`recall_memory`

Memory read

What it does

Returns memories ranked by importance (desc) then recency. Bumps last_accessed_at on every returned row so a cleanup job can spot stale rules.

Best practice: agents call this at the start of any creative or compliance task so brand rules they didn't personally save still apply.

Input schema

Name	Type	Required	Default	Description
query	string	optional	`—`	Case-insensitive substring matched against `content` + `topic`.
type	string	optional	`"any"`	Filter to a single memory type, or `"any"`.
min_importance	number	optional	`0`	Use `8` to fetch only hard rules.
limit	number	optional	`20`	Hard cap `100`.

Example call

json{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "recall_memory",
    "arguments": {
        "type": "rule",
        "min_importance": 7
    }
  }
}

Response shape

json{
  "ok": true,
  "count": 2,
  "filters": { "query": null, "type": "rule", "min_importance": 7, "limit": 20 },
  "memories": [
    {
      "id": "mem_4f2a...",
      "type": "rule",
      "topic": "brand-corposost-no-scale-closeups",
      "content": "CorpoSostenibile NEVER wants...",
      "importance": 9,
      "source": "claude",
      "created_at": 1747830000,
      "updated_at": 1747830000,
      "last_accessed_at": 1747890000
    }
  ]
}

Usage from Claude Desktop

prompt"What hard rules do we have for CorpoSostenibile? I'm about to suggest cuts."

Usage from Python

pythonimport requests

LUMIQA = "https://lumiqa.io/mcp/your-slug"
HEADERS = {"Authorization": "Bearer lk_live_xxxxxxxxxxxx"}

r = requests.post(LUMIQA, headers=HEADERS, json={
    "jsonrpc": "2.0", "id": 1,
    "method": "tools/call",
    "params": {
        "name": "recall_memory",
        "arguments": {"query": "corposost", "min_importance": 7}
    },
})
print(r.json())

Usage from Node

javascriptconst r = await fetch("https://lumiqa.io/mcp/your-slug", {
  method: "POST",
  headers: {
    "Authorization": "Bearer lk_live_xxxxxxxxxxxx",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    jsonrpc: "2.0", id: 1,
    method: "tools/call",
    params: {
      name: "recall_memory",
      arguments: { query: "corposost", min_importance: 7 },
    },
  }),
});
const data = await r.json();
console.log(data);

Required env vars / integrations

D1 table workspace_memories.

Known limitations

Substring search only — no full-text / embeddings yet.
Returns up to 100 rows; iterate by topic or type for larger pulls.
Bumping last_accessed_at mutates state on every call — cache locally if you're fanning out hundreds of recalls.

recall_memory