@cup319/dsh-mmpl

MMPL (Memory Palace) memory plugin for DeepSeek Harness — connects the Rust DuckDB vector-memory MCP server via Streamable HTTP.

What it does

Mounts the shared @deepseek-ai/dsh-mcp-client against a running MMPL server, exposing its 9 memory tools as mcp__mmpl__*:

• memory_write / memory_search / memory_list
• memory_manage / memory_stats / memory_evolve
• memory_compress / memory_palace / memory_symbol

MMPL's Ebbinghaus forgetting curve, "memory palace" (archived-memory palace with confirm-before-purge), BM25 + ONNX semantic vector retrieval, and RRF fusion all live server-side — this bundle only wires the connection.

Prerequisites

A running MMPL server at http://127.0.0.1:7680/mcp. This bundle does not download, build, or supervise the server.

Install the server separately:

# npm (Rust single-binary edition)
npm install -g @cup319/mmpl-rust
mmpl-rust   # → http://127.0.0.1:7680/mcp

Install into a DSH profile

dsh plugin --profile <name> add @cup319/dsh-mmpl
dsh --profile <name>

Configuration

| Env | Default | Purpose | |---|---|---| | MMPL_URL | http://127.0.0.1:7680/mcp | Override the MCP endpoint (remote host / proxy) |

To add auth headers, patch the memory-mmpl row's config.headers in your profile's cordis.patch.yml (a user layer overrides the bundle row by id).

Verify

1. Session A: "Remember that my validation drink is lapsang-."
2. Session B: "What is my validation drink? Check memory."

The model should call mcp__mmpl__memory_search and return the recalled value.

Note

This is an independent community integration, not an official DeepSeek or MMPL endorsement. See examples/mcp-memory in the deepseek-harness repo for the reference integration pattern.