Home / Token cost / Threejs Devtools

The Threejs Devtools MCP server costs 7,546 tokens before the first call.

Connect Threejs Devtools and its 60 tool definitions are loaded into the model's context on every request — 3.8% of a 200k window spent before your agent does anything.

QUICK ANSWER The Threejs Devtools MCP server's tool definitions consume 7,546 tokens — 4.0× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 60 tools · 7,546 tokens · 3.8% of 200k · 0.8% 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 3.8%
1M WINDOW 0.8%

Corpus context: Threejs Devtools ranks #635 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 7,546 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 126 tokens per tool.

ToolCategoryTokens% of server
set_texture Write 372 4.9%
run_js Execute 369 4.9%
set_shadow Write 363 4.8%
add_helper Write 343 4.5%
set_camera Write 311 4.1%
set_renderer Write 254 3.4%
set_object_transform Write 242 3.2%
set_animation Write 225 3.0%
set_light Write 223 3.0%
set_material_property Write 222 2.9%
bounding_boxes Destructive 220 2.9%
find_objects Read 216 2.9%
set_fog Write 197 2.6%
set_layers Write 188 2.5%
set_instanced_mesh Write 181 2.4%
set_morph_target Write 175 2.3%
set_uniform Write 174 2.3%
scene_tree Write 165 2.2%
highlight_object Destructive 143 1.9%
gltf_to_r3f Read 138 1.8%
instanced_mesh_details Read 138 1.8%
raycast Read 128 1.7%
toggle_wireframe Destructive 125 1.7%
toggle_overlay Destructive 124 1.6%
scene_export Write 118 1.6%
console_capture Read 117 1.6%
scene_diff Read 114 1.5%
set_dev_url Write 114 1.5%
perf_monitor Read 111 1.5%
annotated_screenshot Read 108 1.4%
texture_preview Read 102 1.4%
object_details Read 100 1.3%
click_inspect Write 96 1.3%
geometry_details Read 86 1.1%
set_dev_port Write 84 1.1%
remove_helper Destructive 81 1.1%
material_details Read 76 1.0%
shader_source Read 76 1.0%
overlay_selected Write 75 1.0%
take_screenshot Read 74 1.0%
texture_details Read 69 0.9%
postprocessing_list Read 46 0.6%
shadow_details Read 46 0.6%
dispose_check Read 44 0.6%
fog_details Read 41 0.5%
env_map_details Read 40 0.5%
memory_stats Read 40 0.5%
scene_background Read 40 0.5%
performance_snapshot Execute 39 0.5%
camera_details Read 38 0.5%
renderer_settings Read 38 0.5%
animation_details Read 37 0.5%
morph_targets Read 36 0.5%
skeleton_details Read 36 0.5%
material_list Read 33 0.4%
renderer_info Read 33 0.4%
texture_list Read 33 0.4%
layer_details Read 32 0.4%
shader_list Read 30 0.4%
bridge_status Read 27 0.4%

Most agents use a handful of these tools. They pay for all 60.

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 (126 tokens each).

Grant scopeDefinition costReduction
All 60 tools (no gateway) 7,546 tokens
3 granted tools ~377 tokens −95%
5 granted tools ~629 tokens −92%
10 granted tools ~1,258 tokens −83%

Threejs Devtools token-cost questions.

How many tokens does the Threejs Devtools MCP server use?+

Its 60 tool definitions total 7,546 tokens — 3.8% 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 Threejs Devtools 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 Threejs Devtools's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Threejs Devtools 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 377 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 60 catalogued Threejs Devtools tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Threejs Devtools 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.