{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-everything-search","slug":"everything-search","name":"Everything Search","type":"mcp","url":"https://github.com/mamertofabian/mcp-everything-search","page_url":"https://unfragile.ai/everything-search","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-everything-search__cap_0","uri":"capability://search.retrieval.cross.platform.unified.file.search.with.platform.native.backends","name":"cross-platform unified file search with platform-native backends","description":"Implements a SearchProvider abstraction pattern that routes search requests to platform-specific implementations: Windows Everything SDK for indexed full-text search, macOS Spotlight via mdfind subprocess for metadata-aware search, and Linux locate/plocate for filename indexing. The MCP server normalizes heterogeneous result formats into a unified SearchResult data model, allowing clients like Claude Desktop to issue a single search query that adapts to the host OS without knowing platform details.","intents":["I need to search for files across my entire filesystem from an AI agent without platform-specific code","I want to leverage the fastest native search tool available on my OS (Everything on Windows, Spotlight on macOS, locate on Linux)","I need consistent search result formatting regardless of which OS my agent runs on"],"best_for":["AI agent developers building cross-platform tools in Claude Desktop or other MCP clients","Teams deploying LLM-powered file discovery tools across Windows, macOS, and Linux environments","Developers who need sub-millisecond file search performance without implementing OS-specific code"],"limitations":["Windows requires Everything service running and SDK DLL installed; search quality depends on Everything's indexing state","macOS Spotlight search may be slow on first run if index is rebuilding; no control over indexing frequency","Linux locate/plocate requires manual database updates via updatedb; cannot search files added since last index refresh","Query syntax differs per platform (Windows supports regex/operators, macOS supports metadata queries, Linux supports glob patterns only)","Result ordering varies by platform; sort_by parameter (1-14) maps differently across backends"],"requires":["Python 3.9+","Windows: Everything SDK installed, Everything service running, ES_QUERY_TIMEOUT environment variable configured","macOS: mdfind command-line tool (included in macOS)","Linux: locate or plocate package installed, updatedb run at least once","MCP-compatible client (Claude Desktop, custom MCP client, etc.)"],"input_types":["string (search query with platform-specific syntax)","integer (max_results, sort_by)","boolean (match_path, match_case, match_whole_word, match_regex)","object (platform_params for Windows-specific options)"],"output_types":["structured SearchResult array with normalized fields: path, name, size, modified_time, is_directory, match_type"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_1","uri":"capability://search.retrieval.windows.everything.sdk.integration.with.advanced.query.syntax","name":"windows everything sdk integration with advanced query syntax","description":"Wraps the Windows Everything SDK C library through Python bindings to execute full-text indexed searches with support for advanced query operators (wildcards, boolean operators, date/size filters, regex patterns). The WindowsSearchProvider translates normalized search parameters into Everything query syntax, executes queries via the SDK, and maps Everything result objects (with fields like path, size, modified_time, attributes) into the unified SearchResult format. Queries execute against Everything's real-time index, providing sub-millisecond latency on indexed content.","intents":["I need to search for files by name, content metadata, date range, or file size on Windows with sub-millisecond latency","I want to use Everything's advanced query syntax (e.g., 'ext:pdf size:>10MB modified:today') through an MCP interface","I need to configure query timeout and other Windows-specific search parameters for my use case"],"best_for":["Windows developers building file discovery agents that need extreme speed","Teams using Claude Desktop on Windows who want to leverage Everything's indexed search","Power users familiar with Everything query syntax who want to expose that capability to AI agents"],"limitations":["Requires Everything service to be running; if service is stopped, all searches fail","Search results only include files indexed by Everything; newly created files may not appear until Everything re-indexes","Everything SDK DLL must be installed and accessible; adds Windows-specific dependency","Query timeout is global (ES_QUERY_TIMEOUT env var); cannot set per-query timeout","No built-in support for searching file contents; only filename and metadata search"],"requires":["Windows OS (7 or later)","Everything application installed (free, from voidtools.com)","Everything SDK DLL in system PATH or specified location","ES_QUERY_TIMEOUT environment variable set (e.g., '5000' for 5 seconds)","Everything service running (typically auto-starts)"],"input_types":["string (Everything query syntax: wildcards *, ?, regex, operators like AND/OR/NOT, filters like ext:, size:, modified:, attributes:)","integer (max_results to limit output)","boolean (match_case, match_whole_word, match_regex)","object (platform_params for Windows-specific options like sort_by 1-14)"],"output_types":["structured SearchResult array with fields: path (full path), name (filename), size (bytes), modified_time (ISO 8601), is_directory (boolean), match_type (filename/path)"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_2","uri":"capability://search.retrieval.macos.spotlight.search.via.mdfind.subprocess.with.metadata.queries","name":"macos spotlight search via mdfind subprocess with metadata queries","description":"Implements MacSearchProvider that spawns mdfind (macOS Spotlight command-line interface) as a subprocess to execute metadata-aware searches. Translates normalized search parameters into mdfind query syntax, captures subprocess output, parses results, and normalizes them into SearchResult format. Supports Spotlight's metadata query capabilities (e.g., searching by file kind, creation date, author) in addition to filename/content search. Results reflect Spotlight's indexed metadata, providing fast search on macOS without requiring additional indexing infrastructure.","intents":["I need to search files on macOS using Spotlight's metadata indexing without installing additional tools","I want to search by file metadata (kind, creation date, author) through an MCP interface on macOS","I need consistent search results across macOS systems without worrying about Spotlight index state"],"best_for":["macOS developers building file discovery agents who want native Spotlight integration","Teams using Claude Desktop on macOS who want to leverage built-in Spotlight indexing","Organizations standardizing on macOS where Spotlight is always available"],"limitations":["Spotlight index may be rebuilding after system updates or large file changes, causing slow searches","mdfind subprocess overhead adds ~50-200ms latency per search compared to direct SDK calls","No control over Spotlight indexing frequency or index refresh timing","Metadata query syntax is Spotlight-specific and less powerful than Everything's query language","Results may be incomplete if Spotlight indexing is disabled for certain volumes or folders"],"requires":["macOS (10.4 or later)","mdfind command-line tool (included in all macOS versions)","Spotlight indexing enabled for target volumes"],"input_types":["string (search query with Spotlight syntax: filename patterns, metadata queries like 'kind:pdf', 'created:today')","integer (max_results to limit output)","boolean (match_case, match_whole_word, match_regex)"],"output_types":["structured SearchResult array with fields: path (full path), name (filename), size (bytes), modified_time (ISO 8601), is_directory (boolean)"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_3","uri":"capability://search.retrieval.linux.locate.plocate.filename.search.with.pattern.matching","name":"linux locate/plocate filename search with pattern matching","description":"Implements LinuxSearchProvider that executes locate or plocate commands via subprocess to search a pre-built filename database. Translates normalized search parameters into locate/plocate syntax (glob patterns, regex), captures subprocess output, parses results, and normalizes into SearchResult format. The locate database is maintained by the updatedb command (typically run daily via cron) and provides extremely fast filename-only search without requiring real-time indexing. Falls back to plocate (faster variant) if available, otherwise uses locate.","intents":["I need to search for files on Linux systems using the fast locate database without installing additional tools","I want to search by filename pattern (glob or regex) on Linux through an MCP interface","I need to integrate file search into Linux-based AI agents with minimal dependencies"],"best_for":["Linux developers building file discovery agents who want lightweight, fast search","Teams deploying MCP servers on Linux servers where locate is standard","Organizations with daily updatedb cron jobs who want to leverage existing locate infrastructure"],"limitations":["locate database is only as fresh as the last updatedb run (typically daily); newly created files won't appear until next update","Search is filename-only; cannot search file contents or metadata like size/date","No built-in support for complex queries; limited to glob patterns and basic regex","Database may not include all mounted filesystems if updatedb is configured to skip certain paths","plocate availability varies by Linux distribution; fallback to locate may be slower"],"requires":["Linux OS","locate or plocate package installed (mlocate or plocate package, depending on distribution)","updatedb command run at least once to build initial database","Cron job or systemd timer running updatedb periodically (typically daily)"],"input_types":["string (search query with glob patterns or regex syntax supported by locate/plocate)","integer (max_results to limit output)","boolean (match_case, match_regex)"],"output_types":["structured SearchResult array with fields: path (full path), name (filename), is_directory (boolean inferred from path)"],"categories":["search-retrieval","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_4","uri":"capability://tool.use.integration.mcp.protocol.server.implementation.with.stdio.based.communication","name":"mcp protocol server implementation with stdio-based communication","description":"Implements an MCP (Model Context Protocol) server that exposes the search tool through stdio-based bidirectional communication. The server handles MCP protocol framing, tool registration, parameter validation, and result serialization. Clients (like Claude Desktop) communicate with the server by sending JSON-RPC requests over stdin/stdout, and the server responds with tool results. The server detects the