Home / Token cost / Create Web Page

The Create Web Page MCP server costs 11,617 tokens before the first call.

Connect Create Web Page and its 23 tool definitions are loaded into the model's context on every request — 5.8% of a 200k window spent before your agent does anything.

QUICK ANSWER The Create Web Page MCP server's tool definitions consume 11,617 tokens — 6.1× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 23 tools · 11,617 tokens · 5.8% of 200k · 1.2% of 1M Method →

What that buys 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 5.8%
1M WINDOW 1.2%

Corpus context: Create Web Page ranks #140 of 3,213 measured MCP servers by definition cost. The median is 1,905 tokens, p90 is 7,952, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

Where the 11,617 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 505 tokens per tool.

ToolCategoryTokens% of server
block.update Write 3,523 30.3%
block.add Write 2,737 23.6%
page.create_from_brief Write 1,459 12.6%
page.theme.update Write 820 7.1%
page.onboarding.update Execute 415 3.6%
page.create Write 368 3.2%
page.intake.start Execute 294 2.5%
page.header.update Write 259 2.2%
page.onboarding.start Execute 230 2.0%
page.meta.update Write 223 1.9%
block.reorder Write 182 1.6%
block.delete Destructive 174 1.5%
page.publish Write 168 1.4%
source.import Read 135 1.2%
page.claim Destructive 113 1.0%
page.preview Write 85 0.7%
account.page.manage Write 75 0.6%
account.pages.list Read 73 0.6%
page.get Read 70 0.6%
page.unpublish Destructive 65 0.6%
presets.list Read 59 0.5%
account.whoami Write 52 0.4%
layouts.list Read 38 0.3%

Most agents use a handful of these tools. They pay for all 23.

A PolicyLayer grant exposes only the tools you allow — ungranted definitions are filtered out of the tool list, so they never enter the context window. Estimates below assume typical-weight tools (505 tokens each).

Grant scopeDefinition costReduction
All 23 tools (no gateway) 11,617 tokens
3 granted tools ~1,515 tokens −87%
5 granted tools ~2,525 tokens −78%
10 granted tools ~5,051 tokens −57%

Create Web Page token-cost questions.

How many tokens does the Create Web Page MCP server use?+

Its 23 tool definitions total 11,617 tokens — 5.8% 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 Create Web Page 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 Create Web Page's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Create Web Page 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 1,515 tokens, a 87% 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 07-06-2026 from the PolicyLayer scan database over all 23 catalogued Create Web Page tools. Counts refresh with every site build.

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

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

Free to start. No card required.

4,600+ MCP servers and 31,000+ 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.