Limits

Hard caps

Limit	Value
Ideas per POST /ideas/import call	25
Ref window returned by GET /ideas/mining-context	90 days
Brand header	X-Postlyra-Brand

Tool	Cap
push_ideas	25 ideas per call
list_ideas	50 results, no pagination cursor
get_mining_context	Refs from the last 90 days

list_ideas returning has_more: true means there are more than 50 matching ideas and you cannot page past them. Narrow with the status or format arguments instead.

Rate limits

There is no rate limit on the MCP server today.

That is not a guarantee

It is a current implementation fact. Limits get added when they are needed, and a client that hammers the server will be the one that breaks first. Batch pushes into calls of 25, and do not poll list_ideas in a loop.

Plan allowances

MCP calls do not consume AI credits. Your agent's own model calls are billed by whoever provides that model, not by Postlyra, which is the whole point of mining client side.

What plan limits do apply: the brands you can reach are the brands your account has, and the content profile requirement below.

Requirements

A content profile must exist. get_mining_context and push_ideas both need one, because the voice, pillars and persona come from it. Without one you get:

No profile configured for this team yet — add one before importing ideas.

Create one in Studio, under Content profiles. See Content profiles.

What is not supported

	Status
OAuth and client registration	Not implemented. Bearer token only
Hosted connectors (claude.ai, ChatGPT)	Cannot add this server, see above
Per-tool permission tiers	Not implemented. A token reaches every tool
Approving or publishing	Deliberately impossible, and will stay that way
Reading your local files	The server never does this. Your agent does