{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-peliqan","slug":"peliqan","name":"Peliqan","type":"mcp","url":"https://github.com/Peliqan-io/mcp-server-peliqan","page_url":"https://unfragile.ai/peliqan","categories":["mcp-servers","data-pipelines"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-peliqan__cap_0","uri":"capability://tool.use.integration.multi.source.business.application.data.connector.via.mcp","name":"multi-source business application data connector via mcp","description":"Peliqan exposes a Model Context Protocol (MCP) server that enables Claude and other LLM clients to connect to and query data from multiple business applications (ERP, CRM, Accounting systems, etc.) without direct API integration. The MCP server acts as a unified gateway, translating LLM tool calls into application-specific API requests and returning structured results back to the model, enabling conversational data access across heterogeneous enterprise systems.","intents":["Query sales data from Salesforce, inventory from NetSuite, and accounting records from QuickBooks in a single conversation","Build an AI agent that can fetch customer information from CRM and cross-reference with accounting data to answer business questions","Enable Claude to access business data without exposing raw API credentials or requiring custom integration code","Create a unified data interface for multiple business applications without building separate connectors"],"best_for":["Teams building AI agents that need access to multiple business data sources","Non-technical business users who want conversational access to enterprise data","Developers integrating Claude with existing business application stacks","Organizations standardizing on MCP for LLM-to-tool integration"],"limitations":["Requires Peliqan platform account and configuration of business application credentials","Latency depends on underlying business application API response times (typically 500ms-5s per query)","Limited to data sources that Peliqan has pre-built connectors for; custom data sources require additional setup","Query complexity and result size constrained by MCP message size limits and LLM context windows","No built-in caching of frequently accessed data — each query hits the source system"],"requires":["Peliqan platform account with configured business application connectors","MCP-compatible LLM client (Claude via Claude Desktop, or custom MCP client)","Valid API credentials for target business applications (Salesforce, NetSuite, QuickBooks, etc.)","Network connectivity to Peliqan platform and target business applications"],"input_types":["natural language queries from LLM","structured MCP tool call parameters","business application identifiers (customer ID, order ID, etc.)"],"output_types":["structured JSON data from business applications","formatted query results","error messages with diagnostic context"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_1","uri":"capability://data.processing.analysis.built.in.data.warehouse.with.etl.pipeline.execution","name":"built-in data warehouse with etl pipeline execution","description":"Peliqan provides an integrated data warehouse that automatically ingests, transforms, and stores data from connected business applications through configurable ETL pipelines. The platform handles schema management, data normalization, and incremental updates, allowing users to query consolidated business data via SQL or through the MCP interface without managing separate data infrastructure like Snowflake or BigQuery.","intents":["Consolidate data from multiple business applications into a single queryable warehouse without managing separate infrastructure","Run scheduled ETL jobs that sync CRM, ERP, and accounting data on a daily or hourly basis","Query historical business data and trends across multiple systems using SQL","Enable LLMs to access pre-aggregated, normalized business data for faster and more reliable responses"],"best_for":["Small to mid-market companies without dedicated data engineering teams","Organizations wanting to consolidate business data without managing cloud data warehouse infrastructure","Teams building AI agents that need reliable, up-to-date business data without real-time API latency","Non-technical business users who want to query business data without SQL knowledge"],"limitations":["Data warehouse capacity and query performance depend on Peliqan's infrastructure tier (pricing-dependent)","ETL pipeline latency means data is not real-time; typical sync intervals are hourly or daily","Schema conflicts between source systems require manual resolution or custom transformation logic","Limited SQL dialect support — may not support all advanced SQL features available in Snowflake or BigQuery","No built-in data lineage or audit logging for compliance-heavy industries"],"requires":["Peliqan platform account with data warehouse tier enabled","Configured connectors for source business applications","ETL pipeline definitions (can be created via UI or API)","Sufficient data warehouse quota for expected data volume"],"input_types":["business application data via configured connectors","ETL transformation rules (SQL, mapping definitions)","SQL queries against warehouse tables"],"output_types":["normalized, consolidated data tables","query results in JSON or CSV format","ETL execution logs and status"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_10","uri":"capability://data.processing.analysis.data.transformation.and.enrichment.during.etl","name":"data transformation and enrichment during etl","description":"Peliqan supports custom data transformations during ETL pipeline execution, including field mapping, data type conversion, filtering, aggregation, and