{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-pearch","slug":"pearch","name":"Pearch","type":"mcp","url":"https://github.com/Pearch-ai/mcp_pearch","page_url":"https://unfragile.ai/pearch","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-pearch__cap_0","uri":"capability://tool.use.integration.mcp.based.people.search.integration","name":"mcp-based people search integration","description":"Exposes Pearch's people search engine as an MCP (Model Context Protocol) server, allowing Claude and other MCP-compatible AI agents to query talent databases through standardized tool-calling interfaces. Implements MCP resource and tool schemas to abstract away HTTP API complexity, enabling agents to discover and filter people by skills, location, experience, and other professional attributes without direct API management.","intents":["I want my AI agent to search for candidates matching specific skill and location criteria without building custom API wrappers","I need to integrate talent discovery into an agentic workflow that runs alongside other MCP tools","I want to reduce boilerplate code for connecting Claude to a people search backend"],"best_for":["AI agent developers building recruitment or talent discovery workflows","Teams using Claude with MCP for multi-tool orchestration","Builders prototyping talent-sourcing agents that need standardized tool interfaces"],"limitations":["Dependent on Pearch's backend availability and rate limits — no local caching or fallback mechanism documented","MCP protocol overhead adds latency compared to direct HTTP calls; suitable for non-real-time discovery workflows","Search filtering capabilities limited to what Pearch's backend exposes; custom ranking or ML-based filtering not available in MCP layer"],"requires":["MCP-compatible client (Claude, or other MCP-supporting AI framework)","Network access to Pearch backend services","Python 3.8+ (typical for MCP server implementations)"],"input_types":["structured search parameters (skills, location, experience level, etc.)","free-form natural language queries (delegated to Claude for parsing)"],"output_types":["structured JSON profiles of matching candidates","ranked candidate lists with relevance scores"],"categories":["tool-use-integration","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-pearch__cap_1","uri":"capability://search.retrieval.talent.attribute.filtering.and.search","name":"talent attribute filtering and search","description":"Provides structured search capabilities to filter candidates by professional attributes including skills, geographic location, years of experience, job titles, and employment status. Implements query translation from natural language (via Claude) into Pearch's backend search API, supporting multi-field filtering and ranking by relevance. Abstracts backend search syntax so agents can express intent declaratively without learning Pearch's query language.","intents":["I want to find engineers in San Francisco with 5+ years of Python experience","I need to search for product managers with specific domain expertise (e.g., fintech, healthcare)","I want to filter candidates by availability status (actively looking vs passive)"],"best_for":["Recruiters and hiring managers using AI agents for candidate sourcing","Talent acquisition teams automating initial screening workflows","Builders creating specialized recruitment agents for niche skill sets"],"limitations":["Search accuracy depends on data quality and completeness in Pearch's index — incomplete profiles may be missed","No fuzzy matching or typo tolerance documented; exact skill name matching may fail for variations (e.g., 'JavaScript' vs 'JS')","Ranking algorithm opaque to the MCP layer; agents cannot customize scoring or apply custom business logic to results"],"requires":["Access to Pearch's people database (requires account/API credentials)","MCP client capable of parsing structured search parameters","Network connectivity to Pearch backend"],"input_types":["structured filter objects (skills array, location string, experience_years integer, etc.)","natural language queries (parsed by Claude into structured filters)"],"output_types":["ranked candidate profiles with match scores","structured metadata (name, title, location, skills, experience)"],"categories":["search-retrieval","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-pearch__cap_2","uri":"capability://planning.reasoning.agent.driven.candidate.discovery.workflow","name":"agent-driven candidate discovery workflow","description":"Enables multi-step agentic workflows where Claude or other MCP clients iteratively refine candidate searches, evaluate results, and trigger follow-up actions (e.g., outreach, profile deep-dives). Implements tool composition patterns where search results feed into downstream tools, allowing agents to autonomously discover candidates, assess fit, and prepare recruitment actions without human intervention between steps.","intents":["I want an AI agent to autonomously search for candidates, evaluate their fit against job requirements, and generate outreach messages","I need to run a multi-stage candidate discovery pipeline where initial search results are refined based on profile analysis","I want to automate the candidate sourcing phase of recruitment so my team focuses on evaluation and negotiation"],"best_for":["Recruitment teams automating end-to-end sourcing workflows","Talent acquisition platforms integrating Pearch as a discovery layer","Builders creating autonomous recruiting agents that operate with minimal human oversight"],"limitations":["Agent autonomy introduces risk of inappropriate outreach or bias in candidate selection — requires guardrails and human review gates","Multi-step workflows add latency; not suitable for real-time candidate discovery (e.g., live hiring events)","No built-in persistence or state management — agents cannot resume interrupted workflows without external orchestration"],"requires":["MCP-compatible agentic framework (Claude with tool use, or equivalent)","Integration with downstream tools (email, CRM, or communication platforms) for outreach actions","Pearch API credentials and account with sufficient quota for multi-step searches"],"input_types":["job requirements (skills, location, experience level)","candidate evaluation criteria (must-haves, nice-to-haves)","outreach templates or communication preferences"],"output_types":["ranked candidate lists with fit assessments","generated outreach messages or recruitment actions","workflow execution logs and decision traces"],"categories":["planning-reasoning","automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-pearch__cap_3","uri":"capability://text.generation.language.natural.language.to.structured.search.translation","name":"natural