{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"awesome-run-sql-connectorx","slug":"run-sql-connectorx","name":"run-sql-connectorx","type":"mcp","url":"https://github.com/gigamori/mcp-run-sql-connectorx","page_url":"https://unfragile.ai/run-sql-connectorx","categories":["mcp-servers"],"tags":[],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"awesome-run-sql-connectorx__cap_0","uri":"capability://tool.use.integration.multi.database.sql.execution.with.connectorx","name":"multi-database sql execution with connectorx","description":"Executes SQL queries against 8+ database backends (PostgreSQL, MariaDB, BigQuery, MS SQL Server, Redshift, MySQL, SQLite, Oracle) through ConnectorX's Rust-based connector abstraction layer. ConnectorX handles connection pooling, query compilation, and result streaming without materializing full result sets in memory, enabling efficient execution of large queries. The MCP tool wraps ConnectorX's query API to expose database execution as a standardized Model Context Protocol resource.","intents":["Execute SQL queries against multiple database types from a single LLM agent interface","Query large datasets without loading entire results into memory","Support heterogeneous database environments in multi-database architectures","Integrate database access into Claude or other MCP-compatible AI workflows"],"best_for":["AI agents and LLM applications requiring database access across multiple backends","Data engineering teams building MCP-based data pipelines","Teams migrating from REST APIs to MCP for database integration"],"limitations":["ConnectorX performance varies by database backend; some drivers (Oracle, Snowflake) may have higher latency than native clients","No built-in query optimization or execution planning — relies on database query planner","Result streaming to CSV/Parquet adds serialization overhead; not suitable for sub-millisecond latency requirements","Connection pooling configuration is implicit; no exposed tuning parameters for concurrent query limits"],"requires":["ConnectorX library (Rust-based, requires compilation or pre-built wheels)","Valid connection credentials for target database (connection string or environment variables)","MCP server runtime (Claude Desktop, Cline, or compatible MCP host)","Python 3.8+ (if using Python bindings for ConnectorX)"],"input_types":["SQL query string (parameterized or raw)","Database connection URI or credentials","Output format specification (CSV or Parquet)"],"output_types":["CSV file stream","Parquet file stream","Structured query result metadata"],"categories":["tool-use-integration","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-run-sql-connectorx__cap_1","uri":"capability://data.processing.analysis.streaming.result.export.to.columnar.formats","name":"streaming result export to columnar formats","description":"Streams SQL query results directly to CSV or Parquet files without buffering the full result set in memory. Uses ConnectorX's columnar data model to write results in batches, enabling efficient export of multi-gigabyte datasets. The streaming approach prevents out-of-memory errors on large queries and allows results to be consumed incrementally by downstream tools or LLM context windows.","intents":["Export large query results to files without memory constraints","Stream results in Parquet format for downstream analytics tools (DuckDB, Pandas, Polars)","Generate CSV exports suitable for LLM ingestion or human review","Integrate database results into data pipelines without intermediate storage"],"best_for":["Data engineers exporting large datasets from production databases","LLM agents that need to materialize query results for analysis or reporting","Workflows requiring Parquet output for Apache Spark or DuckDB integration"],"limitations":["Streaming to disk adds I/O latency; not suitable for interactive query exploration","CSV export does not preserve type information; Parquet is required for schema-aware downstream processing","No built-in compression for CSV output; Parquet compression is automatic but adds CPU overhead","Result ordering is not guaranteed across streaming batches unless explicitly sorted in SQL query"],"requires":["Writable filesystem with sufficient disk space for output file","ConnectorX with CSV and Parquet writer backends compiled","SQL query that returns results (SELECT, not DDL/DML)"],"input_types":["SQL SELECT query","Output format flag (csv or parquet)","Optional file path or stream destination"],"output_types":["CSV file (text-based columnar format)","Parquet file (binary columnar format with schema)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-run-sql-connectorx__cap_2","uri":"capability://tool.use.integration.mcp.protocol.wrapping.for.database.access","name":"mcp protocol wrapping for database access","description":"Wraps the SQL execution and result export functionality as an MCP (Model Context Protocol) tool named 'run_sql', exposing database queries as a standardized resource that Claude, Cline, and other MCP-compatible clients can invoke. The MCP server handles request/response serialization, error handling, and result streaming through the MCP transport layer, abstracting