enrichment with external data. Transformations can be defined using SQL, JavaScript, or visual mapping tools, enabling complex data preparation without requiring separate transformation tools like dbt.","intents":["Convert customer names from 'LASTNAME, FIRSTNAME' format in one system to 'FIRSTNAME LASTNAME' in the warehouse","Filter out test records from Salesforce before syncing to the warehouse","Enrich customer data with external data sources (e.g., company size, industry) during sync","Aggregate order data by customer and month for faster analytical queries"],"best_for":["Teams needing data preparation without managing separate transformation tools","Organizations with complex data mapping requirements across business applications","Developers building data pipelines that require custom business logic","Companies wanting to keep transformation logic close to data synchronization"],"limitations":["Transformation performance depends on complexity — complex transformations may slow ETL pipelines","Limited transformation language expressiveness compared to full programming languages","No built-in data quality validation or testing framework for transformations","Debugging complex transformations is difficult without detailed execution logs","No version control or testing for transformation logic — changes may break pipelines"],"requires":["Peliqan platform account with ETL pipeline configuration","Knowledge of SQL, JavaScript, or visual mapping tools for transformation definition","Understanding of source and target data schemas"],"input_types":["raw data from source business applications","transformation rules (SQL, JavaScript, or visual mappings)","external data sources for enrichment"],"output_types":["transformed and enriched data","transformation execution logs","error messages for failed transformations"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_2","uri":"capability://data.processing.analysis.sql.based.querying.of.consolidated.business.data","name":"sql-based querying of consolidated business data","description":"Peliqan exposes a SQL query interface that allows users and LLMs to run SQL queries against the built-in data warehouse containing consolidated data from multiple business applications. The query engine supports standard SQL syntax and returns results in structured formats (JSON, CSV), enabling both programmatic access via MCP and direct user queries through the Peliqan UI.","intents":["Write SQL queries to analyze business metrics across multiple data sources (e.g., total revenue by customer across CRM and accounting)","Enable Claude to execute complex analytical queries and return results for business intelligence tasks","Create reusable SQL queries for common business questions without rebuilding queries each time","Export business data in standard formats for further analysis in BI tools or spreadsheets"],"best_for":["Data analysts and business intelligence teams familiar with SQL","Developers building LLM agents that need to execute analytical queries","Organizations wanting to standardize on SQL for data access across business applications","Teams migrating from multiple data sources to a unified query interface"],"limitations":["SQL query performance depends on data warehouse indexing and query optimization — complex joins across large tables may be slow","No support for advanced analytics features like window functions or CTEs (depends on underlying SQL engine)","Query results limited by LLM context window when returned to Claude (typically 100K tokens)","No built-in query optimization or cost estimation — expensive queries may consume significant resources","Limited support for real-time data — queries return warehouse snapshot, not live application data"],"requires":["Peliqan platform account with data warehouse enabled","SQL knowledge or ability to write/understand SQL queries","Data warehouse populated with consolidated business data via ETL pipelines","MCP client or direct API access to execute queries"],"input_types":["SQL query strings","query parameters (for parameterized queries)","table and column names from consolidated warehouse schema"],"output_types":["structured query results (JSON, CSV)","query execution metadata (rows returned, execution time)","error messages with SQL diagnostic context"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_3","uri":"capability://data.processing.analysis.automatic.business.application.schema.discovery.and.mapping","name":"automatic business application schema discovery and mapping","description":"Peliqan automatically discovers and maps schemas from connected business applications (ERP, CRM, Accounting systems), normalizing field names, data types, and relationships into a unified schema representation. This enables the platform to handle schema changes in source systems and present a consistent data model to users and LLMs without manual schema maintenance.","intents":["Automatically detect new fields or tables added to Salesforce or NetSuite without manual configuration","Normalize inconsistent field naming across multiple business applications (e.g., 'customer_id' vs 'cust_id') into a unified schema","Enable LLMs to discover available data fields and relationships without requiring manual documentation","Handle schema evolution in source systems without breaking existing queries or integrations"],"best_for":["Organizations with multiple business applications that evolve frequently","Teams without dedicated data engineers to manually maintain schema mappings","Developers building LLM agents that need to adapt to changing data schemas","Companies standardizing on Peliqan for data consolidation across heterogeneous systems"],"limitations":["Schema discovery