TACIT: Tracked Agent Capabilities In Types
TACIT (Tracked Agent Capabilities In Types) is a safety harness for AI agents. Instead of calling tools directly, agents write code in Scala 3 with capture…
Directory
TACIT (Tracked Agent Capabilities In Types) is a safety harness for AI agents. Instead of calling tools directly, agents write code in Scala 3 with capture…
Enables secure execution of macOS terminal commands through a ZSH shell with a whitelist system that categorizes operations as safe, requiring approval, or…
Integrates with Postman Tool Generation API to convert API collections into type-safe code for AI frameworks, enabling rapid development of AI-powered tools…
Integrates Python development tools for file operations, code analysis, project management, and safe code execution, enabling advanced programming workflows…
Executes code snippets in isolated Docker containers with resource limits and security controls for safe testing and debugging across multiple programming…
Enables integration with DuckDuckGo search capabilities for LLMs, supporting comprehensive web search, regional filtering, result types, and safe browsing with…
A content security protection system for large language models, providing real-time risk identification and interception to ensure safe, compliant, and…
A content security protection system for large language models, providing real-time risk identification and interception to ensure safe and compliant…
Provides read-only access to MySQL databases for schema inspection and safe query execution, enabling database exploration and data analysis without modifying…
The batteries-included, No-Code FinOps automation platform, with the AI you trust.
.NET Core D365 MCP Server exposing Dynamics 365 tools. Uses .NET OData client.
Run a MCP client & server demo with DeepSeek API
Config-driven MCP proxy that adds session-safe file uploads, artifact handling, and robust state and health controls for upstream MCP servers.
Generates a secure, shareable URL for any AI-created visual content (charts/dashboards/HTML) with preserving full interactivity, support Claude, DeepSeek…
This is a sample CLI chat application for an AI assistant using the Anthropic API in conjunction with an MCP client and MCP server.
Shared memory and coordination for AI coding sessions. Persistent sprint board, human-in-the-loop queue, and parallel session protection. Works with Claude…
# 🚀 Greptile MCP Server - TypeScript Edition [](https://badge.fury.io/js/greptile-mcp-server)…
Lightweight MCP client that uses a local Ollama LLM to query multiple MCP servers defined in config.json
<p align="center"> <img width="395" alt="prompts.chat" src="https://github.com/user-attachments/assets/e0d0e32d-d2ce-4459-9f37-e951d9f4f5de" /> </p> <h3…
# SSE-based Server and Client for [MCP](https://modelcontextprotocol.io/introduction) [![smithery…
# n8n AI Agent with Local MCP Integration (Docker + npx) This repository contains an n8n workflow demonstrating how to integrate the Model Context Protocol…
AI-native customer onboarding: live projects, KPIs, tasks, and emails with Onboard MCP. Connect Onboard to Claude or any MCP-compatible AI client to seamlessly…
# Standardizing LLM Interaction with MCP Servers Model Context Protocol, or MCP, is [an open protocol that standardizes how applications provide context to…
The WhatsApp MCP Assistant (Client‑Server) is a natural‑language pipeline that sends and schedules WhatsApp messages. It uses a Mistral LLM to interpret user…