Home / Token cost / Bank Of Canada

The Bank Of Canada MCP server costs 7,795 tokens before the first call.

Connect Bank Of Canada and its 25 tool definitions are loaded into the model's context on every request — 3.9% of a 200k window spent before your agent does anything.

QUICK ANSWER The Bank Of Canada MCP server's tool definitions consume 7,795 tokens — 4.1× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 25 tools · 7,795 tokens · 3.9% 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 3.9%
1M WINDOW 0.8%

Corpus context: Bank Of Canada ranks #420 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 7,795 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 312 tokens per tool.

ToolCategoryTokens% of server
polymarket_edges Destructive 1,070 13.7%
bet_research Read 967 12.4%
polymarket_kalshi_spread Read 588 7.5%
polymarket_arbitrage Read 390 5.0%
ask_pipeworx Read 359 4.6%
recent_changes Read 359 4.6%
entity_profile Read 347 4.5%
pipeworx_feedback Read 327 4.2%
discover_tools Write 316 4.1%
compare_entities Read 315 4.0%
ai_visibility_check Read 305 3.9%
resolve_entity Write 289 3.7%
scan_dependency Read 278 3.6%
scan_competitor_ai_presence Read 269 3.5%
validate_claim Read 225 2.9%
get_observations Read 213 2.7%
pipeworx_trending Read 197 2.5%
generate_llms_txt Write 185 2.4%
remember Destructive 168 2.2%
get_group_observations Read 152 1.9%
recall Destructive 130 1.7%
list_series Read 101 1.3%
list_groups Read 91 1.2%
forget Destructive 83 1.1%
series_info Read 71 0.9%

Most agents use a handful of these tools. They pay for all 25.

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 (312 tokens each).

Grant scopeDefinition costReduction
All 25 tools (no gateway) 7,795 tokens
3 granted tools ~935 tokens −88%
5 granted tools ~1,559 tokens −80%
10 granted tools ~3,118 tokens −60%

Bank Of Canada token-cost questions.

How many tokens does the Bank Of Canada MCP server use?+

Its 25 tool definitions total 7,795 tokens — 3.9% 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 Bank Of Canada 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 Bank Of Canada's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Bank Of Canada 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 935 tokens, a 88% 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 25 catalogued Bank Of Canada tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Bank Of Canada 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.