New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
Home / Token cost / InfraNode

The InfraNode MCP server costs 2,832 tokens before the first call.

Every request your agent makes carries every tool definition this server exposes — context your code, documents and conversation can't use, mostly for tools the agent never calls. You don't need them all in the window, and you don't have to pay for them.

QUICK ANSWER The InfraNode MCP server's 12 tool definitions consume 2,832 tokens — 1.4% of a 200k context window, and around the median MCP server (1,983 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #3054 of 7,332 measured servers · refreshed every build Method →

What that costs before your agent starts working.

Tool definitions are overhead: they occupy context on every request and compete with your code, documents and conversation history for the same window.

200K WINDOW 1.4%
1M WINDOW 0.3%

Corpus context: InfraNode ranks #3054 of 7,332 measured MCP servers by definition cost. The median is 1,983 tokens, p90 is 12,223, and the heaviest (Ainumbers Mcp Apps) is 322,450 — 161% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Where the 2,832 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 236 tokens per tool.

ToolCategoryTokens% of server
get_city_resource Read 738 26.1%
transit_departures Read 375 13.2%
get_city_overview Read 315 11.1%
weather Read 228 8.1%
compare Read 213 7.5%
get_city Read 199 7.0%
pois Read 191 6.7%
air_quality Read 189 6.7%
station_board_departures Read 135 4.8%
station_board_arrivals Read 126 4.4%
list_cities Read 66 2.3%
sources Read 57 2.0%

Your agent uses a handful of these tools. It pays for all 12.

You don't need all 12 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of InfraNode: only the tools you grant are exposed to the agent, the rest never load. A smaller window means a sharper agent — less noise when it picks a tool — and every request costs less:

Grant scopeDefinition costReduction
All 12 tools (no gateway) 2,832 tokens
3 granted tools ~708 tokens −75%
5 granted tools ~1,180 tokens −58%
10 granted tools ~2,360 tokens −17%
  1. Create a free account and register InfraNode — nothing to install.
  2. Grant only the tools you use — ungranted definitions never enter the context window.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CUT INFRANODE TOKEN COST →

Instant setup, no code required.

InfraNode token-cost questions.

How many tokens does the InfraNode MCP server use?+

Its 12 tool definitions total 2,832 tokens — 1.4% of a 200k context window — measured with tiktoken o200k_base over the serialised tools/list payload. Exact counts vary slightly by client and model.

Why does InfraNode consume tokens before I send a message?+

MCP clients load every connected server's tool definitions — name, description, and input schema — into the model's context so it knows what it can call. That payload is charged against your context window on every request, whether or not a tool is used.

How do I reduce InfraNode's token usage?+

Expose fewer tools. A PolicyLayer grant scopes InfraNode to only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. A grant of 3 typical tools costs roughly 708 tokens, a 75% reduction.

Does deferred tool loading fix this?+

Partially, in some clients. Claude Code defers MCP tool schemas behind a tool-search step by default, and VS Code has experimental grouping — but you still pay tokens per search and reload, and Cursor, Windsurf and Gemini CLI load definitions upfront. Reducing the exposed tool set cuts the cost in every client.

How these numbers were measured.

01
Serialisation

Each tool is serialised as a tools/list entry — name, description, input schema — from the schemas in the PolicyLayer scan database. Clients differ slightly in framing, so treat counts as close estimates.

02
Tokeniser

tiktoken o200k_base (GPT-4o/o-series). Anthropic's current tokeniser isn't published, so Claude's exact counts will differ; for English text and JSON schemas the totals are close enough to treat these as estimates.

03
Deferred loading

Some clients now defer schema loading (Claude Code's tool search; VS Code experimental grouping). You still pay per search and reload — and Cursor, Windsurf and Gemini CLI load everything upfront.

Computed 24-08-2026 from the PolicyLayer scan database over all 12 catalogued InfraNode tools. Counts refresh with every site build.

Expose only the tools you use — the rest never enter your context.

A PolicyLayer grant scopes InfraNode to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

Instant setup, no code required.

46,500+ MCP servers and 515,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.