database connection management from the client.","intents":["Enable Claude or other LLM agents to execute SQL queries without custom integrations","Expose database access through a standardized protocol compatible with multiple AI tools","Build multi-tool AI workflows that combine database queries with other MCP resources","Provide database access to non-technical users through LLM interfaces"],"best_for":["Teams building AI agents that need database access (Claude, Cline, custom MCP clients)","Organizations standardizing on MCP for tool integration across AI applications","Developers building multi-tool workflows combining databases with APIs and file systems"],"limitations":["MCP transport adds ~50-200ms latency per request due to serialization and protocol overhead","No built-in authentication beyond connection string credentials; relies on MCP server-level security","Result streaming through MCP may be buffered by client; true streaming benefits only realized if client supports streaming responses","Error messages from database are passed through MCP without sanitization; sensitive error details may leak to LLM"],"requires":["MCP-compatible client (Claude Desktop, Cline, or custom MCP host)","MCP server runtime (Python-based, requires mcp library)","Database connection credentials configured in MCP server environment","Network connectivity between MCP client and server (if remote)"],"input_types":["MCP tool call with 'run_sql' operation","SQL query string parameter","Output format parameter (csv or parquet)"],"output_types":["MCP tool result with file path or streamed content","Error response with database error details"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-run-sql-connectorx__cap_3","uri":"capability://safety.moderation.parameterized.query.execution.with.injection.prevention","name":"parameterized query execution with injection prevention","description":"Executes SQL queries with parameter binding to prevent SQL injection attacks. The implementation accepts query strings with placeholders (e.g., '?' or ':param') and separate parameter values, passing both to ConnectorX's query execution layer which handles safe parameter substitution at the database driver level. This prevents untrusted input (from LLM outputs or user input) from being interpreted as SQL code.","intents":["Execute SQL queries with dynamic values from LLM outputs without SQL injection risk","Build AI agents that can safely query databases with user-provided filter criteria","Integrate user input into database queries without manual escaping","Support templated queries with variable substitution"],"best_for":["AI agents that receive user input or LLM-generated query parameters","Applications requiring SQL injection protection for compliance (SOC 2, HIPAA, PCI-DSS)","Teams building multi-tenant systems where query isolation is critical"],"limitations":["Parameter binding only protects VALUES, not table/column names; dynamic schema access requires additional validation","Some databases (BigQuery, Redshift) have different parameter syntax; abstraction may not support all parameter styles","LLM agents must be instructed to use parameters rather than string concatenation; no automatic detection of injection attempts","Parameter binding adds minimal overhead (~1-5ms) but requires explicit parameter passing rather than inline values"],"requires":["SQL query with parameter placeholders (format depends on database backend)","Separate array or dict of parameter values","Database driver support for parameterized queries (all ConnectorX backends support this)"],"input_types":["SQL query string with placeholders","Parameter values array or dictionary","Database connection URI"],"output_types":["Query result set (CSV or Parquet)","Error response if parameter binding fails"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-run-sql-connectorx__cap_4","uri":"capability://automation.workflow.connection.pooling.and.lifecycle.management","name":"connection pooling and lifecycle management","description":"Manages database connections through ConnectorX's connection pooling layer, which reuses connections across multiple queries to reduce connection overhead. The MCP server maintains connection state and handles connection lifecycle (creation, reuse, cleanup) transparently. Pooling is configured implicitly based on ConnectorX defaults, with connection timeouts and retry logic handled by the underlying database driver.","intents":["Execute multiple SQL queries efficiently without reconnecting for each query","Reduce latency for rapid-fire database operations in AI agent workflows","Prevent connection exhaustion when running many concurrent queries","Handle transient database connection failures with automatic retry"],"best_for":["AI agents executing multiple queries in a single session","High-frequency query workloads where connection overhead is significant","Multi-tenant systems where connection pooling prevents resource exhaustion"],"limitations":["Connection pool size is not exposed for tuning; defaults may be suboptimal for high-concurrency workloads","No built-in connection timeout configuration; relies on database driver defaults (typically 