// MCP TOKEN COST

The Brandcode MCP server costs 10,976 tokens before the first call.

Connect Brandcode and its 43 tool definitions are loaded into the model's context on every request — 5.5% of a 200k window spent before your agent does anything.

QUICK ANSWER The Brandcode MCP MCP server's tool definitions consume 10,976 tokens — 5.8× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 43 tools · 10,976 tokens · 5.5% of 200k · 1.1% of 1M Method →

// CONTEXT WINDOW SHARE

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 5.5%

1M WINDOW 1.1%

Corpus context: Brandcode ranks #156 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.

// PER-TOOL BREAKDOWN

Where the 10,976 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 255 tokens per tool.

Tool	Category	Tokens	% of server
brand_feedback	Read	726	6.6%
brand_extract_figma	Read	464	4.2%
brand_write	Write	381	3.5%
brand_ingest_assets	Read	380	3.5%
brand_brandcode_auth	Destructive	366	3.3%
brand_enrich_skill	Read	329	3.0%
brand_start	Execute	326	3.0%
brand_build_personas	Execute	318	2.9%
brand_export	Write	315	2.9%
brand_check	Read	310	2.8%
brand_runtime	Execute	303	2.8%
brand_brandcode_live	Read	299	2.7%
brand_audit_content	Read	280	2.6%
brand_connect_repo	Write	278	2.5%
brand_compile_messaging	Execute	270	2.5%
brand_audit_drift	Read	266	2.4%
brand_extract_pdf	Read	257	2.3%
brand_brandcode_connect	Write	253	2.3%
brand_feedback_review	Read	248	2.3%
brand_extract_messaging	Read	246	2.2%
brand_set_logo	Write	246	2.2%
brand_preflight	Destructive	245	2.2%
brand_build_themes	Execute	244	2.2%
brand_build_matrix	Execute	240	2.2%
brand_clarify	Read	237	2.2%
brand_generate_designmd	Write	237	2.2%
brand_deepen_identity	Read	233	2.1%
brand_extract_web	Read	233	2.1%
brand_brandcode_sync	Write	227	2.1%
brand_check_compliance	Read	223	2.0%
brand_build_journey	Execute	221	2.0%
brand_extract_visual	Read	208	1.9%
brand_extract_site	Read	201	1.8%
brand_init	Write	170	1.5%
brand_feedback_triage	Write	164	1.5%
brand_resolve_conflicts	Write	159	1.4%
brand_brandcode_status	Read	152	1.4%
brand_repo_status	Read	149	1.4%
brand_compile	Execute	131	1.2%
brand_preview	Execute	123	1.1%
brand_audit	Read	111	1.0%
brand_report	Write	104	0.9%
brand_status	Read	103	0.9%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 43.

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 (255 tokens each).

Grant scope	Definition cost	Reduction
All 43 tools (no gateway)	10,976 tokens	—
3 granted tools	~766 tokens	−93%
5 granted tools	~1,276 tokens	−88%
10 granted tools	~2,553 tokens	−77%

Model your own stack in the token-cost calculator, or see the Brandcode MCP policy for what a sensible grant looks like.

//FAQ

Brandcode MCP token-cost questions.

How many tokens does the Brandcode MCP server use?+

Its 43 tool definitions total 10,976 tokens — 5.5% 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 Brandcode 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 Brandcode MCP's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Brandcode 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 766 tokens, a 93% 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.

// METHOD & REVIEW

How these numbers were measured.

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.

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.

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 43 catalogued Brandcode MCP tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Brandcode MCP to the tools you actually allow. Ungranted definitions never load, and every call that does run is checked against policy first.

SCOPE YOUR GRANT →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.