mcp-shell-server
AI agentsSecure shell command execution.
3,047 results · Page 69 of 85
Secure shell command execution.
Static security scanner for MCP servers and agent tools: detects secrets, shell execution, risky tool descriptions, environment access and prompt injection.
Learning sidecar for AI coding assistants: quizzes developers on AI-generated changes and gives agents persistent project-specific debugging memory via RAG.
Safe Python interpreter based on Hugging Face smolagents' LocalPythonExecutor.
Send desktop notifications with a sound effect when agent tasks complete.
Global search engine for Model Context Protocol (MCP) tools and AI agents.
Self-hosted MCP server registry for enterprise AI agents.
Connect AI agents to interactive live R sessions.
Connect AI agents to MCP servers from one config synced across coding tools, served through one process with compact tool discovery and spec validation.
Real-time Markdown document system that keeps the same doc live in both the browser and the terminal, giving humans collaborative editing while agents can pull, edit, and push through a CLI with three-way merge behavior.
AI-powered ecosystem for sales, marketing, and customer engagement automation.
Meet Pearl, the World's First AI-Driven Phone Agent
Bring an agent into live Google Meet or Zoom calls via a Chrome extension: read captions, answer in a side panel, post to chat and view shared screens.
Cloud-based project management software with AI for automation and efficient business management.
Melete is an AI workspace for teams and individuals that deploys AI agents to research, draft, and execute tasks in commonly used tools such as Slack, Notion, Linear, and GitHub. It emphasizes controllable memory, human approval, and cross-team handoffs, making it suitable for repetitive workflows such as weekly reports, customer handoffs, and release briefs. Individuals can also use it as a personal assistant in a separate space.
Contract intelligence platform for legal document analysis and workflow automation.
Universal memory agent for AI: provides semantic search, namespace management, text/vector operations and RAG for local or remote environments.
Save and query agent memory in a distributed way with Membase.
Local-first memory for coding agents: stores facts, decisions, patterns and architecture notes in SQLite to reduce repeated context across sessions.
Platform for creating and deploying AI personalities (Mements) with autonomous workflows.
Watches git repos and builds a temporal knowledge graph of modules, symbols, decisions and open problems via Graphiti and Neo4j, served to AI coding agents.
Persistent agent memory with semantic search and recency decay, local ONNX embeddings, background summarization and Prometheus/Grafana observability.
Git-like memory system for AI agents, built to branch, preserve, and manage context instead of treating memory as one flat shared log.
Self-hosted, remotely accessible shared long-term memory for AI agents.
Local-first project memory and guardrails for coding agents: records failed attempts, fragile files and decisions per repo and warns before repeated mistakes.
Local-first memory for AI agents in one SQLite file: hybrid BM25 and on-device embedding search with reranking, abstaining instead of returning wrong memories.
Memmy
Shared memory layer for teammates and AI agents that keeps context portable across tools such as Cursor, Claude Code, ChatGPT, and Raycast AI.
Local memory middleware: targeted retrieval instead of full-memory loading, rule-based conflict arbitration and one SQLite store shared across coding agents.
Persistent semantic and graph-based agent memory in a single self-contained binary with embedded database and models.
XMemo: user-owned agent memory to save, search, recall and manage scoped memories across AI tools.
Local-first governed shared memory for coding agents with CLI and desktop console: classify, dedupe, supersede, quarantine and roll back memories.
Open-source AI memory system that stores full conversations and project data locally without cloud dependencies. Organizes memories into a hierarchical "palace" structure, achieves 96.6% recall on LongMemEval — the highest published score for a fully local setup that calls no APIs, supports MCP inte
Versioned, structured agent memory storing facts as keypaths with full version history and automatic conflict detection.
Memvid is an open-source, serverless memory layer and database alternative that provides AI agents, LLMs, and application workflows with long-term data persistence. The software compiles unstructured documents, chat history, notes, and media files into a single, portable index file (such as .mv2 or
Shared context for dev teams: syncs GitHub, Notion and saved decisions into reusable project context that agents load at the start of each session.