{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-mbro","slug":"mbro","name":"MBro","type":"cli","url":"https://github.com/sitbon/magg/blob/main/docs/mbro.md","page_url":"https://unfragile.ai/mbro","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-mbro__cap_0","uri":"capability://tool.use.integration.multi.server.mcp.aggregation.with.unified.tool.namespace","name":"multi-server mcp aggregation with unified tool namespace","description":"Magg implements a hub-and-spoke proxy architecture that connects to multiple backend MCP servers and exposes their tools through a single aggregated MCP interface. It uses a MaggServer class that manages ServerManager instances for each connected backend, routes tool calls to appropriate servers based on configurable prefixes (e.g., calc_add, pw_screenshot), and maintains full MCP protocol semantics including notifications, progress updates, and resource management. The system dynamically discovers and registers tools from all connected servers without requiring manual tool definition.","intents":["I want to expose tools from 5+ different MCP servers to a single LLM client without managing multiple connections","I need to add namespace prefixes to tools from different servers to avoid naming collisions","I want to dynamically add or remove backend MCP servers without restarting the aggregator","I need to maintain full MCP protocol features (notifications, progress, resources) across aggregated servers"],"best_for":["AI teams building multi-tool LLM agents that need centralized tool management","Organizations deploying multiple specialized MCP servers that need unified access","Developers building MCP-based platforms requiring dynamic server composition"],"limitations":["Tool name collisions across servers require manual prefix configuration — no automatic collision detection","Aggregation adds latency for each tool call due to message routing through proxy layer","No built-in load balancing or failover if a backend MCP server becomes unavailable","Resource management (files, memory) is per-server, not aggregated across the cluster"],"requires":["Python 3.9+","FastMCP framework for transport layer","Backend MCP servers running and accessible via stdio or HTTP","Configuration file defining server connections and tool prefixes"],"input_types":["MCP tool call requests with arguments","Server configuration (YAML/JSON with server URLs/commands)"],"output_types":["MCP tool responses","Aggregated tool list with prefixed names","Notifications and progress updates from backend servers"],"categories":["tool-use-integration","proxy-architecture"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_1","uri":"capability://tool.use.integration.interactive.mcp.browser.with.tab.completion.and.auto.documentation","name":"interactive mcp browser with tab completion and auto-documentation","description":"MBRO is an interactive terminal REPL client that connects to MCP servers and provides real-time tab completion for tool names, arguments, and available resources. It implements a command processing system that parses user input, introspects connected MCP servers to extract tool schemas and documentation, and renders formatted output with syntax highlighting. The browser maintains connection state across multiple MCP servers and automatically generates contextual help based on tool schemas without requiring manual documentation maintenance.","intents":["I want to explore available tools in an MCP server interactively with autocomplete","I need to see tool documentation and argument schemas without leaving the terminal","I want to test MCP tool calls manually before integrating them into an agent","I need to work with multiple MCP servers in a single session with tab completion for each"],"best_for":["Developers debugging MCP server implementations","Teams exploring new MCP tools before integration","Solo developers prototyping LLM agent workflows","DevOps engineers testing MCP server deployments"],"limitations":["Tab completion requires full tool schema introspection on startup — adds 500ms+ latency for servers with 100+ tools","No persistent history across sessions unless manually configured","Output formatting is terminal-only — no export to structured formats (JSON, CSV)","Argument validation is schema-based only — no runtime type checking or coercion"],"requires":["Python 3.9+","Terminal with ANSI color support","MCP server running and accessible via stdio or HTTP","Readline or similar for tab completion support"],"input_types":["Interactive terminal commands","Tool names and arguments as text","Configuration for MCP server connections"],"output_types":["Formatted terminal output with syntax highlighting","Tool schemas and documentation","Tool execution results"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_10","uri":"capability://tool.use.integration.multi.server.connection.management.with.independent.state.tracking","name":"multi-server connection management with independent state tracking","description":"MBRO maintains independent connection