"Understanding VS Code Agents or Extensions" matching MCP servers:

Provides FastMCP-based servers with various tools for AI assistants including math operations, file management, note-taking, todo management, and database operations. Offers both basic and advanced server configurations with tools, resources, and prompt templates.

Enables AI agents to inspect, query, test, and safely fix dbt projects and BigQuery warehouses under policy-enforced controls, with read-only direct queries and dbt-only allowlisted writes.

An MCP server that layers additional Home Assistant tools on top of voska/hass-mcp, enabling Lovelace dashboard management, automation/scene manipulation, SSH file access, and recorder database queries.

MCP server for Metabase that gives AI agents full access to query, explore, and manage content in your Metabase instance.

Centrally manages Claude agent definitions, configurations, and custom commands across multiple devices using a SQLite database, eliminating file synchronization conflicts and enabling live updates across all connected Claude sessions.

Builds rich code graphs from TypeScript/NestJS codebases using AST analysis and Neo4j, enabling semantic search, natural language querying, and intelligent graph traversal to provide deep contextual understanding of code relationships and dependencies.

An oil & gas data-analytics MCP server that enables guarded SQL queries, well valuation, and map rendering within chat apps.

Indexes codebases into a SQLite database to provide metadata, exports, dependency graphs, and change tracking for JS/TS projects. It enables users to search for symbols, map internal dependencies, and monitor file changes through MCP tools and a web dashboard.

Provides persistent memory capabilities for Claude Code using Neo4j graph database to track development tasks, code patterns, solutions, and their relationships across sessions and projects, enabling contextual assistance and pattern recognition.

Enables local Claude Code to interact with Snowflake, Asana, M365, GitHub, and Hive Mind with automatic response truncation to prevent memory overload.

Enables MCP-compatible LLM clients to interact with IBM Planning Analytics/TM1 models through callable tools, supporting read operations like inspecting cubes, dimensions, and MDX queries, plus write/model-building operations in read/write mode.

A self-hosted MCP server providing stateful code execution (Python/JavaScript) with SQL query support, file I/O, and artifact management, replacing Azure Code Interpreter.

A governed SQL gateway that exposes typed tools to AI agents, compiling safe read-only queries from a semantic layer while blocking PII before execution, supporting SQL Server, Postgres, and SQLite.

Gives MCP clients a local, single-tenant SQLite-backed store for saving, searching, bootstrapping and recalling memory records, plus saving and loading session handoffs, using text search by default with optional embeddings. It runs over stdio or an authenticated loopback HTTP gateway with explicit-confirmation pruning, scoped policies, and admin-driven backup, restore-copy and restart-drill verification.

CTX is a tool made to solve a big problem when chatting with LLMs like ChatGPT or Claude: giving them enough context about your project.

A Model Context Protocol server providing LLMs read-only access to PostgreSQL databases for inspecting schemas and executing queries.

Read-only MCP server for SQL databases (SQL Server, Postgres, SQLite) with multi-server support and three-layer safety using AST validation and linting.

An MCP server that provides a semantic index and 14 bounded tools for AI agents to navigate Excel workbooks by symbols, references, and diagnostics, avoiding the need to read entire rows.

Provides sub-millisecond access to organizational and engineering data by pre-materializing data into a read-only SQLite database. Enables agents to query people, teams, issues, features, and governance documents without upstream latency or auth.

An MCP server that uses an OWL/SHACL/SKOS knowledge graph to interpret login-diagnosis prompts and return JSON-LD descriptors, guiding Copilot agents to the appropriate SQL Server and MongoDB queries and enabling New Relic escalation when needed.