FRENES

Memory and knowledge · MCP server

Cortex (cdeust): MCP server, setup and security

Cortex (cdeust) is an open-source MCP server that lets an AI agent maintain Claude Code memory with decay and consolidation on PostgreSQL/pgvector. Its repository has 75 stars and its last commit is from October 24, 2026 and it is licensed under MIT.

Actively maintained

What Cortex (cdeust) does

According to its repository: “Neuroscience-inspired memory for Claude Code on PostgreSQL/pgvector: decay, consolidation, a predictive-coding write gate and lifecycle hooks.”

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. Cortex (cdeust) is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #88 by stars.

Topics declared by the repository: agent-memory-system, causal-inference, claude-code, cognitive-architecture, cognitive-science, neuroscience.

Installing and connecting Cortex (cdeust)

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)

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: Python. Listed systems: macOS.

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 Cortex (cdeust). 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 March 18, 2026, the cdeust/Cortex repository has 75 stars and 15 forks, with 53 open issues. It has more stars than 61% of the servers in the directory. It received changes this month. Version published in the registry: 4.23.5 (September 23, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

Context7Context7 : 63.6K63.6KHindsightHindsight : 53.4K53.4KCogneeCognee : 32.7K32.7KSkill SeekersSkill Seekers : 15.2K15.2KHonchoHoncho : 7.8K7.8KBasic memoryBasic memory : 4.3K4.3KNoteDiscoveryNoteDiscovery : 2.8K2.8KMemantoMemanto : 2.3K2.3KCortex (cdeust)Cortex (cdeust) : 7575
GitHub stars of the most followed servers in the category (log scale); Cortex (cdeust) in orange. Checked October 25, 2026.

Verdict

Cortex (cdeust) is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Frequently asked questions

How do I install Cortex (cdeust)?

Cortex (cdeust) is distributed as PyPI package (Python, started with uvx or pip). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of cdeust/Cortex.

Is Cortex (cdeust) free?

The code is published under the MIT licence and can be used free of charge.

Is Cortex (cdeust) 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 cdeust on GitHub. Check who maintains it before giving it access.

What are the alternatives to Cortex (cdeust)?

In the same category: Context7, Basic memory, Hindsight, and Cognee. Context7 and Basic memory score higher on our grid.

Related articles

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