30s)","Connection state is not isolated between MCP requests; concurrent requests may share connections, requiring thread-safe query execution","Pool warmup is not explicit; first query after server startup may experience higher latency"],"requires":["ConnectorX with connection pooling support (included in standard builds)","Database that supports connection pooling (all supported backends do)","Stable network connectivity to database (transient failures are retried, persistent failures timeout)"],"input_types":["Database connection URI","SQL query"],"output_types":["Query result","Connection error if pool exhaustion or timeout occurs"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"awesome-run-sql-connectorx__cap_5","uri":"capability://safety.moderation.error.handling.and.database.specific.exception.translation","name":"error handling and database-specific exception translation","description":"Captures database errors (connection failures, syntax errors, permission errors, timeouts) from ConnectorX and translates them into MCP error responses with human-readable messages. The implementation preserves database-specific error codes and context while sanitizing sensitive information (e.g., internal server details). Errors are returned to the MCP client with appropriate HTTP-like status codes and error descriptions.","intents":["Provide clear error messages to LLM agents when queries fail","Distinguish between recoverable errors (timeouts, transient failures) and permanent errors (syntax, permissions)","Debug query failures without exposing sensitive database internals","Enable LLM agents to implement retry logic based on error type"],"best_for":["AI agents that need to handle database errors gracefully","Applications requiring audit logs of failed queries","Teams building resilient multi-database workflows"],"limitations":["Error messages from database may contain sensitive information (table names, schema details); sanitization is not automatic","Some database errors (e.g., BigQuery quota exceeded) may not map cleanly to standard error categories","Timeout errors are indistinguishable from slow queries; no built-in query execution time tracking","Connection errors may be transient (network blip) or permanent (credentials invalid); no automatic retry logic"],"requires":["ConnectorX error handling (included in standard builds)","MCP error response format support in client"],"input_types":["SQL query that may fail","Database connection that may be unavailable"],"output_types":["MCP error response with error code and message","Structured error details (error type, database-specific code)"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":29,"verified":false,"data_access_risk":"high","permissions":["ConnectorX library (Rust-based, requires compilation or pre-built wheels)","Valid connection credentials for target database (connection string or environment variables)","MCP server runtime (Claude Desktop, Cline, or compatible MCP host)","Python 3.8+ (if using Python bindings for ConnectorX)","Writable filesystem with sufficient disk space for output file","ConnectorX with CSV and Parquet writer backends compiled","SQL query that returns results (SELECT, not DDL/DML)","MCP-compatible client (Claude Desktop, Cline, or custom MCP host)","MCP server runtime (Python-based, requires mcp library)","Database connection credentials configured in MCP server environment"],"failure_modes":["ConnectorX performance varies by database backend; some drivers (Oracle, Snowflake) may have higher latency than native clients","No built-in query optimization or execution planning — relies on database query planner","Result streaming to CSV/Parquet adds serialization overhead; not suitable for sub-millisecond latency requirements","Connection pooling configuration is implicit; no exposed tuning parameters for concurrent query limits","Streaming to disk adds I/O latency; not suitable for interactive query exploration","CSV export does not preserve type information; Parquet is required for schema-aware downstream processing","No built-in compression for CSV output; Parquet compression is automatic but adds CPU overhead","Result ordering is not guaranteed across streaming batches unless explicitly sorted in SQL query","MCP transport adds ~50-200ms latency per request due to serialization and protocol overhead","No built-in authentication beyond connection string credentials; relies on MCP server-level security","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.05,"quality":0.37,"ecosystem":0.39999999999999997,"match_graph":0.25,"freshness":0.6,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-06-17T09:51:04.048Z","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=run-sql-connectorx","compare_url":"https://unfragile.ai/compare?artifact=run-sql-connectorx"}},"signature":"MsF5A37R44sDTzH/AqBJrxyGtdHlAWYlxFuu5j9/ltJlsA9/jWkag2k1OWye1EjYyGyl/JNztl78OwsXqVnxDg==","signedAt":"2026-06-22T07:49:42.659Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/run-sql-connectorx","artifact":"https://unfragile.ai/run-sql-connectorx","verify":"https://unfragile.ai/api/v1/verify?slug=run-sql-connectorx","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"}}