state for each MCP server, tracking authentication tokens, tool schemas, resource lists, and connection status separately. The connection manager handles concurrent requests to multiple servers without blocking, implements per-server timeout and retry logic, and provides connection pooling for HTTP-based servers. Each server connection is isolated — failures in one server don't affect others, and authentication credentials are stored per-server.","intents":["I want to work with multiple MCP servers in a single MBRO session without switching contexts","I need to maintain separate authentication for each MCP server","I want to see which servers are connected and which are unavailable","I need to handle timeouts or failures in one server without affecting others"],"best_for":["Teams managing multiple specialized MCP servers with different authentication","Developers testing interactions between tools from different servers","DevOps engineers monitoring multiple MCP server deployments","Organizations with federated MCP server architectures"],"limitations":["Per-server state tracking adds memory overhead — not suitable for 100+ simultaneous server connections","Connection pooling is per-server — no global connection limit or resource management","No transaction semantics across servers — tool calls to multiple servers may partially fail","Server switching requires manual context management — no automatic server selection based on tool availability"],"requires":["Python 3.9+","MCP server connection details (URL or startup command)","Authentication credentials per server (if required)"],"input_types":["Server connection configuration","Authentication credentials","Tool call requests with server targeting"],"output_types":["Per-server connection status","Tool schemas from each server","Tool responses with server attribution"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_11","uri":"capability://automation.workflow.cli.command.interface.for.server.management.and.configuration","name":"cli command interface for server management and configuration","description":"Magg provides a comprehensive CLI interface (magg.cli:main) for starting servers, managing configurations, handling authentication, and managing kits. The CLI supports subcommands for server startup (with transport mode selection), configuration validation, authentication token generation, kit installation/updates, and server status monitoring. Commands are composable and support both interactive and scripted usage, with detailed help text and error messages.","intents":["I want to start the Magg aggregator server with specific transport modes and configuration","I need to generate authentication tokens for MCP clients","I want to validate my configuration file before deploying","I need to install or update MCP server kits from the command line"],"best_for":["DevOps teams deploying Magg in production environments","Developers setting up local Magg instances for testing","Teams automating MCP server deployment through CI/CD","System administrators managing multiple Magg instances"],"limitations":["CLI is synchronous — long-running operations (kit installation) block the terminal","No built-in progress reporting for long operations — users see no feedback during installation","Configuration validation is schema-only — doesn't test actual server connectivity","Token generation is one-time — no token management UI or revocation interface"],"requires":["Python 3.9+","Magg installed and in PATH","Configuration file for server startup"],"input_types":["CLI arguments and flags","Configuration files","Interactive prompts"],"output_types":["Server startup logs","Authentication tokens","Configuration validation results","Installation status"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_12","uri":"capability://memory.knowledge.tool.schema.introspection.and.documentation.generation","name":"tool schema introspection and documentation generation","description":"Magg automatically introspects connected MCP servers to extract tool schemas (argument types, descriptions, required fields) and generates documentation without manual maintenance. The introspection system queries each server's tool list on connection, caches schemas for performance, and provides schema-based validation and help text generation. Documentation is automatically formatted for display in MBRO with argument descriptions, type information, and usage examples extracted from schemas.","intents":["I want to see documentation for available tools without reading separate docs","I need to understand tool argument types and requirements before calling them","I want to generate help text automatically from tool schemas","I need to validate tool arguments against their schemas before sending requests"],"best_for":["Developers exploring new MCP servers interactively","Teams building user-friendly MCP interfaces with auto-generated help","DevOps engineers documenting MCP tool capabilities","Organizations maintaining multiple MCP servers with evolving schemas"],"limitations":["Schema