Home / Token cost / ScanBIM MCP

The ScanBIM MCP server costs 9,381 tokens before the first call.

Connect ScanBIM and its 19 tool definitions are loaded into the model's context on every request — 4.7% of a 200k window spent before your agent does anything.

QUICK ANSWER The ScanBIM MCP MCP server's tool definitions consume 9,381 tokens — 4.9× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 19 tools · 9,381 tokens · 4.7% of 200k · 0.9% 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 4.7%
1M WINDOW 0.9%

Corpus context: ScanBIM ranks #190 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 9,381 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 494 tokens per tool.

ToolCategoryTokens% of server
acc_create_issue Write 752 8.0%
acc_create_rfi Write 719 7.7%
twinmotion_render Write 682 7.3%
upload_model Write 664 7.1%
detect_clashes Read 574 6.1%
lumion_render Write 570 6.1%
xr_launch_vr_session Execute 555 5.9%
xr_launch_ar_session Execute 539 5.7%
twinmotion_walkthrough Write 486 5.2%
acc_search_documents Read 461 4.9%
acc_list_issues Read 459 4.9%
acc_project_summary Write 412 4.4%
get_viewer_link Read 410 4.4%
xr_list_sessions Read 409 4.4%
get_model_metadata Read 396 4.2%
acc_list_rfis Read 374 4.0%
list_models Read 368 3.9%
acc_list_projects Read 290 3.1%
get_supported_formats Read 261 2.8%

Most agents use a handful of these tools. They pay for all 19.

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 (494 tokens each).

Grant scopeDefinition costReduction
All 19 tools (no gateway) 9,381 tokens
3 granted tools ~1,481 tokens −84%
5 granted tools ~2,469 tokens −74%
10 granted tools ~4,937 tokens −47%

ScanBIM MCP token-cost questions.

How many tokens does the ScanBIM MCP server use?+

Its 19 tool definitions total 9,381 tokens — 4.7% 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 ScanBIM MCP 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 ScanBIM MCP's token usage?+

Expose fewer tools. A PolicyLayer grant scopes ScanBIM MCP 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 1,481 tokens, a 84% 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 19 catalogued ScanBIM MCP tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes ScanBIM MCP 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.