Spomory
← All platforms

Amazon Q Developer CLI

AWS's coding agent — verified local and cloud, via the OAuth endpoint.

Amazon Q Developer CLI (qchat) has real MCP support. Remote MCP servers are only documented for OAuth or no-auth in AWS's own docs — no custom-header path was found — so the cloud section below points at Spomory's OAuth mount (the same one Claude Desktop uses). Verified against a real installation, both local and cloud.

Local (stdio)

Edit the agent config directly (~/.aws/amazonq/cli-agents). command runs uvx, which downloads and runs Spomory on demand — no install step:

{
  "mcpServers": {
    "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"
      }
    }
  }
}

q mcp add also supports adding a server without editing the file directly — check q mcp add --help for how it expects args to be passed alongside --command uvx.

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.

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 →

Amazon Q Developer's MCP docs →

Cloud (OAuth 2.1)

AWS's own docs only show remote MCP servers using OAuth or no auth. This connects to Spomory's OAuth mount:

{
  "mcpServers": {
    "spomory-cloud": {
      "type": "http",
      "url": "https://api.yliuai.com/mcp"
    }
  }
}

This points at Spomory's OAuth-authenticated mount rather than the x-api-key one, since that's the only remote auth style AWS documents. Verified against a real installation — Amazon Q's OAuth flow completes against Spomory's OAuth provider and resolves to the same account/memory graph as every other client on this page.

Amazon Q Developer'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:

Amazon Q doesn't read SKILL.md directly — its custom-agent config (.amazonq/cli-agents/<name>.json or ~/.aws/amazonq/cli-agents/<name>.json) has a prompt field that accepts a file:// URI, which you can point at SKILL.md.

SKILL.md on GitHub →