Home / Token cost / Unreal Engine

The Unreal Engine MCP server costs 37,747 tokens before the first call.

Connect Unreal Engine and its 23 tool definitions are loaded into the model's context on every request — 19% of a 200k window spent before your agent does anything.

QUICK ANSWER The Unreal Engine MCP server's tool definitions consume 37,747 tokens — 35× the median MCP server (1,075 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 23 tools · 37,747 tokens · 19% of 200k · 3.8% 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 19%
1M WINDOW 3.8%

Corpus context: Unreal Engine ranks #9 of 1,659 measured MCP servers by definition cost. The median is 1,075 tokens, p90 is 6,119, and the heaviest (Fusionauth) is 183,337 — 92% of a 200k window on its own.

Where the 37,747 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 1,641 tokens per tool.

ToolCategoryTokens% of server
manage_blueprint Write 3,410 9.0%
manage_networking Write 3,366 8.9%
manage_ai Write 2,878 7.6%
build_environment Execute 2,703 7.2%
animation_physics Execute 2,468 6.5%
manage_level_structure Write 2,307 6.1%
manage_asset Write 2,171 5.8%
manage_combat Write 2,148 5.7%
manage_geometry Write 1,999 5.3%
manage_gas Write 1,712 4.5%
manage_effect Write 1,628 4.3%
manage_audio Write 1,476 3.9%
manage_character Write 1,407 3.7%
manage_inventory Write 1,266 3.4%
system_control Execute 1,108 2.9%
control_actor Execute 941 2.5%
manage_pcg Write 936 2.5%
control_editor Execute 823 2.2%
manage_level Write 818 2.2%
manage_interaction Write 779 2.1%
manage_sequence Write 590 1.6%
inspect Read 569 1.5%
manage_tools Write 244 0.6%

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 (1,641 tokens each).

Grant scopeDefinition costReduction
All 23 tools (no gateway) 37,747 tokens
3 granted tools ~4,924 tokens −87%
5 granted tools ~8,206 tokens −78%
10 granted tools ~16,412 tokens −57%

Unreal Engine token-cost questions.

How many tokens does the Unreal Engine MCP server use?+

Its 23 tool definitions total 37,747 tokens — 19% 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 Unreal Engine 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 Unreal Engine's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Unreal Engine 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 4,924 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 05-06-2026 from the PolicyLayer scan database over all 23 catalogued Unreal Engine tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Unreal Engine 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.