Spomory
← All platforms

Mistral Vibe

Mistral's own coding CLI — config.toml, local and cloud both real.

Mistral Vibe is Mistral AI's own minimal coding-agent CLI (github.com/mistralai/mistral-vibe) — real, documented MCP support for both local stdio servers and remote servers with custom headers. Verified end-to-end against a real Mistral Vibe installation, both local and cloud.

Local (stdio)

Add a [[mcp_servers]] table to config.toml. command runs uvx, which downloads and runs Spomory on demand — no install step:

[[mcp_servers]]
name = "spomory"
transport = "stdio"
command = "uvx"
args = ["--from", "spomory[llm,embedding,mcp]", "spomory-mcp"]

[mcp_servers.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 →

Mistral Vibe's MCP docs →

Cloud (API key)

Same file, an http transport entry with headers instead:

[[mcp_servers]]
name = "spomory-cloud"
transport = "http"
url = "https://api.yliuai.com/mcp-apikey/"
headers = { "x-api-key" = "<your key>" }

Verified against a real Mistral Vibe 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 →

Mistral Vibe'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:

Mistral Vibe auto-discovers skills from ~/.vibe/skills/spomory/SKILL.md (user) or ./.vibe/skills/ / ./.agents/skills/ (project, trusted directories only).

SKILL.md on GitHub →