Commands come from the project's own docs or registry entry. Check them against the source before you run them.
Loading poll...
Codebase Memory is an npm package from DeusData, installed with npx -y codebase-memory-mcp over stdio. Its GitHub description says it gives developers and AI agents local code intelligence, linking code, docs and infrastructure in a persistent graph, with MCP tools and agent integrations. The licence is MIT. The repository shows 47.9 thousand stars and was pushed on 30 October 2026. We would suggest it to developers working in large codebases where an agent keeps losing track of structure, and who prefer a local tool to a hosted index. The main limit is that a code graph must be built and kept current, so check how indexing runs on your repository size before relying on it. It overlaps with Repowise and Repomix, which approach the same problem differently, and our roundups compare them. We have not run it ourselves.
Repowise offers codebase intelligence for AI and humans, per its repository: code health scores, auto-generated docs, git analytics, dead-code detection and architectural decisions, delivered through MCP.
Repomix packs a whole repository into one AI-friendly file, according to its GitHub description, and this entry is its MCP mode, run with npx -y repomix over stdio.
Claude Flow is published on npm as claude-flow, and its repository now sits at ruvnet/ruflo, which the GitHub description calls the original agent harness for deploying multi-agent swarms and coordinating autonomous workflows.
The e2e project from tester-army calls itself a next-generation end-to-end testing framework for web and mobile apps, and this entry is its npm MCP package, installed with npx -y e2e over stdio.
Tried it with one of these? Vote below: works for me, or not.
Questions
How do I install Codebase Memory MCP?
Run this command: claude mcp add codebase-memory -- npx -y codebase-memory-mcp. The install box on this page has the command for each agent it works with.
Is Codebase Memory MCP free?
It is published under the MIT licence.
Who maintains Codebase Memory MCP?
It is maintained by DeusData. The code is at github.com/DeusData/codebase-memory-mcp.
Scrapling is a Python web scraping framework from D4Vinci, described on GitHub as handling everything from a single request to a full-scale crawl, and this entry is its MCP server.
Context7 is an MCP server from Upstash that serves up-to-date library documentation to coding agents, so the model reads current docs instead of guessing from training data.