introspection adds startup latency (500ms+ for servers with 100+ tools)","Schemas are cached — schema changes require server restart to reflect","Documentation is schema-only — no support for custom examples or usage patterns","Schema validation is client-side only — doesn't catch server-side validation errors"],"requires":["Python 3.9+","MCP servers exposing tool schemas","Schema caching mechanism"],"input_types":["MCP tool list requests","Tool schema queries"],"output_types":["Cached tool schemas","Generated documentation","Validation results"],"categories":["memory-knowledge","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_2","uri":"capability://tool.use.integration.transport.layer.abstraction.with.stdio.http.hybrid.mode.selection","name":"transport layer abstraction with stdio/http/hybrid mode selection","description":"Magg abstracts MCP communication through FastMCP framework, supporting three transport modes: stdio (direct process pipes for desktop clients), HTTP (REST API for web/remote access), and hybrid (both simultaneously). The transport layer is selected at server startup and handles serialization, deserialization, and protocol framing for each mode. Stdio mode uses JSON-RPC over stdin/stdout for low-latency local communication, HTTP mode exposes MCP as REST endpoints with request/response marshaling, and hybrid mode runs both transports in parallel with shared state.","intents":["I want to run MCP servers locally with minimal latency for desktop clients","I need to expose MCP tools via HTTP API for web-based or remote clients","I want to support both local and remote clients simultaneously without running separate server instances","I need to integrate MCP with existing REST API infrastructure"],"best_for":["Teams deploying MCP servers in containerized environments requiring HTTP access","Developers building web-based LLM interfaces that need MCP tool access","Organizations with mixed local and remote MCP client deployments","DevOps teams integrating MCP into existing API gateways"],"limitations":["HTTP mode adds ~50-200ms latency per request compared to stdio due to TCP overhead and serialization","Hybrid mode doubles resource consumption (memory, file descriptors) by running two transport listeners","HTTP mode requires authentication/authorization layer — no built-in API key management beyond JWT","Stdio mode is single-connection only — cannot multiplex multiple clients on one server instance"],"requires":["Python 3.9+","FastMCP framework","For HTTP mode: network access and port binding permissions","For stdio mode: parent process managing stdin/stdout pipes"],"input_types":["MCP protocol messages (JSON-RPC format)","HTTP requests with JSON payloads"],"output_types":["MCP protocol responses (JSON-RPC format)","HTTP responses with JSON payloads"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_3","uri":"capability://automation.workflow.dynamic.configuration.reloading.with.watchdog.based.file.monitoring","name":"dynamic configuration reloading with watchdog-based file monitoring","description":"Magg uses watchdog-based file system monitoring to detect changes to configuration files (server definitions, tool prefixes, authentication settings) and automatically reloads them without server restart. The ConfigManager class watches the configuration directory, detects file modifications, validates new configuration against schema, and applies changes to running ServerManager instances. This enables adding/removing backend MCP servers, changing tool prefixes, or updating authentication settings in real-time while maintaining active client connections.","intents":["I want to add a new MCP server to the aggregator without restarting and losing client connections","I need to update tool prefixes or server URLs without downtime","I want to enable/disable specific MCP servers dynamically based on operational needs","I need to rotate authentication credentials without server restart"],"best_for":["Production deployments requiring zero-downtime configuration updates","Teams managing multiple MCP servers with frequent topology changes","DevOps teams using infrastructure-as-code to manage MCP server configurations","Organizations with strict uptime requirements for LLM agent platforms"],"limitations":["Configuration validation errors are logged but don't block server operation — invalid configs are silently skipped","File system events may be delayed on network-mounted filesystems (NFS, SMB) — not suitable for real-time config sync","No transaction semantics — partial configuration updates may leave system in inconsistent state if file write fails mid-operation","Reload latency depends on file system event propagation — typically 100-500ms delay between file write and configuration application"],"requires":["Python 3.9+","watchdog library for file system monitoring","Configuration file in YAML or JSON format","Write permissions to configuration directory"],"input_types":["Configuration files (YAML/JSON) with server definitions","File system events from