codebase-agent-mcp is an autonomous agent designed to provide token-efficient code analysis, documentation retrieval, and implementation guidance for large library repositories. Below are 31 ai & ml apps with similar functionality to codebase-agent-mcp, matched by what each product actually does — not ranked or scored. Explore each to find the closest fit for your use case.
codebase-memory-mcp is an open-source, fast code intelligence engine designed for AI coding agents. Distributed as a single static binary MCP server, it enables local analysis of codebases for agent frameworks and research. It is suitable for developers building AI-powered code tools and workflows.
contextl-mcp is an open-source MCP server designed for AI coding agents. It provides repository intelligence, code search, and integrates with the Model Context Protocol, allowing developers to build advanced AI-powered code tools. Distributed under the MIT license.
agentdrive-mcp is an open-source MCP server designed for use with Claude Code, enabling agent-driven automation and integration via API. It is suitable for developers building automation systems and agent frameworks.
cctx-mcp is an open-source MCP server designed for AI agents, offering structured code analysis that significantly reduces token usage. It integrates with Tree-sitter and is aimed at developers building efficient AI-powered code tools.
ucm-mcp is an open-source MCP server designed for AI-agent code navigation and mapping. It supports AST parsing and integrates with AI agents to facilitate code analysis and automation. The tool is aimed at developers building intelligent code navigation solutions or automating codebase understanding.
<!-- ~ Copyright (c) 2025-2026 Datalayer, Inc. ~ ~ BSD 3-Clause License --> [](https://datalayer.io) [](https://github.com/sponsors/datalayer) # 🤖 👨💻 Agent Codemode [](https://pypi.org/project/agent-codemode) **Generate programmatic tools from MCP Servers and Skills.** ## What is Agent Codemode? Agent Codemode generates **programmatic tools** from two sources: 1. **MCP Servers** - Connect to any MCP server and generate typed Python bindings for its tools 2. **Skills** - Reusable code patterns that compose multiple tools into higher-level operations These programmatic tools can be: - **Used directly by an agent** - Import generated bindings and call tools from your agent's code - **Exposed as an MCP Server** - Serve the generated tools via MCP protocol for any MCP-compatible client <p align="center"> <img src="https://images.datalayer.io/products/mcp-codemode/demo-claude-list-tools.png" width="55%" alt="" /> <img src="https://
agent-brain-ag-mcp is an open-source Model Context Protocol (MCP) server that exposes Agent Brain as MCP tools, resources, and prompts. It enables developers to integrate Agent Brain capabilities into agent-based applications, supporting RAG workflows and Claude integration. Ideal for AI developers seeking extensible agent frameworks.
agent-replay-debugger-mcp is an open-source CLI tool for debugging and auditing agentic AI workflows. It records every agent step, enables deterministic replay, and exports signed audit evidence. Designed for AI developers and researchers needing transparency and reproducibility in agentic loops.
agent-harnesses-mcp is an open-source MCP server that provides recommendations, search, and head-to-head decision guides for over 100 agent harnesses. It is designed for AI developers and researchers working with LLM-based agents, offering weekly rescoring and structured comparison tools.
agent-policy-enforcement-mcp is an open-source CLI tool that enables per-agent-pair IAM and policy enforcement for agent-to-agent (A2A) calls. It allows developers to define, enforce, and attest to policies, supporting compliance with EU AI Act and ISO 42001. Ideal for AI developers and security teams.
agentsec-cli is an open-source CLI tool that performs static security analysis on AI coding agents and Model Context Protocol (MCP) configurations. It helps developers and security teams identify vulnerabilities and misconfigurations in agent-based AI systems before deployment.
MCP Server for Claude Desktop - Agent OS kernel primitives including code safety verification, CMVK multi-model review, and IATP trust
central-mcp is an open-source Python package that serves as an agent-agnostic MCP hub for managing and orchestrating multiple coding agents. It enables AI developers to coordinate various coding agents using the Model Context Protocol (MCP).
purposebot-mcp is an open-source trust layer for the Model Context Protocol (MCP), offering agent identity, provenance, API access decisions, and trust-ranked discovery for agent-based commerce. It is aimed at developers building secure agent ecosystems.
miosa-mcp is an open-source MCP server that exposes MIOSA computer-use tools for integration with Claude Code and other agent frameworks. It provides a standardized API for agent developers to enable automation and computer control capabilities in their AI systems.
mcp-coder is an open-source CLI toolkit that leverages AI (Claude Code) and MCP servers to automate code analysis, testing, and implementation workflows. It is designed for developers seeking to streamline and enhance their software development processes with intelligent automation.
mcp-agent-tester is an open-source tool for inspecting, testing, and running MCP servers and agents. It provides both a web UI and CLI, supports JSON trace export, and is designed for developers working with Model Context Protocol agents and infrastructure.
agent-lsp is an open-source MCP server that bridges AI agents with language server protocol (LSP) features, providing code intelligence across 30+ languages. It enables agents to perform complex code operations with context, improving code quality and automation workflows.
Agent MCP Studio is a free, browser-based platform for building, running, and exporting Model Context Protocol (MCP) tools and AI agents. It enables developers to specify tools in natural language, generate code with LLMs, and run agents entirely in the browser or via Docker. Designed for AI developers and researchers.
mcp-mcts is an open-source CLI tool for local MCP security scanning, attack chain analysis, inventory management, and CI integration. It supports optional Semgrep and LLM analysis, making it suitable for security engineers and DevOps teams focused on codebase security.
dlb-mcp is an open-source CLI tool and MCP server that allows independent agent sessions to leave notes for each other using dead-letter semantics. It is lightweight, requires no daemon, and is suitable for developers building agent-based or distributed systems.
mcp-toolsmith is an open-source CLI utility for auditing and compiling Python tool schemas for use with LLM agents. It validates schemas against the Model Context Protocol, helping developers ensure compatibility and correctness before deployment.
agent-audit-logger-mcp is an open-source Python package for generating tamper-evident, hash-chained audit logs for agent-to-agent calls. It supports MCP, HMAC signing, and compliance with EU AI Act and DORA requirements, making it suitable for regulated AI systems.
MCP server that wraps the basecamp CLI.
mcp-defense is a CLI tool for AI infrastructure engineers and security teams, providing kernel-native runtime defense for AI agents. It enforces MCP tool-call policies and correlates kernel events to secure agentic workloads such as Claude Code, Codex, and Devin.
mcp-base is an open-source CLI tool for setting up and managing Model Context Protocol (MCP) servers. It supports OIDC authentication with providers like Auth0, Dex, and Keycloak, and integrates with Kubernetes for scalable deployments.
mcpolish is a command-line static linter for Model Context Protocol (MCP) servers. It helps developers catch vague, colliding, or misleading tool descriptions before AI agents interact with them, improving reliability and clarity in agentic workflows.
MCPfinder is an open-source tool that helps AI agents discover and configure Model Context Protocol (MCP) servers. It inspects trust signals, manages environment variables, and generates install-ready configurations, streamlining integration for developers building AI agents that interact with external tools and data sources.
air-blackbox-mcp is an open-source CLI tool and MCP server that scans AI agent code for compliance with the EU AI Act, GDPR, and bias detection. It helps developers and compliance teams analyze, remediate, and protect AI systems against regulatory risks.
Agentic Model Context Protocol server for NetBox — read-only, tool-rich, built for LLM reasoning workflows
ai-agentic-mcpscan is an open-source command-line tool that provides local-first, offline-by-default security posture scanning for Model Context Protocol (MCP) and local-agent environments. It is intended for security engineers and teams managing agent-based infrastructures.
