Pensyve MCP Server

Universal memory runtime for AI agents — episodic, semantic, and procedural memory.

Remote serverstreamable-httpPython

What is the Pensyve MCP server?

Most knowledge and memory work still happens through a UI a human drives. Pensyve MCP server moves it into the conversation instead. Universal memory runtime for AI agents — episodic, semantic, and procedural memory.

The short version

Universal memory runtime for AI agents. Framework-agnostic, protocol-native, offline-first.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • Variable — Default
  • PENSYVE_API_KEYS(empty)
  • PENSYVE_VALIDATION_URL(none)
  • PENSYVE_RATE_LIMIT — 300
  • HOST — 0.0.0.0
  • PORT — 3000
  • Core — The Core tool exposed by this server
  • Benchmarks — The Benchmarks tool exposed by this server

What it needs from you

Configuration is passed through the environment: PENSYVE_PATH, PENSYVE_API_KEY, PENSYVE_VALIDATION_URL, PENSYVE_REMOTE_URL, DATABASE_URL, REDIS_URL, PENSYVE_TIER2_MODEL_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Pensyve's toolset — Variable, PENSYVE_API_KEYS, PENSYVE_VALIDATION_URL and 5 more — is a fair guide to whether it matches your workflow. It is maintained by major7apps; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Pensyve's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
VariableDefault
PENSYVE_API_KEYS_(empty)_
PENSYVE_VALIDATION_URL_(none)_
PENSYVE_RATE_LIMIT300
HOST0.0.0.0
PORT3000
CoreThe Core tool exposed by this server.
BenchmarksThe Benchmarks tool exposed by this server.

How to install the Pensyve MCP server

```json
{
  "mcpServers": {
    "pensyve": {
      "command": "./target/release/pensyve-mcp",
      "env": { "PENSYVE_PATH": "~/.pensyve/default" }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
PENSYVE_PATHFilesystem location the server is allowed to use.Optional
PENSYVE_API_KEYCredential the server authenticates with.Yes
PENSYVE_VALIDATION_URLEndpoint or connection string the server talks to.Yes
PENSYVE_REMOTE_URLEndpoint or connection string the server talks to.Yes
DATABASE_URLEndpoint or connection string the server talks to.Yes
REDIS_URLEndpoint or connection string the server talks to.Yes
PENSYVE_TIER2_MODEL_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Pensyve to Variable.
  • Use Pensyve to PENSYVE API KEYS.
  • Use Pensyve to PENSYVE VALIDATION URL.

Frequently asked questions

It connects Pensyve to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (Variable, PENSYVE_API_KEYS, PENSYVE_VALIDATION_URL, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Pensyve directly.