain (e.g., UserToolset, OrderToolset)","Automatically generate tool schemas from Python type hints and docstrings"],"best_for":["Django developers familiar with decorators and metaclasses","Teams building domain-specific tool collections for AI agents","Projects requiring custom business logic exposure beyond ORM queries"],"limitations":["Metaclass-based discovery runs at import time; dynamic tool registration not supported","Type hints must be explicit; complex nested types may require custom serializers","Docstrings are parsed for schema generation; inconsistent formatting breaks schema inference","No built-in rate limiting or quota management per tool"],"requires":["Python 3.9+ (for type hint support)","MCPToolset base class from django-mcp-server","@mcp_tool decorator","Type hints on all tool method parameters"],"input_types":["Python method definitions with type hints","Docstrings (for schema documentation)"],"output_types":["MCP tool schemas (JSON)","Tool execution results (JSON-serialized return values)"],"categories":["tool-use-integration","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_10","uri":"capability://automation.workflow.mcp.inspect.command.line.tool.for.local.development.and.testing","name":"mcp_inspect command-line tool for local development and testing","description":"Provides a Django management command (mcp_inspect) that introspects the MCP server configuration and registered tools during local development. Displays tool schemas, parameters, descriptions, and authentication requirements in human-readable format. Enables developers to test tool invocation locally without connecting an MCP client, simulating tool calls with custom parameters and inspecting results. Supports schema validation and debugging of tool definitions.","intents":["Inspect registered tools and their schemas during development","Test tool invocation locally without an MCP client","Debug tool parameter schemas and validation","Verify authentication and permission configuration"],"best_for":["Local development and debugging","Testing tool definitions before deploying","Developers unfamiliar with MCP protocol wanting to understand tool structure"],"limitations":["mcp_inspect is development-only; not suitable for production monitoring","No persistent logging of tool invocations; results not saved","Limited to local development environment; requires Django shell access","No support for testing streaming responses","No performance profiling or benchmarking capabilities"],"requires":["Django management command infrastructure","Local Django development environment","Python shell access"],"input_types":["Tool name (optional, for filtering)","Tool parameters (for testing invocation)"],"output_types":["Tool schema information (human-readable)","Tool invocation results","Error messages and validation feedback"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_11","uri":"capability://safety.moderation.permission.and.access.control.enforcement.per.tool","name":"permission and access control enforcement per tool","description":"Enforces Django permission checks on a per-tool basis, integrating with Django's permission system to restrict tool access based on user roles and permissions. Tools can declare required permissions through configuration or decorators, and the framework validates user permissions before tool execution. Supports both model-level permissions (add, change, delete) and custom permission definitions. Permission checks are enforced at the transport layer (HTTP) and during tool execution, with proper error responses for unauthorized access.","intents":["Restrict MCP tool access based on Django user permissions","Enforce model-level permissions (add, change, delete) for CRUD tools","Define custom permissions for domain-specific tools","Prevent unauthorized users from invoking sensitive tools"],"best_for":["Multi-user Django applications with role-based access control","Teams requiring fine-grained permission enforcement","Projects using Django's permission system for access control"],"limitations":["Permission checking relies on Django's permission system; custom permission logic requires overrides","No built-in role-based access control (RBAC); requires custom permission definitions","Permission checks are synchronous; no async permission evaluation","No built-in audit logging of permission checks","Object-level permissions (row-level security) not supported; requires custom implementation"],"requires":["Django user model and permission system","Permission definitions for tools","Authenticated user context in request"],"input_types":["User object with permissions","Tool invocation request","Required permissions for tool"],"output_types":["Permission check result (allowed/denied)","Error response for unauthorized access","Tool execution result (if authorized)"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_12","uri":"capability://automation.workflow.multiple.mcp.server.instances.with.isolated.tool.registries","name":"multiple mcp server instances with isolated tool registries","description":"Supports running multiple independent MCP server instances within a single Django application, each with its own isolated tool registry and configuration. Enables