Memory and knowledge · MCP server
CodeCortex: MCP server, setup and security
CodeCortex is an open-source MCP server that lets an AI agent retrieve persistent codebase knowledge about symbols, dependencies and architectural decisions. Its repository has 10 stars and its last commit is from April 21, 2026 and it is licensed under MIT.
What CodeCortex does
According to its repository: “Persistent codebase knowledge for coding agents: symbols, dependency graphs, co-change patterns and architectural decisions extracted with tree-sitter.”
An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. CodeCortex is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #194 by stars.
Topics declared by the repository: ai-agents, developer-tools, typescript, claude-code, code-analysis, context-engineering.
Installing and connecting CodeCortex
No package or remote server is declared in the official MCP registry: you install it from source, following the repository README.
Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript. Listed systems: macOS, Windows, Linux.
Security: what to check
An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.
None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to CodeCortex. That does not replace reading the code.
Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.
Project activity and maintenance
Created on February 25, 2026, the rushikeshmore/CodeCortex repository has 10 stars and 1 forks, with 0 open issues. It has more stars than 26% of the servers in the directory. Last change 6 months ago.
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
CodeCortex is still a modest project: read its code and compare it with the alternatives before using it.
Strengths
- Permissive licence (MIT)
Limitations
- No commit for 6 months
- Few visible users
- Install from source
Alternatives
- Context763.6K ★
- Basic memory4.3K ★
- Hindsight53.4K ★
- Cognee32.7K ★
- Skill Seekers15.2K ★
- Honcho7.8K ★
Learn more
Frequently asked questions
How do I install CodeCortex?
No package is declared in the MCP registry: clone the rushikeshmore/CodeCortex repository, follow its README, then declare the start command in your client's MCP configuration.
Is CodeCortex free?
The code is published under the MIT licence and can be used free of charge.
Is CodeCortex safe?
No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.
Is it an official server?
Nothing says so: it is a project published by rushikeshmore on GitHub. Check who maintains it before giving it access.
What are the alternatives to CodeCortex?
In the same category: Context7, Basic memory, Hindsight, and Cognee. Context7 and Basic memory score higher on our grid.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score