Home / Token cost / SceneView 3D & AR

The SceneView 3D & AR MCP server costs 17,096 tokens before the first call.

Connect SceneView 3D & AR and its 63 tool definitions are loaded into the model's context on every request — 8.5% of a 200k window spent before your agent does anything.

QUICK ANSWER The SceneView 3D & AR MCP server's tool definitions consume 17,096 tokens — 9.0× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 63 tools · 17,096 tokens · 8.5% of 200k · 1.7% 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 8.5%
1M WINDOW 1.7%

Corpus context: SceneView 3D & AR ranks #68 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 17,096 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 271 tokens per tool.

ToolCategoryTokens% of server
get_sample Read 1,312 7.7%
create_3d_artifact Write 1,181 6.9%
get_room_planner Read 525 3.1%
get_car_configurator Read 494 2.9%
get_anatomy_viewer Read 454 2.7%
get_molecule_viewer Read 420 2.5%
get_material_switcher Read 417 2.4%
get_dental_viewer Read 412 2.4%
get_lighting_design Read 405 2.4%
get_level_editor Read 397 2.3%
get_furniture_placement Read 391 2.3%
get_car_paint_shader Read 384 2.2%
get_parts_catalog Read 374 2.2%
get_hud_overlay Read 371 2.2%
get_physics_game Read 363 2.1%
get_character_viewer Read 360 2.1%
get_inventory_3d Read 353 2.1%
get_surgical_planning Read 345 2.0%
get_medical_imaging Read 344 2.0%
get_room_tour Read 335 2.0%
get_ar_showroom Read 334 2.0%
get_dashboard_3d Read 331 1.9%
get_ev_charging_station_viewer Read 323 1.9%
get_particle_effects Read 320 1.9%
debug_issue Write 315 1.8%
search_models Read 311 1.8%
generate_ar_logger Write 286 1.7%
render_3d_preview Read 277 1.6%
embed_web_viewer Read 262 1.5%
list_medical_models Read 247 1.4%
list_car_models Read 243 1.4%
list_furniture_models Read 242 1.4%
list_game_models Read 239 1.4%
setup_rerun_project Write 222 1.3%
generate_scene Write 216 1.3%
get_platform_setup Read 212 1.2%
analyze_project Read 188 1.1%
generate_python_sidecar Write 187 1.1%
migrate_code Write 154 0.9%
explain_concept Read 151 0.9%
get_node_reference Read 139 0.8%
validate_code Destructive 134 0.8%
get_ios_setup Read 131 0.8%
get_web_rendering_guide Read 131 0.8%
get_gesture_guide Read 125 0.7%
get_performance_tips Read 123 0.7%
get_material_guide Read 121 0.7%
validate_automotive_code Read 117 0.7%
validate_interior_code Read 115 0.7%
list_samples Read 112 0.7%
get_model_optimization_guide Read 111 0.6%
get_best_practices Read 108 0.6%
validate_medical_code Read 107 0.6%
validate_game_code Read 105 0.6%
get_animation_guide Read 104 0.6%
get_collision_guide Read 102 0.6%
get_web_setup Read 86 0.5%
get_ar_setup Read 80 0.5%
get_setup Read 77 0.5%
get_troubleshooting Read 77 0.5%
get_platform_roadmap Read 70 0.4%
get_migration_guide Read 66 0.4%
list_platforms Read 58 0.3%

Most agents use a handful of these tools. They pay for all 63.

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 (271 tokens each).

Grant scopeDefinition costReduction
All 63 tools (no gateway) 17,096 tokens
3 granted tools ~814 tokens −95%
5 granted tools ~1,357 tokens −92%
10 granted tools ~2,714 tokens −84%

SceneView 3D & AR token-cost questions.

How many tokens does the SceneView 3D & AR MCP server use?+

Its 63 tool definitions total 17,096 tokens — 8.5% 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 SceneView 3D & AR 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 SceneView 3D & AR's token usage?+

Expose fewer tools. A PolicyLayer grant scopes SceneView 3D & AR 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 814 tokens, a 95% 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 63 catalogued SceneView 3D & AR tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes SceneView 3D & AR 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.