different MCP servers to expose different tool collections to different client groups (e.g., admin tools vs. user tools). Each server instance maintains separate authentication, permission, and session configuration. Multiple servers can coexist in the same Django application through separate URL routes or STDIO processes.","intents":["Expose different tool collections to different client groups (admin vs. user)","Run multiple MCP servers with isolated configurations in one Django app","Segment tools by domain or access level across multiple server instances","Support different authentication schemes for different server instances"],"best_for":["Multi-tenant applications requiring tool isolation","Teams with different tool access requirements for different client groups","Projects needing to segment tools by domain or access level"],"limitations":["Multiple server instances increase memory overhead; no shared tool registry","Configuration management becomes complex with multiple servers; requires careful setup","Session state not shared between server instances; requires external session store","Tool discovery must be done per server instance; no global tool discovery","Debugging multiple server instances more difficult; requires separate logging per instance"],"requires":["Multiple DjangoMCP server instances","Separate URL routes or STDIO processes per server","Isolated tool registry per server","Separate authentication/permission configuration per server"],"input_types":["Server configuration (tools, auth, permissions)","MCP client requests"],"output_types":["Tool discovery responses per server","Tool execution results per server"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_2","uri":"capability://data.processing.analysis.orm.aware.query.tool.generation.via.modelquerytoolset","name":"orm-aware query tool generation via modelquerytoolset","description":"Automatically generates MCP tools from Django ORM models by subclassing ModelQueryToolset and specifying a model class. The system introspects model fields, relationships, and querysets to generate parameterized query tools (list, filter, get, create, update, delete) with schema validation. Implements a query DSL that translates MCP tool parameters into Django ORM calls, with support for filtering, pagination, ordering, and field selection. Handles serialization of model instances to JSON via Django REST Framework serializers.","intents":["Expose Django models as queryable tools for AI agents without writing custom views","Allow agents to filter, paginate, and retrieve model data through typed parameters","Enable CRUD operations on models through MCP tools with automatic permission checking","Generate query tools with schema validation derived from model field definitions"],"best_for":["Teams with Django models that need AI agent access","Projects using Django REST Framework for serialization","Developers building data-driven agentic workflows"],"limitations":["Query DSL supports basic filtering/ordering; complex aggregations require custom tools","Relationship traversal limited to single-level foreign keys; deep nested queries not supported","Serialization depends on DRF serializers; models without serializers require custom configuration","No built-in pagination defaults; agents must specify limit/offset explicitly","Permission checking relies on Django's permission system; custom permission logic requires overrides"],"requires":["Django ORM model definitions","Django REST Framework (for serialization)","ModelQueryToolset base class","Model field type hints (for schema generation)"],"input_types":["Django model class","Query parameters (filter, order_by, limit, offset, fields)","CRUD operation parameters (create, update, delete)"],"output_types":["JSON-serialized model instances","Paginated query results with metadata","CRUD operation confirmations"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_3","uri":"capability://tool.use.integration.django.rest.framework.view.publishing.as.mcp.tools","name":"django rest framework view publishing as mcp tools","description":"Provides decorators and publishing functions that expose existing Django REST Framework views as MCP tools without modifying view code. Introspects DRF view classes to extract serializer schemas, HTTP methods, and permission classes, then generates MCP tool schemas that map to view endpoints. Handles request/response translation between MCP protocol and DRF's request/response objects, including authentication token injection and permission enforcement.","intents":["Expose existing DRF views as MCP tools without rewriting them","Leverage DRF's serialization and permission system for MCP tool validation","Publish multiple DRF views as a cohesive tool collection for AI agents","Maintain DRF views as the source of truth while exposing them via MCP"],"best_for":["Teams with mature DRF APIs wanting to add AI agent access","Projects seeking to avoid code duplication between REST and MCP interfaces","Developers familiar with DRF patterns and wanting minimal learning curve"],"limitations":["View introspection limited to standard DRF patterns; custom view logic may not translate to MCP schemas","HTTP method semantics (GET, POST, PATCH) must