"The concept of thinking or introspection" matching MCP servers:

Exposes GObject Introspection metadata to coding agents, enabling querying of libraries, classes, functions, signals, properties, and more through MCP tools.

Automatically extracts technical concepts from AI coding conversations, organizes them into a searchable knowledge base with hierarchy and categories, and links them to specific locations in your codebase.

Enables AI assistants and developers to analyze code for language-specific best practices and idiomatic patterns across programming languages, CI automation, and configuration formats.

Enterprise-grade code intelligence server for AI assistants that analyzes codebases for due diligence, tech debt, security vulnerabilities, and code quality.

An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.

Enables agents to audit and safeguard repositories by detecting dependency pinning issues, license compliance problems, hardcoded secrets, and dead code through MCP tools.

Enables coding agents to audit a Next.js codebase read-only, checking routes, Prisma models, environment variables, and locale consistency via MCP tools.

MCP server for automatic Storybook story generation, component analysis, and validation. Auto-detects React frameworks and syncs component documentation.

An MCP server that extends AI coding assistants with deterministic, algorithmic capabilities such as code analysis, fault localization, and formal verification, enabling an autonomous engineering team within the IDE.

Validates Mermaid diagrams with comprehensive grammar parsing supporting 28+ diagram types. Processes markdown files, ZIP archives, and direct input with detailed error reporting and enterprise-grade performance capabilities.

Exposes a set of CLI tools (test generation, documentation generation, linting, test running, code search) to AI assistants via MCP, allowing them to perform these tasks through natural language.

Enables static security audit of Solidity smart contracts by analyzing source code or deployed bytecode for vulnerabilities, providing risk scores and detailed findings.

Enables AI assistants to perform read-only introspection of Symfony applications, exposing routes, controllers, services, entities, database schema, migrations, logs, and more via MCP tools.

A robust, language-agnostic Model Context Protocol (MCP) server that provides AI coding agents with the ability to edit files surgically via Abstract Syntax Trees (AST) instead of relying on token-heavy, brittle search-and-replace or diff operations.

A read-only MCP server that provides LLMs with introspection data and documentation for the Freqtrade codebase. It enables AI tools to access class signatures, method details, and configuration schemas to assist in writing more reliable trading strategies.

MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.

MCP server that brings Octopus AI code review into editors, allowing review of code changes and asking questions about your codebase. Integrates with Cursor, Claude, or any MCP client via natural language.

Provides MCP tools to review git changes using OpenAI Codex CLI, enabling code review of unstaged, staged, or last-commit changes.

A deterministic symbol oracle over a locally built index of the repository: whether a symbol exists, what a file declares, and what changed structurally since the last snapshot. It also ships a PreToolUse guard that stops an Edit/Write referencing a function, constant or type the repo does not declare, before the write lands rather than after the build fails. No LLM, no API keys, no network, no l

Mason indexes your codebase into a persistent concept map linking features and flows to their implementing files, so AI agents can answer "where is X implemented" without running grep/glob. It also provides pre-edit impact analysis and generates CLAUDE.md files from structured analysis of git history, architectural file sampling, and test mappings.