latency — may take minutes to hours to detect schema changes in source systems","Complex custom fields or non-standard data types in business applications may not map correctly","Schema conflicts between source systems (e.g., same field name with different meanings) require manual resolution","No built-in schema versioning — difficult to track schema changes over time or rollback to previous schemas","Limited support for nested or hierarchical data structures common in modern APIs"],"requires":["Peliqan platform account with configured business application connectors","Valid API credentials for target business applications","Sufficient permissions in source systems to read schema metadata"],"input_types":["business application metadata (schema, field definitions, relationships)","manual schema mapping rules (for conflict resolution)"],"output_types":["unified schema representation","field mappings between source and warehouse schemas","schema change notifications"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_4","uri":"capability://automation.workflow.incremental.data.synchronization.with.change.tracking","name":"incremental data synchronization with change tracking","description":"Peliqan implements incremental ETL synchronization that tracks changes in source business applications (using timestamps, change logs, or API cursors) and only syncs modified records to the data warehouse. This reduces API calls, network bandwidth, and warehouse storage costs compared to full table scans, while keeping data relatively fresh through scheduled sync intervals.","intents":["Sync only changed customer records from Salesforce since the last sync, rather than re-fetching all customers","Reduce API rate limit consumption by syncing only modified orders from e-commerce platforms","Keep business data warehouse up-to-date with minimal infrastructure cost and latency","Enable near-real-time data availability for LLM agents without full table refreshes"],"best_for":["Organizations with large business application datasets (millions of records) where full syncs are prohibitively expensive","Teams with strict API rate limits from business applications","Companies wanting to minimize data warehouse storage and compute costs","Developers building LLM agents that need fresh data without real-time latency"],"limitations":["Incremental sync accuracy depends on source system change tracking capabilities — some systems lack reliable change logs","Sync latency means data is not real-time; typical intervals are 15 minutes to 1 hour","Handling of deleted records requires special logic — some systems don't provide reliable deletion tracking","Schema changes in source systems may break incremental sync logic and require manual intervention","No built-in conflict resolution for concurrent updates to the same record in source and warehouse"],"requires":["Peliqan platform account with ETL pipeline configuration","Source business applications with reliable change tracking (timestamps, change logs, or API cursors)","Configured sync schedules and incremental sync rules"],"input_types":["change tracking metadata from source systems (timestamps, change logs, cursors)","incremental sync configuration (which fields to track, sync intervals)"],"output_types":["incremental data updates to warehouse","sync execution logs with change counts","sync status and error notifications"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_5","uri":"capability://tool.use.integration.mcp.tool.definition.generation.from.business.application.schemas","name":"mcp tool definition generation from business application schemas","description":"Peliqan automatically generates MCP tool definitions from discovered business application schemas, creating callable functions that LLMs can invoke to query specific data sources. The tool definitions include parameter schemas, descriptions, and return types, enabling Claude and other LLM clients to understand and call business data queries without manual tool definition.","intents":["Automatically expose Salesforce customer lookup, order history, and opportunity data as callable MCP tools","Enable Claude to discover available data queries by inspecting MCP tool definitions without manual documentation","Generate parameterized query tools that accept user inputs (e.g., customer ID) and return relevant data","Reduce manual effort in defining LLM tools by auto-generating from business application schemas"],"best_for":["Developers building LLM agents that need to query multiple business applications","Teams wanting to minimize manual tool definition overhead","Organizations standardizing on MCP for LLM-to-tool integration","Non-technical users who want to expose business data to Claude without coding"],"limitations":["Generated tool definitions may be overly generic or not optimized for specific use cases","Complex business logic or data transformations cannot be expressed in auto-generated tools","Tool parameter schemas may not capture all validation rules or constraints from source systems","No built-in versioning of tool definitions — schema changes may break existing agent implementations","Limited customization of tool descriptions and examples for LLM understanding"],"requires":["Peliqan platform account with business application connectors configured","Discovered business application schemas","MCP-compatible LLM client (Claude Desktop or custom MCP client)"],"input_types":["business application schemas","tool generation configuration (which tables/fields to expose)"],"output_types":["MCP tool definitions (JSON schema format)","callable functions with parameter and return type