Doubao (豆包)

No config file — a point-and-click custom connector, local or cloud.

local stdio
cloud API key
verified

Doubao has no JSON or TOML config file at all — it has a point-and-click custom connector dialog instead. In Doubao: 技能・连接器・伙伴 → 新建 (+) → 新建自定义连接器.

Local (STDIO)

Pick transport type STDIO:

服务器名称 (server name): anything, e.g. Spomory
传输类型 (transport type): STDIO
命令 (command): uvx — downloads and runs Spomory on demand, no install step
参数 (arguments): two separate rows, --from spomory[llm,embedding,mcp] and spomory-mcp
环境变量 (environment variables): LLM_API_KEY, LLM_BASE_URL, LLM_MODEL

Prefer a fixed, pinned install over uvx's on-demand cache? Install into a virtual environment outside ~/Documents (pip install 'spomory[llm,embedding,mcp]'), set 命令 to that venv's bin/memory-core-mcp directly, and leave 参数 empty.

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 →

Full local setup guide on GitHub →

Cloud (HTTP, API key)

Pick transport type HTTP:

服务器名称 (server name): anything, e.g. Spomory Cloud
传输类型 (transport type): HTTP
服务器 URL: https://api.yliuai.com/mcp-apikey/ (the trailing slash is required)
自定义 Headers (custom headers): x-api-key → <your key>

Verified against a real Doubao client (2026-09-28) — add_memory called successfully through both the STDIO and HTTP setups above, 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 →

Full remote-access guide on GitHub →

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:

We couldn't find a documented Skills or custom-instructions feature for Doubao's consumer app specifically (its separate enterprise product, 豆包工作, has an unrelated skill.md upload mechanism). Check Doubao's own settings/help for anything resembling custom instructions before assuming this isn't possible.

SKILL.md on GitHub →