analyze_catalog_budgetLABSCO SUMMARY
A budget for the one cost nobody budgets.
Tool definitions are charged to context on every single turn, and they are the part of an agent setup that grows quietly as you add servers. This puts a number on that and hands back a two-part index — a small eager list plus schemas fetched on demand — with a trace replay to confirm the model can still find the right tool afterwards. It is a paid hosted endpoint rather than something you run, so what you hand over is catalog metadata, not your data.
What it is
A remote MCP server aimed at a problem you only hit once several servers are connected at the same time: every tool definition rides along in the model's context on every turn, and nothing in the client tells you what that adds up to. It reads a catalog — a server URL, a server card, or a tools/list response — reports the cost, and hands back a slimmed version. The surface is read-only by design: no shell, no SQL, no deployment or deletion tools.
What you get
analyze_catalog_budgetmeasures eager catalog tokens and estimates what progressive loading would savegenerate_progressive_indexproduces an eager tool index plus an on-demand schema manifestreplay_trace_budgetchecks whether representative traces still route correctly against the slim indexcompare_client_loadingreturns client-specific notes for Claude, Codex, Cursor, Gemini CLI and custom clientsmonitor_catalog_driftcompares the current catalog budget against a prior baseline and a CI threshold
Requirements
Nothing to install. It is a hosted Streamable HTTP server at https://mcploadbudgeter.space/mcp, registered as space.mcploadbudgeter/mcploadbudgeter-mcp at version 0.1.0. Access is paid: complete checkout, claim the one-time bearer token, and send it as Authorization: Bearer <token>. The token is shown once.
Setup effort
Add the hosted endpoint plus a key — paste it into your client, then supply credentials
USE CASES
01
Finding out what your MCP setup costs per turn
Point it at a server URL or a tools/list response and read the eager catalog token count back.
02
Cutting a large tool catalog down to size
Generate a small eager index with schemas loaded on demand, then replay traces to confirm routing still works.
03
Keeping catalog growth out of your CI
Compare the current budget against a stored baseline and fail the gate when it drifts.
04
Checking how different clients load your tools
Get per-client notes for Claude, Codex, Cursor and Gemini CLI before you ship a config.
5 tools
Listed in project docs. Your client may show a different list.
generate_progressive_indexreplay_trace_budgetcompare_client_loadingmonitor_catalog_driftBEFORE YOU INSTALL
What to know first
Tools you get
5 tools named in the project's documentation.
Requires
- A paid plan on mcploadbudgeter.space; the bearer token is issued only after checkout and a one-time token claim
- An MCP client that supports remote Streamable HTTP servers and sends an Authorization header
INSTALLATION
Connect your client
Paste it into your client, then supply credentials.
Server setup
Setup
Open https://mcploadbudgeter.space/pricing/?utm_source=github&utm_medium=directory&utm_campaign=sbl202605.
Choose a plan and complete checkout.
Claim the one-time MCP bearer token from the hosted claim flow.
Paste only the token value into your MCP client secret field.
Configure the server URL as https://mcploadbudgeter.space/mcp in any MCP client that supports remote Streamable HTTP MCP servers and pass the bearer token in the Authorization header.
Hosted endpoint
ENDPOINT URL
https://mcploadbudgeter.space/mcpAdd this hosted endpoint to your MCP client using the credentials listed under Requirements.
