"A database that can be operated or managed" matching MCP servers:

Enables AI agents to format SQL, explain queries in plain English, analyze schemas, build queries from natural language, and generate migrations, all without requiring a database connection.

Offline PostgreSQL diagnostics: reviews SQL, risky migrations, candidate indexes and EXPLAIN JSON plans without database credentials or executing statements.

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

Enables AI agents to deterministically inspect, author, convert, validate, and diagnose Classical CAN and CAN FD databases and trace logs, including bit-layout validation, template generation, trace aggregation, ISO-TP/UDS reassembly, bus-health analysis, and reverse engineering.

Enables AI agents to run deterministic database intelligence tasks including natural-language-to-SQL synthesis, AST SQL auditing and optimization, schema migration diffing, SQL transpilation, index and normalization advice, PII scrubbing, fixture generation, connection-pool sizing, isolation-hazard auditing, and ORM model compilation over Streamable HTTP or stdio.

Enables MCP clients to execute Python snippets and interact with Ghidra through its PyGhidra scripting environment via a local Java plugin.

Enables secure read-only querying of multiple database types (MySQL, PostgreSQL, MSSQL, Oracle) through natural language. Automatically reads database configuration from project files and blocks any data modification operations for safety.

Codebase Q&A agent with git-history awareness. Explore a repo with list_files, read_file, and search, plus git log, blame, and diff and a repo map to answer "why did this change?" questions. Runs locally as an MCP server for Claude Code and other MCP clients.

Enables semantic code search across multi-language codebases using natural language queries, integrated with Qdrant vector database for fast, cached retrieval.

A standalone MCP server for SAP ABAP development and customizing that connects directly to your SAP system via ADT REST API, enabling AI assistants to search, read, write, activate, transport, debug, and run quality checks on ABAP code, as well as manage customizing/IMG configurations with governed transport recording.

A lean, local knowledge graph that joins a repo's code to its aSPARK delivery artifacts, enabling agents to trace user stories to code and assess impact of changes, served over MCP.

Enables executing arbitrary Joern/CPGQL queries against a loaded Code Property Graph, loading source code in multiple languages (PHP, Java, JavaScript, Python, C/C++) to build new CPGs, and inspecting loaded projects and the active workspace. It communicates with a running Joern server over its synchronous HTTP query endpoint, so no state polling is required.

Zero-dependency MCP server inspector for protocol conformance, tool annotations, and capability checks.

Local memory for coding agents that can refuse, not only recall. A rule carrying a machine-checkable proof blocks the matching command before it runs, while prose-only rules can warn but never block.

A code review tool that generates detailed HTML review documents by comparing branches or commits, with author filtering and intelligent analysis.

A local MCP server that indexes a repository into line-range chunks and serves compact evidence packets to cut token usage when exploring or debugging code.

Gives coding agents read-only tools that return, in one call, a declaration's callers traced up to entry points or its callees down to 8 levels, plus a map of directories, files, declarations and every usage of a symbol. Maps TypeScript, JavaScript, Go, Python and Java using each language's own compiler, so a change's impact can be traced across imports, methods, interfaces and decorators.

Enables AI assistants to scan Terraform and Dockerfiles for security misconfigurations, returning structured Checkov findings that can be explained in plain language.

The MCP server for Nanostores that scans your codebase with AST analysis to find stores, subscribers, and dependency chains, and can ingest live events to spot noisy, error-prone, or unused stores.

Clones a Git repo into a temp directory so MCP clients can search and read files from another repo for context.

Enables AI agents to browse, read, search, blame, and diff files from any branch, tag, or commit in a self-managed GitLab instance without checking anything out or modifying the working tree. Content is served read-only from locally cached git mirrors or your own clones, so no GitLab REST API access is needed.

A codebase-memory MCP server for AI coding agents with hybrid semantic+BM25 code search, structural outlines, a work journal, and gaze-and-think deep reasoning over a local LanceDB database.

A self-contained, in-memory graph database for AI Agents. Provides semantic code understanding through the Model Context Protocol (MCP).

Enables querying Odoo's model registry (fields, inheritance, methods) without a database connection by loading the registry in-memory.

Gives an AI agent complete knowledge of a specific DevExpress XAF application: its entities, controllers, actions, business rules, Model Editor customizations, custom property editors and the version-gated data migrations that ran once on a production database. Reads the source with Roslyn without compiling it, so it works on a branch that does not build and needs no DevExpress licence.

Enables semantic and keyword search over a local codebase by chunking source files along function and class boundaries, embedding them offline, and fusing vector and BM25 results. Runs entirely on your machine in a single SQLite file, so AI coding agents can find relevant code with no API keys, telemetry, or cloud calls.

Fast pre-commit dependency gate for AI-assisted code changes. Answers "is this safe to commit?" with a PASS/WARN/BLOCK verdict in seconds, so you can catch risky blast radius before a bad commit, not after it. No database, no heavy setup.

Read-only server that reports what is actually true in a local Ansible checkout: the option specs of installed modules, task-argument validity checks, role interfaces, redacted inventory, play structure, effective config, requirements drift, and which tasks a collection upgrade would break. It lets coding agents verify specs and arguments against the installed collections before writing anything, without running plays, connecting to managed hosts, or supplying vault secrets.

Blocks unsafe PostgreSQL migrations before an AI agent writes or runs them. check_before_apply returns a pass/fail gate; reads the real Postgres parser, classifies the lock each statement takes, checks 112 safety rules. Runs offline, no database required.

Enables agents to run semantic search across one or more local project directories by automatically maintaining a LAN-local Qdrant index with Ollama embeddings. Indexing, staleness checks, and incremental updates happen transparently, so users can query code by meaning without managing collections, chunks, or hashes.