language to structured search translation","description":"Translates free-form natural language queries (e.g., 'Find senior backend engineers in NYC who know Rust') into structured search parameters (skills array, location, experience level) that Pearch's backend can execute. Leverages Claude's language understanding to parse intent, extract entities, and map them to Pearch's searchable attributes. Handles ambiguity resolution (e.g., 'NYC' → location filter) and skill name normalization without requiring users to learn Pearch's query syntax.","intents":["I want to search for candidates using conversational language without learning the backend's filter syntax","I need to extract structured search criteria from a job description or hiring brief","I want to handle variations in how skills are named (e.g., 'JavaScript' vs 'JS' vs 'Node.js')"],"best_for":["Non-technical recruiters who prefer natural language over structured queries","Builders creating conversational recruiting interfaces","Teams integrating Pearch into chatbot or voice-based hiring workflows"],"limitations":["Translation accuracy depends on Claude's entity extraction; ambiguous queries may be misinterpreted (e.g., 'Python' as location vs language)","No feedback loop to correct misinterpretations — failed searches require manual query reformulation","Skill name normalization relies on Pearch's index; unmapped or niche skills may not match despite correct intent"],"requires":["Claude or equivalent LLM with strong entity extraction capabilities","Pearch skill taxonomy or mapping table for normalization","MCP client capable of passing natural language to the translation layer"],"input_types":["free-form natural language strings","job descriptions or hiring briefs","conversational queries"],"output_types":["structured filter objects (skills, location, experience_years, etc.)","confidence scores for extracted entities","clarification prompts for ambiguous inputs"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-pearch__cap_4","uri":"capability://memory.knowledge.candidate.profile.enrichment.and.context.injection","name":"candidate profile enrichment and context injection","description":"Retrieves and enriches candidate profiles with additional context (employment history, portfolio links, social profiles) from Pearch's database, then injects this context into Claude's conversation for deeper analysis. Enables agents to make informed decisions about candidate fit by providing comprehensive professional background without requiring separate API calls or manual profile lookups. Implements context windowing to balance information richness with token efficiency.","intents":["I want to evaluate a candidate's fit by reviewing their full employment history and skill progression","I need to generate personalized outreach messages based on a candidate's specific background and achievements","I want to identify candidates with relevant portfolio or open-source contributions"],"best_for":["Recruiters evaluating candidate quality before outreach","Builders creating candidate evaluation agents","Teams generating personalized recruitment communications"],"limitations":["Profile completeness varies; some candidates may have sparse or outdated information in Pearch's index","Context injection adds token overhead — large profiles may exceed Claude's context window or increase API costs","Privacy considerations: enriched profiles contain PII; workflows must implement appropriate access controls and data handling"],"requires":["Pearch API access with profile retrieval endpoints","Claude or equivalent LLM with sufficient context window","Compliance framework for handling candidate PII"],"input_types":["candidate IDs or identifiers from search results","enrichment parameters (which fields to include)"],"output_types":["enriched candidate profiles with employment history, skills, portfolio links","structured metadata suitable for downstream analysis","context-injected conversation state for agent decision-making"],"categories":["memory-knowledge","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":24,"verified":false,"data_access_risk":"high","permissions":["MCP-compatible client (Claude, or other MCP-supporting AI framework)","Network access to Pearch backend services","Python 3.8+ (typical for MCP server implementations)","Access to Pearch's people database (requires account/API credentials)","MCP client capable of parsing structured search parameters","Network connectivity to Pearch backend","MCP-compatible agentic framework (Claude with tool use, or equivalent)","Integration with downstream tools (email, CRM, or communication platforms) for outreach actions","Pearch API credentials and account with sufficient quota for multi-step searches","Claude or equivalent LLM with strong entity extraction capabilities"],"failure_modes":["Dependent on Pearch's backend availability and rate limits — no local caching or fallback mechanism documented","MCP protocol overhead adds latency compared to direct HTTP calls; suitable for non-real-time discovery workflows","Search filtering capabilities limited to what Pearch's backend exposes; custom ranking or ML-based filtering not available in MCP layer","Search accuracy depends on data quality and completeness in Pearch's index — incomplete profiles may be missed","No fuzzy matching or typo tolerance documented; exact skill name matching may fail for variations (e.g., 'JavaScript' vs 'JS')","Ranking algorithm opaque to the MCP layer; agents cannot customize scoring or apply custom business logic to results","Agent autonomy introduces risk of inappropriate outreach or bias in candidate selection — requires guardrails and human review gates","Multi-step workflows add latency; not suitable for real-time candidate discovery (e.g., live hiring events)","No built-in persistence or state management — agents cannot resume interrupted workflows without external orchestration","Translation accuracy depends on Claude's entity extraction; ambiguous queries may be misinterpreted (e.g., 'Python' as location vs language)","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.2,"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":"2026-06-17T09:51:03.579Z","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=pearch","compare_url":"https://unfragile.ai/compare?artifact=pearch"}},"signature":"qLTrAB2WSIGrio9IVsiimaAcfxXt58O/ERJgX7TUUbzkHCepZ3gXykyFs+CrRZ3nDr+4+hQsmjVvyTbwFNCCAg==","signedAt":"2026-06-22T15:25:21.632Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/pearch","artifact":"https://unfragile.ai/pearch","verify":"https://unfragile.ai/api/v1/verify?slug=pearch","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"}}