map cleanly to tool parameters; complex workflows require custom tools","Authentication token handling requires explicit configuration; session-based auth not fully supported","Response streaming and file downloads not supported through MCP protocol","Pagination and filtering must be explicitly defined in serializers; implicit DRF pagination not auto-exposed"],"requires":["Django REST Framework views","Serializer definitions with schema information","DRF publishing decorators or functions","Authentication configuration (token or OAuth2)"],"input_types":["DRF ViewSet or APIView class","Serializer definitions","HTTP method specifications"],"output_types":["MCP tool schemas derived from serializers","Serialized response data","HTTP status/error information"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_4","uri":"capability://automation.workflow.multi.transport.mcp.server.deployment.http.and.stdio","name":"multi-transport mcp server deployment (http and stdio)","description":"Supports both HTTP and STDIO transports for MCP protocol communication, allowing deployment in different environments without code changes. HTTP transport runs as a Django view (MCPServerStreamableHttpView) integrated into URL routing, supporting both WSGI and ASGI application servers. STDIO transport enables local/containerized deployments where the MCP server communicates via standard input/output streams. Transport abstraction layer handles protocol message serialization, session management, and error handling uniformly across both transports.","intents":["Deploy MCP server in cloud environments using HTTP transport","Run MCP server locally or in containers using STDIO transport","Support multiple MCP clients connecting simultaneously via HTTP","Migrate between deployment environments without code changes"],"best_for":["Teams deploying to cloud platforms (AWS, GCP, Azure) with HTTP endpoints","Local development and testing using STDIO transport","Projects requiring both cloud and local deployment flexibility"],"limitations":["HTTP transport requires authentication configuration; unauthenticated endpoints expose all tools","STDIO transport limited to single client connection; no concurrent client support","HTTP transport adds network latency; not suitable for sub-100ms response requirements","Session state not persisted across server restarts; requires external session store for production","STDIO transport incompatible with containerized environments requiring HTTP health checks"],"requires":["Django URL routing configuration (for HTTP transport)","WSGI or ASGI application server","MCPServerStreamableHttpView for HTTP transport","STDIO-compatible client for STDIO transport"],"input_types":["MCP protocol messages (JSON-RPC format)","HTTP POST requests (for HTTP transport)","STDIN stream (for STDIO transport)"],"output_types":["MCP protocol responses (JSON-RPC format)","HTTP responses with streaming support","STDOUT stream (for STDIO transport)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_5","uri":"capability://safety.moderation.session.and.authentication.management.for.mcp.clients","name":"session and authentication management for mcp clients","description":"Implements session management and authentication enforcement for MCP clients, supporting stateless and stateful interaction contexts. Integrates with Django's authentication system (user models, permissions) and supports multiple authentication classes (token-based, OAuth2, custom). Session context is passed through the request/response lifecycle, enabling permission checks and user-scoped data access. Authentication is enforced at the transport layer (HTTP) or session initialization (STDIO), with per-tool permission validation.","intents":["Restrict MCP tool access based on Django user permissions","Enforce authentication for MCP clients connecting via HTTP","Scope tool results to authenticated user (e.g., user's own orders)","Support OAuth2 and token-based authentication for MCP clients"],"best_for":["Multi-tenant Django applications requiring user-scoped data access","Teams deploying MCP servers with authentication requirements","Projects using Django's permission system for access control"],"limitations":["Session state is stateless by default; multi-turn conversations require external session store","OAuth2 setup requires manual configuration; no built-in OAuth2 provider","Permission checking relies on Django's permission system; custom permission logic requires overrides","Token-based auth requires token generation outside MCP server","No built-in rate limiting or quota enforcement per authenticated user"],"requires":["Django user model and authentication system","Authentication class configuration (token, OAuth2, or custom)","Django permission definitions for tools","Session store (database, cache, or external service)"],"input_types":["Authentication credentials (token, OAuth2 code, custom)","MCP tool requests with session context"],"output_types":["Authenticated session context","User-scoped tool results","Permission validation responses"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_6","uri":"capability://data.processing.analysis.query.dsl.for.parameterized.orm.queries","name":"query dsl for parameterized