Home / Token cost / NOSTOS

The NOSTOS MCP server costs 1,737 tokens before the first call.

Connect NOSTOS and its 14 tool definitions are loaded into the model's context on every request — 0.9% of a 200k window spent before your agent does anything.

QUICK ANSWER The NOSTOS MCP server's tool definitions consume 1,737 tokens — around the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 14 tools · 1,737 tokens · 0.9% of 200k · 0.2% 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 0.9%
1M WINDOW 0.2%

Corpus context: NOSTOS ranks #1685 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 1,737 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 124 tokens per tool.

ToolCategoryTokens% of server
search_inventory Read 318 18.3%
get_trade_in_offer_estimate Read 279 16.1%
lookup_market_price Read 169 9.7%
get_shipping_estimate Read 157 9.0%
check_availability Read 133 7.7%
get_condition_grading_rubric Read 105 6.0%
get_item Read 99 5.7%
list_recent_drops Read 91 5.2%
get_buying_policy Read 73 4.2%
get_store_info Read 70 4.0%
get_credit_policy Read 66 3.8%
list_departments Read 65 3.7%
get_return_policy Read 59 3.4%
list_platforms Read 53 3.1%

Most agents use a handful of these tools. They pay for all 14.

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 (124 tokens each).

Grant scopeDefinition costReduction
All 14 tools (no gateway) 1,737 tokens
3 granted tools ~372 tokens −79%
5 granted tools ~620 tokens −64%
10 granted tools ~1,241 tokens −29%

NOSTOS token-cost questions.

How many tokens does the NOSTOS MCP server use?+

Its 14 tool definitions total 1,737 tokens — 0.9% 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 NOSTOS 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 NOSTOS's token usage?+

Expose fewer tools. A PolicyLayer grant scopes NOSTOS 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 372 tokens, a 79% 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 14 catalogued NOSTOS tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes NOSTOS 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.