host platform at startup and initializes the appropriate SearchProvider backend, maintaining a single search tool interface across all platforms.","intents":["I need to integrate file search into Claude Desktop or other MCP clients without custom protocol implementation","I want to expose a search tool to LLM agents through the standard MCP protocol","I need a server that auto-detects my OS and routes search requests to the appropriate backend"],"best_for":["Claude Desktop users who want to add file search capability to their AI agent","Developers building MCP-compatible tools who need a reference implementation of MCP server patterns","Teams deploying LLM agents that need standardized file search across multiple machines"],"limitations":["Stdio-based communication adds latency compared to direct library calls; not suitable for real-time interactive search","Server process must remain running for the entire duration of client use; no connection pooling or persistence","MCP protocol overhead adds ~10-50ms per request for serialization/deserialization","Single search tool only; cannot extend with additional tools without modifying server code","No built-in authentication or access control; assumes trusted client environment"],"requires":["Python 3.9+","mcp package (Python MCP SDK)","Platform-specific search backend installed (Everything SDK on Windows, mdfind on macOS, locate on Linux)","MCP-compatible client (Claude Desktop, custom MCP client, etc.)"],"input_types":["JSON-RPC requests with tool name 'search' and parameters: query (string), max_results (integer), match_path (boolean), match_case (boolean), match_whole_word (boolean), match_regex (boolean), sort_by (integer), platform_params (object)"],"output_types":["JSON-RPC responses with SearchResult array serialized as JSON"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_5","uri":"capability://data.processing.analysis.normalized.search.result.formatting.and.schema.validation","name":"normalized search result formatting and schema validation","description":"Implements a SearchResult data model that normalizes heterogeneous results from Windows Everything SDK, macOS mdfind, and Linux locate into a unified schema with fields: path (full filesystem path), name (filename only), size (bytes, null if unavailable), modified_time (ISO 8601 string, null if unavailable), is_directory (boolean), match_type (string: 'filename' or 'path'). Each platform provider maps its native result format to this schema before returning to the client. The schema includes validation to ensure all results conform to expected types and formats.","intents":["I need consistent search result formatting regardless of which OS my search runs on","I want to parse search results in my agent without handling platform-specific result formats","I need to validate that search results contain expected fields before processing them"],"best_for":["AI agent developers who need predictable result formats for downstream processing","Teams building cross-platform tools that must handle results uniformly","Developers who want to avoid platform-specific result parsing logic"],"limitations":["Some fields are null on certain platforms (e.g., size is unavailable from Linux locate)","Timestamp precision varies by platform (Windows: 100-nanosecond resolution, macOS/Linux: second resolution)","match_type field is inferred from search parameters, not always accurate across platforms","Schema is read-only; clients cannot customize result fields or add platform-specific metadata"],"requires":["Python 3.9+ with dataclass or Pydantic support","Platform-specific result objects from SearchProvider implementations"],"input_types":["platform-native result objects (Everything SDK result objects, mdfind output strings, locate output strings)"],"output_types":["SearchResult dataclass/Pydantic model with fields: path (str), name (str), size (int | null), modified_time (str | null), is_directory (bool), match_type (str)"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_6","uri":"capability://data.processing.analysis.parameter.translation.and.query.syntax.adaptation","name":"parameter translation and query syntax adaptation","description":"Implements parameter translation logic that converts normalized MCP search parameters (query string, max_results, match_case, match_whole_word, match_regex, sort_by) into platform-specific query syntax. Each SearchProvider subclass translates these parameters into the native query language: Windows Everything query syntax (operators, filters, regex), macOS mdfind syntax (metadata queries, glob patterns), or Linux locate/plocate syntax (glob patterns, regex). The translation layer handles incompatibilities (e.g., regex support varies by platform) and falls back to safe defaults when a parameter is unsupported on a given platform.","intents":["I want to issue the same search parameters across Windows, macOS, and Linux without learning platform-specific query syntax","I need to know which search parameters are supported on each platform and what happens when I use unsupported parameters","I want to use regex search on all platforms, even though Linux locate has limited regex support"],"best_for":["Cross-platform agent developers who want to abstract query syntax differences","Teams deploying agents on multiple OSes who need consistent parameter handling","Developers who want to avoid platform-specific conditional logic in their agents"],"limitations":["Some parameters are ignored on certain platforms (e.g., match_whole_word is not supported by Linux locate)","Regex support varies: Windows Everything supports full regex, macOS mdfind has limited regex, Linux locate has basic regex","sort_by parameter (1-14) maps differently across platforms; no guarantee of consistent sort order","match_regex and match_whole_word may be mutually exclusive on some platforms, causing silent parameter conflicts","No error reporting when unsupported parameters are used; they are silently ignored"],"requires":["Python 3.9+","Platform-specific query syntax knowledge (Everything syntax, mdfind syntax, locate syntax)","SearchProvider subclass implementation for each platform"],"input_types":["normalized parameters: query (str), max_results (int), match_path (bool), match_case (bool), match_whole_word (bool), match_regex (bool), sort_by (int), platform_params (dict)"],"output_types":["platform-specific query strings and subprocess arguments"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-everything-search__cap_7","uri":"capability://automation.workflow.platform.detection.and.dynamic.searchprovider.initialization","name":"platform detection and dynamic searchprovider initialization","description":"Implements platform detection logic that runs at MCP server startup to identify the host OS (Windows, macOS, or Linux) and instantiate the appropriate SearchProvider subclass (WindowsSearchProvider, MacSearchProvider, or LinuxSearchProvider). Uses Python's sys.platform or platform.system() to detect OS, then initializes the corresponding provider with any required configuration (e.g., Everything SDK path on Windows). The initialized provider is stored as a module-level singleton and reused for all subsequent search requests, avoiding repeated platform detection overhead.","intents":["I want the MCP server to automatically detect my OS and use the best search backend without manual configuration","I need the server to fail gracefully if the required search backend is not installed on my OS","I want to deploy the same MCP server binary across Windows, macOS, and Linux without platform-specific configuration"],"best_for":["Teams deploying MCP servers across heterogeneous OS environments","Developers who want zero-configuration MCP server setup","Organizations standardizing on a single MCP server binary for all platforms"],"limitations":["Platform detection happens once at startup; changing OS (e.g., via VM migration) requires server restart","If required search backend is not installed, server initialization fails with an error; no fallback to alternative backends","Platform detection is based on sys.platform, which may be inaccurate in some virtualization environments","No support for cross-platform search (e.g., searching Windows files from a macOS client); each server instance is OS-specific"],"requires":["Python 3.9+","sys.platform or platform.system() available","Platform-specific search backend installed (Everything SDK on Windows, mdfind on macOS, locate on Linux)"],"input_types":["none (platform detection is automatic)"],"output_types":["initialized SearchProvider instance (WindowsSearchProvider, MacSearchProvider, or LinuxSearchProvider)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":26,"verified":false,"data_access_risk":"high","permissions":["Python 3.9+","Windows: Everything SDK installed, Everything service running, ES_QUERY_TIMEOUT environment variable configured","macOS: mdfind command-line tool (included in macOS)","Linux: locate or plocate package installed, updatedb run at least once","MCP-compatible client (Claude Desktop, custom MCP client, etc.)","Windows OS (7 or later)","Everything application installed (free, from voidtools.com)","Everything SDK DLL in system PATH or specified location","ES_QUERY_TIMEOUT environment variable set (e.g., '5000' for 5 seconds)","Everything service running (typically auto-starts)"],"failure_modes":["Windows requires Everything service running and SDK DLL installed; search quality depends on Everything's indexing state","macOS Spotlight search may be slow on first run if index is rebuilding; no control over indexing frequency","Linux locate/plocate requires manual database updates via updatedb; cannot search files added since last index refresh","Query syntax differs per platform (Windows supports regex/operators, macOS supports metadata queries, Linux supports glob patterns only)","Result ordering varies by platform; sort_by parameter (1-14) maps differently across backends","Requires Everything service to be running; if service is stopped, all searches fail","Search results only include files indexed by Everything; newly created files may not appear until Everything re-indexes","Everything SDK DLL must be installed and accessible; adds Windows-specific dependency","Query timeout is global (ES_QUERY_TIMEOUT env var); cannot set per-query timeout","No built-in support for searching file contents; only filename and metadata search","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.26,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.52,"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":"2026-06-17T09:51:03.039Z","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=everything-search","compare_url":"https://unfragile.ai/compare?artifact=everything-search"}},"signature":"uHtS6xgDbK6fz5pMltHOVl3/ytIDkYpB5eRl480ldUWNwbvdODPD/S7MytHlH6ki25bLsJBI6XuqTLrELaqoBw==","signedAt":"2026-06-19T22:50:09.257Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/everything-search","artifact":"https://unfragile.ai/everything-search","verify":"https://unfragile.ai/api/v1/verify?slug=everything-search","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"}}