Memory and knowledge · MCP server
Vault Cortex: MCP server, setup and security
Vault Cortex is an open-source MCP server that lets an AI agent search and manage notes, files, memories and tasks in Obsidian vaults. Its repository has 31 stars and its last commit is from October 24, 2026 and it is licensed under MIT.
What Vault Cortex does
According to its repository: “Standalone Obsidian vault server: hybrid search, notes and files, memory and tasks; run locally or self-host for remote access.”
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. Vault Cortex is listed under Memory and knowledge, a category of 250 servers in the directory, where it ranks #123 by stars.
Topics declared by the repository: docker, obsidian, obsidian-vault, obsidian-mcp-server, obsidian-sync, knowledge-base.
Installing and connecting Vault Cortex
Distribution modes declared in the official MCP registry:
- Docker (OCI) image
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.
The registry lists one secret variable to provide (API key, access token). Keep them in the client's environment variables, never in a shared file or a repository.
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.
Points found for Vault Cortex:
- Secrets: the server acts with your credentials. Create a dedicated key with minimum rights and an expiry date.
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 May 1, 2026, the aliasunder/vault-cortex repository has 31 stars and 3 forks, with 0 open issues. It has more stars than 45% of the servers in the directory. It received changes this month. Version published in the registry: 0.55.2 (October 24, 2026).
Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.
Verdict
Vault Cortex 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)
Limitations
- Requires an API key or token
Avoid if…
- You do not want to give credentials to an agent
Alternatives
- Context763.6K ★
- Basic memory4.3K ★
- Hindsight53.4K ★
- Cognee32.7K ★
- Skill Seekers15.2K ★
- Honcho7.8K ★
Learn more
Frequently asked questions
How do I install Vault Cortex?
Vault Cortex is distributed as Docker (OCI) image. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of aliasunder/vault-cortex.
Is Vault Cortex free?
The code is published under the MIT licence and can be used free of charge. It needs an API key: the service it connects to may be paid.
Is Vault Cortex safe?
Points to watch: secrets. Give it minimum rights and approve sensitive actions.
Is it an official server?
Nothing says so: it is a project published by aliasunder on GitHub. Check who maintains it before giving it access.
What are the alternatives to Vault Cortex?
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