LangChain / LangGraph

Code-level integration via langchain-mcp-adapters — shared by both frameworks.

local stdio
cloud API key
verified

LangChain and LangGraph are developer frameworks, not GUI apps — this is for building your own agent in Python or JS using the official langchain-mcp-adapters package, which both frameworks share under the hood. There's no settings screen; this goes into your own agent code. Verified against a real installation.

Local (stdio)

In your agent code. command runs uvx, which downloads and runs Spomory on demand — no install step:

from langchain_mcp_adapters.client import MultiServerMCPClient

client = MultiServerMCPClient({
    "spomory": {
        "command": "uvx",
        "args": ["--from", "spomory[llm,embedding,mcp]", "spomory-mcp"],
        "env": {
            "LLM_API_KEY": "...",
            "LLM_BASE_URL": "https://api.deepseek.com",
            "LLM_MODEL": "deepseek-v4-flash",
        },
        "transport": "stdio",
    }
})
tools = await client.get_tools()

Prefer a fixed, pinned install over uvx's on-demand cache? Install into a virtual environment outside ~/Documents (pip install 'spomory[llm,embedding,mcp]'), then point command at that venv's bin/memory-core-mcp directly (and drop args).

Where do these environment variables come from?

LLM_API_KEY is your key for whichever OpenAI-compatible provider you use for extraction — OpenAI, DeepSeek, Qwen, and others all work. LLM_BASE_URL and LLM_MODEL default to OpenAI if you leave them out; swap them to point at DeepSeek, Qwen, or any other OpenAI-compatible provider, or a fully local server (Ollama, vLLM, llama.cpp, MLX):

export LLM_API_KEY=...
export LLM_BASE_URL=https://api.deepseek.com   # optional, defaults to OpenAI
export LLM_MODEL=deepseek-v4-flash             # optional, defaults to gpt-4o-mini
export EMBEDDING_MODEL=BAAI/bge-m3             # optional, defaults to bge-m3

Full local setup guide, including the macOS ~/Documents gotcha →

langchain-mcp-adapters docs →

Cloud (API key)

Same client, an http entry with headers instead:

client = MultiServerMCPClient({
    "spomory-cloud": {
        "transport": "http",
        "url": "https://api.yliuai.com/mcp-apikey/",
        "headers": {
            "x-api-key": "<your key>",
        },
    }
})

Verified against a real installation, resolving to the same account/memory graph as every other client on this page.

Where does <your key> come from?

Get one instantly with curl — fine for your own testing:

curl -X POST https://api.yliuai.com/users/register \
  -H "Content-Type: application/json" \
  -d '{"email": "you@example.com"}'
# the api_key in the response (starts with mck_) is shown only this once -- save it

That hands you a key with no proof you control the email — fine for testing, but for real use, get one through the email-confirmation form instead, which actually verifies the address.

Get a verified key on the Cloud & Apps page →

langchain-mcp-adapters docs →

Make it actually get used

Connecting the tools doesn't mean your client reaches for them on its own — it needs to be told to call search_memory before answering and add_memory after you share something worth keeping. SKILL.md is a short instructions file that does that. How you load it is specific to each client: some auto-discover a skills folder the same way Claude Code does, others only have a custom-instructions or system-prompt field instead. Verified for this one:

Core LangChain/LangGraph has no file-discovery convention — the system prompt is just a string in your own code. (The optional deepagents add-on does support SKILL.md folders, but only if you pass the path explicitly in your agent's constructor.)

SKILL.md on GitHub →