Documentation
Knowledge
knowledge.capacity
REST
ShippingPOST /api/v1/knowledge/capacityMCP tool
Liveknowledge.capacityExposed on: REST API · Shop MCP server · Claude connector · Dash (in-app copilot) · Zapier. Part of the Knowledge domain.
Operating contract
How many facts this shop may hold, how many it is using, and how much of them can reach one AI call.
TWO DIFFERENT LIMITS, and they answer different questions. limit is how many facts the shop may SAVE — a cap enforced when a new one is added. recall_chars is how much of them fits into ONE grounded AI call, and it is the one that decides what an agent actually knows in a given moment.
A shop at its recall budget with a hundred facts is not using a hundred facts: the budget is spent on the brief, then the PINNED facts, then everything else newest-first, cutting on whole-fact boundaries. That is why pinning matters and why a shop that edits its FAQ weekly can push its own warranty terms out of every prompt without touching them.
limit: null means the plan is unlimited on saved facts. The recall budget still applies — it is a property of a prompt, not of a plan's generosity.
A CAP, NOT A GATE. A shop that drops to a smaller plan keeps every fact it ever saved and simply cannot add another until it is back under the number. Nothing is ever deleted by a downgrade, and saying otherwise would frighten somebody for no reason.
One shop's allowance, returned whole, so nothing is truncated.
Who may call it
- Permission
shop.manageThe caller must hold shop.manage at the ACT level. A read-only dashboard grant on the same section is refused.- Plan
- Every planNo plan gate. Available on every Service VIN plan.
- Retries
naturalNaturally idempotent — running it twice leaves the same world as running it once. A retrying integration needs no key.- Rate class
readCounted against the read budget — the widest of the four.
Input
This capability takes no arguments.
Output
| Field | Type | Description |
|---|---|---|
| used | number | — |
| limit | number | null | — |
| recall_chars | number | — |
| plan | string | — |
Examples
Built from this capability's own schema — required fields and the ones carrying a default, and nothing invented. Paste one and it validates.
export SERVICEVIN_API_KEY=svk_live_…
curl -X POST https://www.servicevin.com/api/v1/knowledge/capacity \
-H "Authorization: Bearer $SERVICEVIN_API_KEY" \
-H "Content-Type: application/json" \
-d '{}'const res = await fetch("https://www.servicevin.com/api/v1/knowledge/capacity", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.SERVICEVIN_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({}),
});
// Success and failure are both envelopes. Switch on error.code, never
// on error.message — the codes are stable, the messages are for people.
const payload = await res.json();
if (!res.ok) throw new Error(payload.error.code);
const data = payload.data;import os, requests
res = requests.post(
"https://www.servicevin.com/api/v1/knowledge/capacity",
headers={"Authorization": f"Bearer {os.environ['SERVICEVIN_API_KEY']}"},
json={},
timeout=30,
)
payload = res.json()
if not res.ok:
raise RuntimeError(payload["error"]["code"])
data = payload["data"]{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "knowledge.capacity",
"arguments": {}
}
}Refusals
The four gates run in this order on every surface, and the order is not arbitrary — see Authentication.
| Status | Code | When |
|---|---|---|
| 404 | not_found | The id is unknown, or the feature is not enabled for this account. Deliberately the same answer for both. |
| 403 | forbidden | This login does not hold shop.manage. |
| 422 | validation_error | An argument was wrong. The message names the field. |
| 429 | rate_limited | Too many read calls. Back off and retry. |
| 500 | internal_error | Something failed on our side. Nothing was changed. |