MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,944 servers in this category.
Lets AI agents autonomously run 150+ security tools for pentesting, vulnerability discovery, and bug bounty automation.
Turns natural language, code, and infrastructure sources into editable draw.io architecture diagrams, with sync, testing, and export tools.
Lets an AI client search an index of over 17,000 open-source tools built by reverse engineering closed apps, APIs, devices, protocols, and file formats.
Enforces AI accuracy by using deterministic tools to verify claims against ground truth in binaries and source code.
Provides a governed shared memory layer for AI agent fleets to store, recall, and compound knowledge across multiple agents and tenants.
Provides a suite of reference implementations for managing and interacting with Oracle Cloud Infrastructure and other Oracle products via MCP.
Lets AI clients search the web and retrieve full page content, including complete StackOverflow threads, GitHub issues, Wikipedia and arXiv papers.
Reviews software architectures from various formats and automatically generates interactive Excalidraw diagrams and risk assessments.
Lets an AI client run headless Screaming Frog crawls, export crawl data, aggregate results, and manage stored crawls via the CLI.
$claude mcp add screaming-frog-mcp -- uvx screaming-frog-mcp
Allows an AI assistant to write, push, and test MicroPython code directly on PicoCalc MicroPython hardware over USB.
$claude mcp add picocalc -- uvx picocalc-mcp
Provides persistent, neuroscience-inspired memory for AI coding agents using local SQLite or PostgreSQL storage.
$claude mcp add cortex -- uvx hypermnesia-mcp
Exposes Appwrite's API including databases, users, functions, teams, and storage as tools for AI clients.
$claude mcp add mcp-for-api -- uvx mcp-server-appwrite
Enables AI clients to perform reverse engineering on ELF, Mach-O, and PE binaries using Ghidra to decompile, disassemble, and trace value flows.
$claude mcp add pyghidra-lite -- uvx pyghidra-lite
Allows an AI agent to control Rigol digital oscilloscopes via SCPI to adjust settings, run acquisitions, capture waveforms, and take screenshots.
$claude mcp add labmcp-rigol-scope -- uvx labmcp-rigol-scope
Lets an AI client list, inspect, and grant or deny pending CTRLRun approval requests.
$claude mcp add ctrlrun -- uvx ctrlrun
Connects AI agents to live Synopsys Verdi sessions to inspect waveforms, navigate RTL, and analyze signal transitions.
$claude mcp add verdi-bridge -- uvx verdi-bridge
Enables AI agents to explore SystemVerilog and VHDL designs by tracing connectivity, hierarchy, and logic cones with file-and-line references.
$claude mcp add naja-scope -- uvx naja-scope
Provides a shared, local-first memory for AI coding agents to persist project decisions and lessons across different sessions and tools.
$claude mcp add yggdrasil -- uvx yggdrasil-memory
Reduces AI agent context size by removing unnecessary tool outputs while keeping essential data byte-for-byte and recoverable via hash-based recall.
$claude mcp add lcc -- uvx local-context-compiler
Generates tests from acceptance criteria and uses a separate coding agent to converge code implementation without exposing the test requirements.
$claude mcp add qikly -- uvx qikly