specifications"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_6","uri":"capability://text.generation.language.conversational.data.access.with.natural.language.query.translation","name":"conversational data access with natural language query translation","description":"Peliqan enables users and LLMs to query business data using natural language, which is translated into SQL queries or API calls against the data warehouse or source systems. The platform uses LLM-based query translation (likely leveraging Claude) to convert conversational questions into executable queries, with fallback to structured query execution if translation fails.","intents":["Ask 'What was our total revenue last month?' and get an answer without writing SQL","Enable non-technical business users to query business data through conversational interfaces","Build AI agents that can answer business questions by translating natural language to data queries","Reduce friction for users unfamiliar with SQL or specific data schemas"],"best_for":["Non-technical business users who want to query data without SQL knowledge","Developers building conversational AI agents for business intelligence","Organizations wanting to democratize data access across teams","Teams building chatbots or voice interfaces for business data"],"limitations":["Natural language query translation accuracy depends on LLM quality and data schema clarity — ambiguous questions may produce incorrect queries","Complex multi-step analytical questions may not translate correctly to single SQL queries","Requires clear documentation and examples for LLM to understand data schema and business context","No built-in disambiguation for ambiguous natural language queries — may require user clarification","Performance unpredictable — LLM-based translation adds latency compared to direct SQL queries"],"requires":["Peliqan platform account with data warehouse enabled","LLM access (Claude or other model) for query translation","Well-documented data schema and business context for accurate translation","Conversational interface (Peliqan UI, custom chatbot, or Claude Desktop)"],"input_types":["natural language questions","business context and schema documentation","user clarification for ambiguous queries"],"output_types":["translated SQL queries","query results in natural language summary","confidence scores or explanations of query translation"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_7","uri":"capability://data.processing.analysis.real.time.data.access.through.direct.api.queries","name":"real-time data access through direct api queries","description":"Peliqan provides a real-time query mode that bypasses the data warehouse and directly queries source business applications through their APIs, returning current data without warehouse latency. This is useful for queries requiring the latest data (e.g., current inventory levels, real-time customer status) where warehouse sync intervals are too slow.","intents":["Check current inventory levels in NetSuite without waiting for warehouse sync","Retrieve real-time customer status from Salesforce for immediate decision-making","Build LLM agents that need the latest business data for accurate responses","Query data that changes frequently and cannot tolerate warehouse sync latency"],"best_for":["Use cases requiring real-time or near-real-time data (inventory, pricing, status)","Developers building LLM agents that need current data for decision-making","Organizations with low-latency requirements for specific queries","Teams wanting flexibility to choose between warehouse (batch) and API (real-time) queries"],"limitations":["Real-time API queries are slower than warehouse queries (typically 500ms-5s per query) due to network latency","Subject to source system API rate limits — high-frequency queries may be throttled","Cannot aggregate or join data across multiple systems in real-time without custom logic","Real-time queries consume API quota and may incur additional costs from business applications","No caching — identical queries hit the API each time, increasing latency and cost"],"requires":["Peliqan platform account with business application connectors configured","Valid API credentials for target business applications","Network connectivity to source business applications","Sufficient API rate limit quota for expected query volume"],"input_types":["query parameters (customer ID, product ID, etc.)","real-time query configuration (which fields to fetch)"],"output_types":["current data from source business applications","query execution metadata (latency, API calls made)"],"categories":["data-processing-analysis","search-retrieval"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_8","uri":"capability://safety.moderation.multi.tenant.data.isolation.and.access.control","name":"multi-tenant data isolation and access control","description":"Peliqan implements multi-tenant architecture with row-level and table-level access controls, ensuring that data from different business applications and customers is isolated and only accessible to authorized users. Access control is enforced at the MCP interface and data warehouse query level, preventing unauthorized data leakage across tenants.","intents":["Ensure that data from one customer's Salesforce instance is not visible to another customer","Implement role-based access control so sales users can only see customer data, not financial data","Build multi-tenant SaaS applications on top of Peliqan without worrying about data isolation","Comply with data privacy regulations by enforcing strict access controls"],"best_for":["Multi-tenant SaaS applications built on Peliqan","Organizations with strict data privacy and compliance requirements","Teams building internal tools that need role-based access control","Companies