watchdog"],"output_types":["Updated ServerManager state","Log entries for configuration changes","Validation errors (logged, not returned)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_4","uri":"capability://safety.moderation.jwt.based.authentication.and.bearer.token.validation","name":"jwt-based authentication and bearer token validation","description":"Magg implements a BearerAuthManager class that validates JWT tokens in HTTP requests and stdio connections, enforcing authentication before tool access. The system generates and validates bearer tokens with configurable expiration, supports multiple authentication backends, and integrates with the MCP protocol's authentication handshake. Authentication can be enabled per-server or globally, and tokens are validated on every tool call without caching.","intents":["I want to restrict MCP tool access to authenticated clients only","I need to issue temporary credentials to external teams for MCP server access","I want to audit which clients are accessing which tools","I need to revoke access immediately without waiting for token expiration"],"best_for":["Teams deploying MCP servers in multi-tenant environments","Organizations with strict security requirements for tool access","DevOps teams integrating MCP with existing identity management systems","Companies requiring audit trails for tool usage"],"limitations":["No built-in token revocation list — revoked tokens remain valid until expiration","JWT validation adds ~5-10ms latency per request due to cryptographic operations","No integration with external identity providers (OAuth2, SAML) — requires custom implementation","Token expiration is global — cannot set per-token or per-client expiration times","No rate limiting or throttling based on authentication identity"],"requires":["Python 3.9+","JWT library (PyJWT or similar)","Secret key for signing tokens (must be securely stored)","Configuration defining authentication requirements per server"],"input_types":["Bearer tokens in HTTP Authorization header","Authentication credentials for token generation"],"output_types":["JWT validation result (valid/invalid)","Token claims (user ID, expiration, scopes)","Authentication errors"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_5","uri":"capability://automation.workflow.kit.management.system.for.bundling.and.distributing.mcp.server.configurations","name":"kit management system for bundling and distributing mcp server configurations","description":"Magg provides a KitManager that packages MCP server definitions, tool configurations, and dependencies into distributable 'kits'. Kits are versioned bundles containing server startup commands, tool prefix mappings, authentication settings, and documentation. The system supports kit installation, updates, and removal through CLI commands, with automatic dependency resolution and configuration merging. Kits can be stored locally or fetched from remote repositories.","intents":["I want to package a set of MCP servers with their configurations as a reusable bundle","I need to distribute MCP server configurations across teams without manual setup","I want to version MCP server configurations and roll back to previous versions","I need to manage dependencies between MCP servers (e.g., server A requires server B)"],"best_for":["Teams building reusable MCP server packages for distribution","Organizations standardizing MCP deployments across multiple environments","DevOps teams managing MCP infrastructure as code","Open-source projects distributing MCP server bundles"],"limitations":["No built-in package registry — requires manual repository setup or GitHub releases","Dependency resolution is linear only — no support for complex version constraints or conflicts","Kit updates require manual configuration merge — no automatic conflict resolution for overlapping settings","No signature verification for remote kits — security depends on HTTPS and repository access control"],"requires":["Python 3.9+","KitManager implementation in magg.kit module","Kit definition files in YAML or JSON format","Network access for remote kit fetching (optional)"],"input_types":["Kit definition files (YAML/JSON)","Kit metadata (version, dependencies, checksums)"],"output_types":["Installed kit configurations","Merged server definitions","Installation logs and status"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_6","uri":"capability://tool.use.integration.message.routing.and.proxy.system.with.per.server.request.handling","name":"message routing and proxy system with per-server request handling","description":"Magg implements a message routing layer that intercepts MCP protocol messages, determines the target backend server based on tool name prefixes, and forwards requests to the appropriate ServerManager instance. The proxy maintains per-server connection state, handles response aggregation, and manages error handling for individual server failures. Routing decisions are made based on configurable prefix mappings (e.g., 'calc_' routes to calculator server), with