VS Code (Copilot)

Native MCP support — mcp.json, plus a guided Command Palette flow.

local stdio
cloud API key
verified

VS Code has native MCP support for GitHub Copilot's agent mode — a workspace or user config file, or the guided "MCP: Add Server" Command Palette flow. Verified against a real VS Code installation.

Local (stdio)

Add to .vscode/mcp.json in your workspace (servers key), or run "MCP: Add Server" from the Command Palette and choose Workspace or Global. command runs uvx, which downloads and runs Spomory on demand — no install step:

{
  "servers": {
    "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"
      }
    }
  }
}

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 args at []).

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 →

VS Code's MCP docs →

Cloud (API key)

Same file, an http-type entry instead:

{
  "servers": {
    "spomory-cloud": {
      "type": "http",
      "url": "https://api.yliuai.com/mcp-apikey/",
      "headers": {
        "x-api-key": "<your key>"
      }
    }
  }
}

VS Code's docs point to "input variables" for keeping secrets like this out of the file directly. Verified against a real VS Code 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 →

VS Code's MCP 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:

VS Code auto-discovers Agent Skills from .github/skills/, .claude/skills/, or .agents/skills/ (workspace), and ~/.copilot/skills/, ~/.claude/skills/, or ~/.agents/skills/ (personal) — separate from the older .github/copilot-instructions.md file.

SKILL.md on GitHub →