managing data for multiple customers or business units"],"limitations":["Access control configuration complexity increases with number of roles and data sources","Row-level access control may impact query performance on large datasets","No built-in audit logging of data access — requires external logging for compliance","Access control rules must be manually maintained as business applications and user roles change","Limited support for dynamic access control based on real-time conditions"],"requires":["Peliqan platform account with multi-tenant configuration enabled","User authentication system (OIDC, SAML, or Peliqan native auth)","Role and permission definitions for each user or group","Access control rules configured for each data source and table"],"input_types":["user identity and role information","access control rules (table-level, row-level, column-level)","authentication credentials"],"output_types":["filtered query results based on user permissions","access denied errors for unauthorized queries","access control audit logs"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-peliqan__cap_9","uri":"capability://automation.workflow.scheduled.etl.pipeline.execution.with.error.handling.and.retry.logic","name":"scheduled etl pipeline execution with error handling and retry logic","description":"Peliqan provides a scheduler that executes ETL pipelines on a defined cadence (hourly, daily, weekly) with built-in error handling, retry logic, and failure notifications. The scheduler manages pipeline dependencies, handles transient failures (network timeouts, API rate limits), and provides detailed execution logs for debugging.","intents":["Schedule daily syncs of Salesforce and NetSuite data to the warehouse at 2 AM","Automatically retry failed syncs with exponential backoff to handle transient API failures","Receive notifications when ETL pipelines fail so issues can be addressed quickly","Monitor ETL pipeline execution history and performance to optimize sync schedules"],"best_for":["Organizations with scheduled data synchronization requirements","Teams without dedicated data engineering infrastructure (Airflow, Dagster)","Developers building data pipelines that need reliability and observability","Companies wanting to minimize operational overhead for data synchronization"],"limitations":["Limited scheduling granularity — minimum interval typically 15 minutes, no sub-minute scheduling","Retry logic is fixed (exponential backoff) — no custom retry strategies","No built-in pipeline dependency management — complex multi-step pipelines require manual orchestration","Failure notifications are basic (email, webhooks) — no integration with advanced alerting systems","No built-in data quality checks or validation — pipeline success only means data was synced, not that it's correct"],"requires":["Peliqan platform account with ETL pipeline configuration","Configured ETL pipelines with source and destination definitions","Notification configuration (email, webhooks, Slack, etc.)","Sufficient platform resources for scheduled pipeline execution"],"input_types":["ETL pipeline definitions","schedule configuration (cron expressions or UI-based scheduling)","error handling and retry policies"],"output_types":["pipeline execution logs","success/failure notifications","execution metrics (rows synced, duration, errors)"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":32,"verified":false,"data_access_risk":"high","permissions":["Peliqan platform account with configured business application connectors","MCP-compatible LLM client (Claude via Claude Desktop, or custom MCP client)","Valid API credentials for target business applications (Salesforce, NetSuite, QuickBooks, etc.)","Network connectivity to Peliqan platform and target business applications","Peliqan platform account with data warehouse tier enabled","Configured connectors for source business applications","ETL pipeline definitions (can be created via UI or API)","Sufficient data warehouse quota for expected data volume","Peliqan platform account with ETL pipeline configuration","Knowledge of SQL, JavaScript, or visual mapping tools for transformation definition"],"failure_modes":["Requires Peliqan platform account and configuration of business application credentials","Latency depends on underlying business application API response times (typically 500ms-5s per query)","Limited to data sources that Peliqan has pre-built connectors for; custom data sources require additional setup","Query complexity and result size constrained by MCP message size limits and LLM context windows","No built-in caching of frequently accessed data — each query hits the source system","Data warehouse capacity and query performance depend on Peliqan's infrastructure tier (pricing-dependent)","ETL pipeline latency means data is not real-time; typical sync intervals are hourly or daily","Schema conflicts between source systems require manual resolution or custom transformation logic","Limited SQL dialect support — may not support all advanced SQL features available in Snowflake or BigQuery","No built-in data lineage or audit logging for compliance-heavy industries","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.47,"ecosystem":0.49999999999999994,"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=peliqan","compare_url":"https://unfragile.ai/compare?artifact=peliqan"}},"signature":"0ioxquRrKvm32uPcDhnMwyvP5ZnMDK8sGyq8lbDPBU7RgNJWiaL16WGroXb/vx/K0cLdrf1RuuNS5YBGe9ifAw==","signedAt":"2026-06-23T07:59:31.092Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/peliqan","artifact":"https://unfragile.ai/peliqan","verify":"https://unfragile.ai/api/v1/verify?slug=peliqan","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"}}