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

The Gradus Notation MCP server costs 5,767 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 Gradus Notation MCP server's 10 tool definitions consume 5,767 tokens — 2.9% of a 200k context window, and 3.1× the median MCP server (1,879 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #2437 of 9,299 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 2.9%
1M WINDOW 0.6%

Corpus context: Gradus Notation ranks #2437 of 9,299 measured MCP servers by definition cost. The median is 1,879 tokens, p90 is 13,073, and the heaviest (Ainumbers Mcp Apps) is 342,008 — 171% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Where the 5,767 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 577 tokens per tool.

ToolCategoryTokens% of server
notation_render Read 1,174 20.4%
knowledge_search Read 859 14.9%
theory_analyze_score Read 670 11.6%
theory_pitch_utils Read 594 10.3%
notation_validate Read 580 10.1%
theory_validate_ranges Read 491 8.5%
theory_respell Read 429 7.4%
notation_examples Read 339 5.9%
theory_parse_xml Read 323 5.6%
notation_schema Read 308 5.3%

Your agent uses a handful of these tools. It pays for all 10.

You don't need all 10 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Gradus Notation: 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 10 tools (no gateway) 5,767 tokens
3 granted tools ~1,730 tokens −70%
5 granted tools ~2,884 tokens −50%
  1. Create a free account and register Gradus Notation — 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 GRADUS NOTATION TOKEN COST →

Instant setup, no code required.

Gradus Notation token-cost questions.

How many tokens does the Gradus Notation MCP server use?+

Its 10 tool definitions total 5,767 tokens — 2.9% 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 Gradus Notation 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 Gradus Notation's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Gradus Notation 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 1,730 tokens, a 70% 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 20-09-2026 from the PolicyLayer scan database over all 10 catalogued Gradus Notation tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Gradus Notation 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.