MCP servers that give coding agents real developer tooling: linters, package registries, test runners, language docs and local build commands. 13,961 servers in this category.
Converts Python functions into MCP servers with automated Gradio web interfaces for testing and demonstration.
Verifies AI agent responses for hallucinations, citation accuracy, numeric drift, and workspace symbol grounding using deterministic rules.
Secures MCP tool usage by locking tool definitions, guarding agent tool calls with deterministic policies, and generating signed audit receipts.
An interactive multi-agent development system where ten specialized AI agents collaborate with users to plan, code, test, and review software.
Lets an AI client read real-time documentation and API signatures directly from installed Python packages to prevent hallucinations.
Allows Claude to read and edit Visual Paradigm (.vpp) projects, including class diagrams, sequence diagrams, and design patterns.
A self-hosted MCP gateway that enables AI clients to remotely control Windows and Linux computers via terminal, file systems, and desktop GUI tools.
A self-hosted memory infrastructure that turns conversations and application events into traceable, searchable knowledge graphs for AI agents.
Enables AI clients to perform semantic, full-text, and structural code searches across repositories using vector embeddings and SCIP indexes.
Scans AI agent skills, plugins, and MCP configurations for security risks like hardcoded secrets, suspicious instructions, and excessive permissions.
Provides a local-first, Markdown-native memory layer for AI coding agents to store project decisions and troubleshooting fixes.
Enables AI clients to generate, layout, and validate document-ready UML class and sequence diagrams with PNG output.
Allows an AI assistant to analyze videos by generating contact sheets of sharpest frames and extracting full-sized individual frames.
Performs static security analysis on AI agent skills and MCP server configurations to detect prompt injection, credential theft, and malicious instructions.
Build spec-compliant MCP servers quickly using Python type hints to automatically generate JSON Schemas for tools, resources, and prompts.
Translates natural-language arguments into English for English-only MCP servers while preserving JSON schema structure and localizing tool results.
Scans MCP server configurations for poisoned tool descriptions, over-privileged access, malicious packages, and unsafe transport methods.
Provides an AI agent and MCP server for secure, local access to e-commerce data using Qwen via Ollama and SQLite.
Scans coding agent files and git history to detect and fix hardcoded secrets in MCP configs, Claude Code settings, and session transcripts.
Scans Claude Code agents, skills, and MCP configurations to detect security risks like over-privileged permissions and unpinned dependencies.