fallback to default server if no prefix matches.","intents":["I want to route tool calls to different backend servers based on tool name prefixes","I need to handle failures in individual backend servers without affecting other servers","I want to aggregate responses from multiple servers into a single MCP response","I need to maintain separate connection state for each backend server"],"best_for":["Teams managing multiple specialized MCP servers with clear tool namespaces","Organizations requiring fault isolation between different tool categories","Developers building MCP proxy layers for complex tool ecosystems","DevOps teams deploying MCP servers with dynamic routing requirements"],"limitations":["Prefix-based routing requires careful naming conventions — ambiguous prefixes cause routing errors","No load balancing across multiple servers with same prefix — routes to first matching server only","Error handling is per-server — one server failure doesn't affect others but client sees partial tool availability","Routing logic is static after server startup — cannot dynamically change prefix mappings without reload"],"requires":["Python 3.9+","Prefix-to-server mapping configuration","Backend MCP servers running and accessible"],"input_types":["MCP tool call requests with tool names","Prefix mapping configuration"],"output_types":["Routed MCP requests to backend servers","Aggregated responses from backend servers","Error responses for routing failures"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_7","uri":"capability://automation.workflow.server.lifecycle.management.with.startup.shutdown.and.health.monitoring","name":"server lifecycle management with startup, shutdown, and health monitoring","description":"Magg's ServerManager class handles the complete lifecycle of backend MCP server connections: spawning processes (for stdio mode), establishing HTTP connections, monitoring health status, and graceful shutdown. The system tracks connection state, detects server crashes or disconnections, and implements automatic reconnection with exponential backoff. Health monitoring uses periodic heartbeat messages or HTTP health checks to detect unresponsive servers without blocking client requests.","intents":["I want to automatically start and stop MCP server processes as needed","I need to detect when a backend MCP server crashes and reconnect automatically","I want to monitor the health of multiple MCP servers without manual intervention","I need to gracefully shut down all backend servers when the aggregator stops"],"best_for":["Teams deploying MCP servers in containerized environments with automatic process management","Organizations requiring high availability for MCP tool access","DevOps teams building self-healing MCP infrastructure","Developers testing MCP server implementations with automatic restart"],"limitations":["Automatic reconnection adds latency (exponential backoff up to 30s) — not suitable for real-time tool access","Health monitoring is asynchronous — stale server state may be served to clients briefly after failure","No support for graceful server shutdown with in-flight request completion — requests may be interrupted","Reconnection logic is per-server — no coordination between servers for cascading failures"],"requires":["Python 3.9+","Server startup command or HTTP endpoint","Process management (for stdio mode) or network access (for HTTP mode)","Health check configuration (heartbeat interval, timeout)"],"input_types":["Server configuration (startup command, HTTP URL)","Health check parameters"],"output_types":["Server connection state (connected/disconnected/unhealthy)","Health check results","Reconnection logs"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_8","uri":"capability://text.generation.language.output.formatting.and.display.with.syntax.highlighting.and.structured.rendering","name":"output formatting and display with syntax highlighting and structured rendering","description":"MBRO implements an output formatting system that renders MCP tool responses with syntax highlighting, structured data formatting, and terminal-aware layout. The system detects response content types (JSON, text, binary), applies appropriate formatters, and uses ANSI color codes for syntax highlighting. Complex nested structures are formatted with indentation and collapsible sections, while binary data is displayed as hex dumps or base64 encoding. The formatter respects terminal width and wraps long lines appropriately.","intents":["I want to see tool responses formatted nicely in the terminal with syntax highlighting","I need to view complex nested JSON responses in a readable way","I want to see binary data (images, files) represented in a terminal-friendly format","I need to copy formatted output for documentation or sharing"],"best_for":["Developers debugging MCP tool responses interactively","Teams documenting MCP tool behavior with formatted examples","DevOps engineers troubleshooting MCP server issues","Solo developers exploring MCP tools for the first time"],"limitations":["Syntax