"Vector Database" matching MCP servers:

An MCP server that analyzes SQL schemas, generates realistic test data, benchmarks queries, and provides optimization recommendations to improve database performance.

MCP server for multiple databases (PostgreSQL, MySQL, MariaDB, SQLite, MongoDB, Redis) with tools for schema inspection, querying, performance diagnostics, and safe write operations, featuring access modes, PII masking, and audit logging.

A drop-in Model Context Protocol (MCP) server that lets an AI agent query PostgreSQL — read-only, enforced at the database level, with real SQL validation, timeouts, cost limits, OAuth 2.1, and an audit trail.

Enables AI assistants to search, analyze, and debug application API traffic captured by Tusk Drift, including HTTP requests, database queries, distributed traces, latency metrics, and error rates.

Enables LLM assistants to analyze PostgreSQL query execution plans with EXPLAIN and receive structured reports highlighting performance bottlenecks, all through read-only database access.

Enables querying OpenObserve logs—listing streams, inspecting schemas, and running SearchSQL time-windowed searches—so you can answer what actually happened in production. Optionally correlates those logs against a database through a verified read-only connection via DbSchema and DbQuery tools.

An MCP server for controlled server operations via BaoTa Panel, providing 50+ tools for system, site, database, files, cron, Docker, and network management with safety features like permission tiers, credential masking, and audit logs.

FastMCP server with read-only tools to monitor Redis — queue depths, Celery queue status, connected clients, server/memory info, and per-database key counts

Enables agents to report and query performance metrics to build a community-driven quality database for MCP tools. This server helps agents discover and select the most reliable tools based on success rates and user-reported quality scores.

A Model Context Protocol (MCP) server for PostgreSQL that provides safe, structured access to your database for AI assistants, enabling health checks, index tuning, lock analysis, and more.

Enables local-first observability for MCP agent workflows by recording tool calls, prompts, latency, and token usage in a local SQLite database, and provides tools for inspecting, comparing, exporting, and generating dashboards from traces.

Enables MCP clients to explore ClickHouse schemas, run analytical queries, and manage the database with statement-aware security modes and access-control flags.

Enables AI agents to manage Stape.io infrastructure, including container management, custom domains, power-ups, request logs, and Stape Store NoSQL database operations.

Enables AI assistants and MCP clients to analyze offline Oracle AWR/ASH reports in HTML or text across Oracle 10g–23ai, including single-instance and RAC global reports, returning report type, version, active sessions, load profile, top waits and SQL with version-aware tuning advice plus a prioritized top-3 summary, all locally without an Oracle client or database connection.

Enables MCP-compatible AI assistants to inspect and manage local or remote servers in plain language, covering system health, Docker containers, services, ports, disks, scoped files, and read-only database queries over key-only SSH. Write actions such as container restarts, file edits, and allowlisted dev commands require client approval.

Enables Azure SQL Database performance and administration through typed execution, query benchmarking, and managed DBA operations.

A Claude Code MCP server that connects to Laravel Clockwork to provide insights into application performance, database queries, errors, and request flow.

A Model Context Protocol server that provides secure database access to PostgreSQL through Kysely ORM, enabling natural language interaction with PostgreSQL databases. It offers 40+ MCP tools for querying, schema inspection, diagnostics, and Java backend monitoring.

A local, read-only MCP server for RavenDB diagnostics, providing 21 tools to inspect cluster, database, index, task, storage, and performance state, plus logs and data.

A flight recorder for Claude Code that captures tool calls and observations into a SQLite database, then classifies them into a distilled timeline for incident troubleshooting.

Enables AI agents to review and compare Go goroutine dumps, surfacing goroutine leaks, lock pile-ups, exhausted database pools, and missing HTTP timeouts from dump text alone without connecting to the service.

Exposes SereneDB server state as read-only MCP tools (status, storage, memory, activity, threads, profile, callgraph, host, config, and optional set_setting) so agents can query live database health and metrics with evidence-backed findings instead of viewing screenshots.

MCP server for safely exposing SQL Server database capabilities to LLM clients, with read-only mode, security features, and observability.

Enables AI agents and software engineers to investigate and resolve realistic distributed-system incidents using safe MCP-based diagnostic tools for code, logs, metrics, traces, database, and deployments.

Provides financial audit reporting and ledger query tools for AI agents, enabling generation of compliance, risk, and transaction reports and querying of transaction data, balances, and summaries from an in-memory SQLite database via MCP.

Enables LLMs to query real job data and summarize backend job failures using MCP tools backed by a SQLite database.

Enables AI agents to query a private MySQL database through a self-maintained SSH tunnel while enforcing read-only SQL by default, with optional opt-in server and Docker operations.

A read-only MCP service for production troubleshooting that lets you register database, log, code, and message-queue connections in a web console, then have AI clients query them safely by target name. Models never supply hosts, accounts, or passwords themselves, and all operations are restricted to a read-only whitelist with audit logging.

Enables on-call database diagnostics: it classifies load pressure, traces root causes with hypothesis-evidence-confidence, detects blocking and lock chains, scores health across a dimension tree, and renders deliverable incident reports. Works from symptom text alone with no database connection or history required (Tier0), escalating to snapshot-based and trend-based analysis as observations accumulate.

A local gateway that caches LLM prompts and tool results, stores searchable compressed context, and relays downstream MCP tools under deny-by-default rules. It keeps everything in one SQLite database with a single ledger tracking tokens paid upstream versus tokens avoided, plus a web console for live metrics.