orm queries","description":"Implements a query DSL that translates MCP tool parameters into Django ORM queries, supporting filtering, ordering, pagination, and field selection. The DSL accepts filter parameters in a standardized format (e.g., field__lookup=value), maps them to Django's ORM query syntax, and executes queries with automatic schema validation. Supports nested field access through foreign key relationships, custom field lookups (exact, icontains, gte, lte), and result pagination with limit/offset. Schema generation from model fields ensures type-safe parameter validation.","intents":["Allow AI agents to query Django models with complex filters without writing SQL","Support parameterized queries with automatic ORM translation and validation","Enable pagination and field selection in model queries","Provide type-safe query parameters derived from model field definitions"],"best_for":["Data-driven agentic workflows requiring flexible model queries","Teams wanting to expose model data without custom view code","Projects using Django ORM exclusively (no raw SQL)"],"limitations":["DSL supports basic filtering/ordering; complex aggregations (GROUP BY, COUNT) require custom tools","Relationship traversal limited to single-level foreign keys; deep nested queries not supported","Custom field lookups must be explicitly whitelisted; arbitrary ORM operations not allowed","No support for raw SQL queries; all queries must use ORM","Performance not optimized for large result sets; no built-in query optimization or indexing hints"],"requires":["Django ORM model definitions","Model field type information","Query DSL parser and executor","Schema generation from model fields"],"input_types":["Filter parameters (field__lookup=value format)","Ordering parameters (order_by=field)","Pagination parameters (limit, offset)","Field selection parameters (fields=field1,field2)"],"output_types":["Paginated query results","Result count and metadata","JSON-serialized model instances"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_7","uri":"capability://data.processing.analysis.automatic.schema.generation.from.django.models.and.drf.serializers","name":"automatic schema generation from django models and drf serializers","description":"Introspects Django ORM models and Django REST Framework serializers to automatically generate MCP-compatible tool schemas with type information, field descriptions, and validation rules. Extracts field types, relationships, validators, and help text from model definitions and serializer metadata, then generates JSON schemas that describe tool parameters and return types. Supports nested schema generation for related models and custom field types through serializer configuration.","intents":["Generate MCP tool schemas automatically from model definitions without manual schema writing","Ensure tool schemas stay in sync with model changes","Provide type-safe parameter validation for MCP tools based on model field definitions","Document tool parameters and return types from model metadata"],"best_for":["Teams using Django ORM and DRF for data modeling","Projects requiring schema-driven tool generation","Developers wanting to avoid manual schema maintenance"],"limitations":["Schema generation limited to standard Django field types; custom fields require custom serializers","Nested schema generation only supports single-level relationships; deep nesting not supported","Serializer metadata (help_text, validators) must be explicitly defined; implicit metadata not extracted","Schema generation runs at startup; dynamic schema updates not supported","Complex validation rules (cross-field validation) not fully represented in generated schemas"],"requires":["Django ORM model definitions with field type information","Django REST Framework serializers (for DRF integration pattern)","Schema generation engine","JSON schema output format"],"input_types":["Django model class","DRF serializer class","Field definitions and metadata"],"output_types":["JSON schema for tool parameters","JSON schema for tool return types","Field descriptions and validation rules"],"categories":["data-processing-analysis","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_8","uri":"capability://tool.use.integration.tool.discovery.and.registration.via.metaclass.based.registry","name":"tool discovery and registration via metaclass-based registry","description":"Implements a metaclass-based tool registry that auto-discovers and registers tools at class definition time by scanning for decorated methods and subclasses. When a class inheriting from MCPToolset or ModelQueryToolset is defined, the metaclass intercepts class creation, extracts tool definitions from decorated methods or model configuration, and registers them in a central registry. The registry maintains tool metadata (schemas, handlers, permissions) and exposes tools to MCP clients through the discovery protocol. No manual registration required; tools are discovered during Django application startup.","intents":["Automatically discover and register tools without manual configuration","Organize tools into logical collections (toolsets) by domain","Maintain a central registry of all available tools for MCP clients","Enable