{"id":"tidb-mcp-server","name":"tidb-mcp-server","homepage":"https://pypi.org/project/tidb-mcp-server/","repo_url":"https://github.com/poneglyph-research/tidb-mcp-server","category":"infrastructure","subcategories":[],"tags":["mcp","tidb","database","sql","agent-tools"],"what_it_does":"Provides an MCP (Model Context Protocol) server interface to interact with a TiDB/TiDB-compatible database, exposing database operations as MCP tools for agent workflows.","use_cases":["Enable LLM/agent workflows to run SQL against TiDB","Agent-driven data exploration and query assistance","Building internal tools/dashboards that use MCP to access TiDB data"],"not_for":["Public unauthenticated access to production databases","Use cases requiring strong multi-tenant isolation and fine-grained authorization by default (if not explicitly implemented)","Latency-sensitive interactive workloads without caching/query optimization"],"best_when":"Used inside controlled environments where database credentials, network access, and tool permissions are carefully managed for agent-driven SQL execution.","avoid_when":"Avoid when you cannot restrict what SQL/operations agents may run, or when you lack guardrails for data exfiltration and destructive queries.","alternatives":["Direct TiDB/MySQL client access from the agent with custom tool wrappers","Generic MCP-to-SQL bridges (if available) configured for the specific database","Use an OpenAPI/HTTP wrapper around TiDB with strict allowlists for agent use"],"af_score":34.2,"security_score":46.0,"reliability_score":20.0,"package_type":"mcp_server","discovery_source":["pypi"],"priority":"low","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-04-04T21:42:04.653989+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":null},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":null},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":34.2,"security_score":46.0,"reliability_score":20.0,"mcp_server_quality":55.0,"documentation_accuracy":40.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":40.0,"rate_limit_clarity":0.0,"tls_enforcement":60.0,"auth_strength":50.0,"scope_granularity":20.0,"dependency_hygiene":50.0,"secret_handling":50.0,"security_notes":"Assessed conservatively based on limited available information. MCP servers that allow SQL execution typically require strong guardrails: least-privilege DB accounts, network restrictions, SQL allowlists (read-only), output redaction, and explicit handling of prompt injection. TLS/secret-handling specifics and whether the MCP server supports authentication/authorization were not provided, so scores reflect uncertainty.","uptime_documented":0.0,"version_stability":50.0,"breaking_changes_history":0.0,"error_recovery":30.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["SQL-executing tools can be high-risk: agents may produce destructive or data-exfiltrating queries unless explicit query allowlists/deny-lists and row/column restrictions exist.","Agents may retry on ambiguous failures; without clear retry semantics and idempotent tool design, retries could cause duplicate writes (if write operations are exposed).","If the MCP server passes through raw SQL, ensure strict input validation/constraints to prevent prompt-injection-style SQL manipulation."]}}