LibreChat

Self-hosted chat UI — librechat.yaml, both stdio and Streamable HTTP.

local stdio
cloud API key
verified

LibreChat is an open-source, self-hosted chat interface. Configure MCP servers in its librechat.yaml — both a local stdio server and a remote Streamable HTTP server with custom headers. Verified against a real LibreChat installation.

Local (stdio)

Add under mcpServers in librechat.yaml. 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"

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 →

LibreChat's MCP docs →

Cloud (API key)

Same file, a streamable-http entry with a headers block:

mcpServers:
  spomory-cloud:
    type: streamable-http
    url: https://api.yliuai.com/mcp-apikey/
    headers:
      x-api-key: "<your key>"

LibreChat's own docs recommend Streamable HTTP over stdio for anything beyond a single local user. Verified against a real LibreChat 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 →

LibreChat'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:

LibreChat auto-loads skills at startup from ./skill (configurable via DEPLOYMENT_SKILLS_DIR), each in its own subfolder with a SKILL.md — but only for Agents with "Enable Skills" turned on.

SKILL.md on GitHub →