dynamic tool discovery during application startup"],"best_for":["Teams building modular tool collections organized by domain","Projects requiring zero-configuration tool registration","Developers familiar with Python metaclasses and decorators"],"limitations":["Metaclass discovery runs at import time; dynamic tool registration not supported","Tool registration order depends on import order; circular imports can cause issues","Registry is global; no namespace isolation between toolsets","No built-in tool versioning or deprecation support","Tool removal requires application restart; no hot-reloading"],"requires":["MCPToolset or ModelQueryToolset base class","@mcp_tool decorator (for MCPToolset pattern)","Python metaclass support","Django application startup"],"input_types":["Tool class definitions (MCPToolset subclasses)","Decorated tool methods","Model class definitions (for ModelQueryToolset)"],"output_types":["Registered tool metadata","Tool schemas and handlers","Tool discovery responses"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github_mcp-gts360-django-mcp-server__cap_9","uri":"capability://automation.workflow.request.response.lifecycle.management.with.streaming.support","name":"request/response lifecycle management with streaming support","description":"Manages the complete request/response lifecycle for MCP protocol messages, including message parsing, tool invocation, result serialization, and streaming response handling. Implements a pipeline architecture with stages for authentication, permission checking, tool execution, and response formatting. Supports streaming responses for large result sets through HTTP chunked transfer encoding or STDIO stream writing. Handles error cases with proper MCP error response formatting and exception propagation.","intents":["Process MCP tool requests end-to-end with proper error handling","Stream large results to MCP clients without buffering in memory","Enforce authentication and permissions throughout request lifecycle","Serialize tool results to MCP-compatible response format"],"best_for":["Production deployments requiring reliable request handling","Applications with large result sets requiring streaming","Teams needing comprehensive error handling and logging"],"limitations":["Streaming support limited to HTTP chunked encoding; STDIO streaming less efficient","Error handling follows MCP spec; custom error formats not supported","Pipeline stages run sequentially; no parallel execution","Request timeout handling depends on application server configuration","Memory usage not optimized for very large result sets; streaming helps but doesn't eliminate buffering"],"requires":["MCP protocol message format","Tool execution engine","Response serialization","HTTP or STDIO transport"],"input_types":["MCP JSON-RPC request messages","Tool parameters","Authentication credentials"],"output_types":["MCP JSON-RPC response messages","Streamed result chunks","Error responses"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":41,"verified":false,"data_access_risk":"high","permissions":["Django 3.2+","Python 3.9+","MCP SDK (Python or language-specific client)","FastMCP framework (underlying dependency)","WSGI or ASGI application server","Python 3.9+ (for type hint support)","MCPToolset base class from django-mcp-server","@mcp_tool decorator","Type hints on all tool method parameters","Django management command infrastructure"],"failure_modes":["Requires Django 3.2+ and Python 3.9+; no support for legacy Django versions","MCP protocol overhead adds latency compared to direct REST calls; not suitable for sub-100ms response requirements","Session management is stateless by default; requires external persistence for multi-turn agent conversations","STDIO transport limited to local/containerized deployments; HTTP transport requires careful authentication setup","Metaclass-based discovery runs at import time; dynamic tool registration not supported","Type hints must be explicit; complex nested types may require custom serializers","Docstrings are parsed for schema generation; inconsistent formatting breaks schema inference","No built-in rate limiting or quota management per tool","mcp_inspect is development-only; not suitable for production monitoring","No persistent logging of tool invocations; results not saved","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.3219027964106564,"quality":0.5,"ecosystem":0.52,"match_graph":0.25,"freshness":0.6,"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":"2026-05-24T12:16:22.065Z","last_scraped_at":"2026-05-03T14:23:38.364Z","last_commit":"2026-03-10T10:38:28Z"},"community":{"stars":323,"forks":52,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=mcp-gts360-django-mcp-server","compare_url":"https://unfragile.ai/compare?artifact=mcp-gts360-django-mcp-server"}},"signature":"SwLryAYqvAR94aEo8EgCWTRNijst0oy//MYBAs7Vtdf7u2MlyunbzPe8Zmx6/pBipnK4lhnHJP1SrHf+5XOrCA==","signedAt":"2026-06-22T04:15:43.086Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mcp-gts360-django-mcp-server","artifact":"https://unfragile.ai/mcp-gts360-django-mcp-server","verify":"https://unfragile.ai/api/v1/verify?slug=mcp-gts360-django-mcp-server","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"}}