PluginBench
MCP Server
Active
MIT

Perseus Vault — persistent, encrypted memory for AI agents MCP Server

io.github.Perseus-Computing-LLC/perseus-vault

Persistent, encrypted, deterministic memory system for AI agents with 173 canonical tools.

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the Perseus Vault — persistent, encrypted memory for AI agents MCP server?

The Perseus Vault MCP server is a local-first memory system that provides persistent, encrypted, and deterministic storage for AI agents. It offers 173 canonical tools designed to enable agents to reliably store, retrieve, and manage information across sessions.

Perseus Vault gives AI agents a secure, encrypted memory layer that persists across conversations and sessions. Built on local-first principles, it ensures data stays private while providing deterministic behavior for reproducible agent operations. With 173 built-in tools, it supports complex memory management workflows without external dependencies.

How to install Perseus Vault — persistent, encrypted memory for AI agents

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "perseus-vault": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/perseus-computing-llc/perseus-vault:2.23.2",
        "-i",
        "--rm",
        "-v",
        "perseus-vault-data:/data",
        "serve",
        "--db",
        "/data/perseus-vault.db"
      ]
    }
  }
}

Use cases

  • Store and retrieve conversation context across multiple AI agent sessions
  • Maintain encrypted knowledge bases and fact repositories for consistent agent behavior
  • Build deterministic workflows where agent decisions are reproducible based on stored memory
  • Implement secure multi-turn agent systems with persistent state management
  • Create audit trails of agent decisions and memory modifications

Perseus Vault — persistent, encrypted memory for AI agents MCP server FAQ

What is Perseus Vault?

Perseus Vault is a local-first memory system for AI agents that provides persistent, encrypted, and deterministic storage. It includes 173 canonical tools for managing agent memory across sessions.

Is it free?

The registry entry does not specify pricing; check the GitHub repository for license and cost details.

How do I install it?

Install via the OCI container image: ghcr.io/perseus-computing-llc/perseus-vault:2.23.2. Configure it in your MCP client (Cursor, Claude, or other MCP-compatible tools) to connect to this container.

Does it require authentication?

The README does not specify authentication requirements; refer to the GitHub repository documentation for setup details.

Is my data encrypted?

Yes, Perseus Vault provides encrypted storage by design, keeping data secure and local to your system.

Can I use it offline?

Yes, Perseus Vault is local-first, meaning it operates without requiring external services or internet connectivity.

Related MCP servers

Verifiable, hash-chained event provenance for autonomous systems. Local-first, MIT. 5 MCP tools.

4
Python
MIT
View repository →

Live context engine that resolves git, services, and tests into agent-ready context.

20
Python
MIT
View repository →
PEPERSONAIZER logo

Free MCP API to create AI chat personas for websites — upload knowledge, search, and chat

0
View repository →

Continuity for agents: a live memory you can read and cite right now, outliving the context window.

0
MIT
View repository →

Live aviation data for AI agents: METAR weather, airports, aircraft, glossary & FAA questions.

0
JavaScript
MIT
View repository →

Web search, clean page reading & one-call research dossiers for AI agents. No API key.

0
JavaScript
View repository →