highlighting is terminal-only — no export to HTML or Markdown with formatting","Large responses (>10MB) may cause terminal lag or memory issues","Binary data display is limited to hex/base64 — no inline image rendering in terminal","Color output requires ANSI-capable terminal — falls back to plain text on unsupported terminals"],"requires":["Python 3.9+","Terminal with ANSI color support (optional, falls back to plain text)","Sufficient terminal width for formatted output (80+ columns recommended)"],"input_types":["MCP tool responses (JSON, text, binary)","Response metadata (content type, size)"],"output_types":["Formatted terminal output with ANSI colors","Structured text representation of complex data","Hex/base64 representation of binary data"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-mbro__cap_9","uri":"capability://text.generation.language.advanced.input.features.with.command.parsing.and.argument.validation","name":"advanced input features with command parsing and argument validation","description":"MBRO implements a command processing system that parses user input into structured MCP tool calls, validates arguments against tool schemas, and provides helpful error messages for invalid input. The parser supports multiple input formats (natural language-like commands, JSON, YAML), performs type coercion based on schema definitions, and suggests corrections for typos or missing arguments. Input validation happens before sending requests to MCP servers, reducing round-trip latency for invalid calls.","intents":["I want to call MCP tools with natural language-like syntax without memorizing exact argument names","I need validation of tool arguments before sending requests to catch errors early","I want helpful error messages that suggest corrections for typos or missing arguments","I need to pass complex nested arguments (arrays, objects) in a user-friendly way"],"best_for":["Developers exploring MCP tools interactively without reading full documentation","Teams building user-friendly MCP interfaces with helpful error messages","Solo developers prototyping MCP workflows quickly","Non-technical users accessing MCP tools through natural language input"],"limitations":["Natural language parsing is heuristic-based — ambiguous input may be misinterpreted","Type coercion is schema-based only — no runtime type checking or validation","Error messages are generated locally — don't reflect server-side validation errors","Input parsing adds ~10-50ms latency per command due to schema introspection and validation"],"requires":["Python 3.9+","Tool schemas available from MCP server","Input parser implementation in MBRO"],"input_types":["Natural language-like commands","JSON/YAML formatted arguments","Interactive prompts for missing arguments"],"output_types":["Validated MCP tool call requests","Error messages with suggestions","Argument validation results"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":31,"verified":false,"data_access_risk":"high","permissions":["Python 3.9+","FastMCP framework for transport layer","Backend MCP servers running and accessible via stdio or HTTP","Configuration file defining server connections and tool prefixes","Terminal with ANSI color support","MCP server running and accessible via stdio or HTTP","Readline or similar for tab completion support","MCP server connection details (URL or startup command)","Authentication credentials per server (if required)","Magg installed and in PATH"],"failure_modes":["Tool name collisions across servers require manual prefix configuration — no automatic collision detection","Aggregation adds latency for each tool call due to message routing through proxy layer","No built-in load balancing or failover if a backend MCP server becomes unavailable","Resource management (files, memory) is per-server, not aggregated across the cluster","Tab completion requires full tool schema introspection on startup — adds 500ms+ latency for servers with 100+ tools","No persistent history across sessions unless manually configured","Output formatting is terminal-only — no export to structured formats (JSON, CSV)","Argument validation is schema-based only — no runtime type checking or coercion","Per-server state tracking adds memory overhead — not suitable for 100+ simultaneous server connections","Connection pooling is per-server — no global connection limit or resource management","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.5,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.52,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:03.578Z","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=mbro","compare_url":"https://unfragile.ai/compare?artifact=mbro"}},"signature":"1kY9HEtND3Fw0VLw1zH3+hP76hI6FQo5+8t4FBmW40ja4nMVftCy7jglrimNsP8fYTD/EwhwxVhET1ak/79oDQ==","signedAt":"2026-06-22T05:12:29.289Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mbro","artifact":"https://unfragile.ai/mbro","verify":"https://unfragile.ai/api/v1/verify?slug=mbro","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"}}