MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,969 servers in this category.
Audits MCP configurations to detect leaked API keys, supply-chain vulnerabilities, tool poisoning, and malicious package installs.
Enables AI assistants to interact with cyberinfrastructure resources including compute allocations, system status, software discovery, and usage metrics.
A Git-based marketplace for MCP servers that provides a searchable directory, installation configurations, and automated health monitoring.
Provides a multi-network blockchain SDK for accessing Solana, Ethereum, Avalanche, and other chain families via standardized RPC interfaces.
Visualizes AI memory as a live 3D brain that tracks note reading, searching, and writing activities in real-time.
Reduces LLM context bloat by lazily loading MCP server tool schemas on demand through two meta-tools.
Allows AI agents to drive your existing Chrome browser using dedicated tabs, colored groups, and isolated clipboards without taking over your screen.
Allows AI agents to verify signed content permissions, fetch token-budgeted markdown, and validate assets using cryptographically verifiable declarations.
$claude mcp add aifeed-protocol -- npx -y aifeed-mcp-server
Provides a community-maintained registry of MCP server definitions for easy installation via the McpMux desktop gateway.
Enables a human-in-the-loop workflow where an AI writes HTML and a human polishes it via a local visual editor, syncing changes back to the agent.
Provides a local-first vault for coding-agent session history, enabling hybrid search, decision extraction, and session recovery via MCP.
An AI coding agent that reads, edits, and runs code in local directories while requesting user approval for all changes.
Seeds realistic demo content into CMS platforms like Ghost to preview themes with authentic articles, images, galleries, and videos.
Lints API artifacts like OpenAPI, AsyncAPI, and JSON Schema against a comprehensive governance ruleset using OpenLint.
Decodes VINs to provide comprehensive vehicle reports including technical specs, recalls, safety ratings, and fuel economy.
Converts any web page into an interactive interface that AI agents can navigate, click, and input text into.
Provides approval-first terminal control for AI coding agents to drive interactive shells, CLIs, and TUIs with safety limits.
Enables AI agents to model parts, assemble components, verify mass properties, and generate engineering drawings within SOLIDWORKS.
Enables Claude Code to delegate hands-on coding tasks to OpenAI Codex using persistent threads, asynchronous execution, and interactive approvals.
Enables full-duplex messaging between different MCP-capable coding agents like Claude Code and Codex using a shared filesystem.