Home / Token cost / Uk Legal

The Uk Legal MCP server costs 7,398 tokens before the first call.

Connect Uk Legal and its 29 tool definitions are loaded into the model's context on every request — 3.7% of a 200k window spent before your agent does anything.

QUICK ANSWER The Uk Legal MCP server's tool definitions consume 7,398 tokens — 3.9× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 29 tools · 7,398 tokens · 3.7% of 200k · 0.7% 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 3.7%
1M WINDOW 0.7%

Corpus context: Uk Legal ranks #801 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 7,398 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.

ToolCategoryTokens% of server
parliament_member_interests Read 519 7.0%
case_law_search Read 511 6.9%
legislation_get_toc Read 460 6.2%
legislation_get_section Read 458 6.2%
bills_search_bills Read 408 5.5%
votes_search_divisions Read 376 5.1%
parliament_search_hansard Read 366 4.9%
committees_search_evidence Read 350 4.7%
case_law_grep_judgment Read 341 4.6%
citations_parse Execute 332 4.5%
legislation_search Read 327 4.4%
parliament_member_debates Read 257 3.5%
committees_search_committees Read 251 3.4%
parliament_search_petitions Read 229 3.1%
bills_get_bill Read 214 2.9%
parliament_vibe_check Read 208 2.8%
citations_network Read 206 2.8%
hmrc_get_vat_rate Read 194 2.6%
hmrc_check_mtd_status Read 191 2.6%
citations_resolve Write 167 2.3%
parliament_find_member Read 147 2.0%
votes_get_division Read 144 1.9%
hmrc_search_guidance Read 141 1.9%
judgment_get_paragraph Read 139 1.9%
judgment_get_header Read 114 1.5%
get_prompt Read 105 1.4%
committees_get_committee Read 103 1.4%
judgment_get_index Read 98 1.3%
list_prompts Read 42 0.6%

Most agents use a handful of these tools. They pay for all 29.

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 scopeDefinition costReduction
All 29 tools (no gateway) 7,398 tokens
3 granted tools ~765 tokens −90%
5 granted tools ~1,276 tokens −83%
10 granted tools ~2,551 tokens −66%

Uk Legal token-cost questions.

How many tokens does the Uk Legal MCP server use?+

Its 29 tool definitions total 7,398 tokens — 3.7% 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 Uk Legal 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 Uk Legal's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Uk Legal 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 765 tokens, a 90% 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 29 catalogued Uk Legal tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Uk Legal 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.