// MCP TOKEN COST

The Voidly MCP server costs 7,619 tokens before the first call.

Connect Voidly and its 84 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 Voidly MCP server's tool definitions consume 7,619 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 84 tools · 7,619 tokens · 3.8% of 200k · 0.8% 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 3.8%

1M WINDOW 0.8%

Corpus context: Voidly ranks #559 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 7,619 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 91 tokens per tool.

Tool	Category	Tokens	% of server
agent_create_attestation	Write	203	2.7%
agent_broadcast_task	Read	177	2.3%
agent_memory_set	Write	175	2.3%
agent_query_attestations	Read	155	2.0%
agent_create_channel	Write	151	2.0%
agent_corroborate	Read	149	2.0%
voidly_pay_overview	Financial	147	1.9%
agent_send_message	Write	145	1.9%
agent_create_task	Write	140	1.8%
get_domain_history	Read	133	1.7%
agent_update_task	Write	133	1.7%
get_platform_risk	Read	132	1.7%
verify_claim	Read	129	1.7%
agent_invite_to_channel	Write	129	1.7%
check_vpn_accessibility	Read	127	1.7%
check_domain_blocked	Read	124	1.6%
agent_register_capability	Write	123	1.6%
get_incident_report	Read	120	1.6%
agent_post_to_channel	Write	118	1.5%
agent_list_channels	Read	116	1.5%
check_service_accessibility	Read	115	1.5%
agent_register	Write	115	1.5%
get_risk_forecast	Read	111	1.5%
agent_list_tasks	Read	110	1.4%
agent_register_webhook	Write	108	1.4%
agent_read_channel	Read	102	1.3%
check_domain_probes	Read	102	1.3%
get_high_risk_countries	Read	102	1.3%
get_incident_detail	Read	100	1.3%
get_isp_status	Read	99	1.3%
agent_receive_messages	Read	98	1.3%
agent_verify_message	Read	97	1.3%
agent_discover	Read	95	1.2%
agent_analytics	Read	90	1.2%
agent_search_capabilities	Read	90	1.2%
agent_memory_list	Read	89	1.2%
compare_countries	Read	89	1.2%
get_incident_evidence	Read	89	1.2%
agent_key_pin	Write	88	1.2%
get_isp_risk_index	Read	87	1.1%
agent_respond_invite	Write	87	1.1%
get_incidents_since	Read	86	1.1%
agent_update_profile	Write	85	1.1%
agent_mark_read_batch	Write	83	1.1%
get_domain_status	Read	82	1.1%
get_country_status	Read	81	1.1%
agent_key_verify	Read	79	1.0%
agent_memory_get	Read	78	1.0%
get_election_risk	Read	78	1.0%
agent_memory_delete	Destructive	77	1.0%
agent_trust_leaderboard	Read	77	1.0%
agent_export_data	Write	77	1.0%
agent_get_consensus	Read	76	1.0%
agent_mark_read	Write	75	1.0%
agent_delete_message	Destructive	72	0.9%
agent_list_invites	Read	70	0.9%
agent_get_trust	Read	68	0.9%
agent_unread_count	Read	68	0.9%
get_probe_network	Read	68	0.9%
agent_get_broadcast	Read	66	0.9%
agent_join_channel	Read	66	0.9%
agent_list_broadcasts	Read	66	0.9%
get_community_probes	Read	65	0.9%
agent_delete_capability	Destructive	64	0.8%
agent_get_identity	Read	63	0.8%
get_most_censored	Read	63	0.8%
agent_get_task	Read	62	0.8%
get_censorship_index	Read	61	0.8%
agent_deactivate	Read	60	0.8%
agent_key_pins	Read	59	0.8%
agent_ping_check	Read	58	0.8%
agent_ping	Write	54	0.7%
agent_get_attestation	Read	50	0.7%
agent_get_profile	Read	50	0.7%
agent_memory_namespaces	Read	50	0.7%
get_alert_stats	Read	48	0.6%
get_incident_stats	Read	47	0.6%
agent_list_webhooks	Read	45	0.6%
agent_list_capabilities	Read	44	0.6%
agent_relay_stats	Read	44	0.6%
get_active_incidents	Read	44	0.6%
get_community_leaderboard	Read	44	0.6%
relay_info	Read	42	0.6%
relay_peers	Read	35	0.5%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 84.

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 (91 tokens each).

Grant scope	Definition cost	Reduction
All 84 tools (no gateway)	7,619 tokens	—
3 granted tools	~272 tokens	−96%
5 granted tools	~454 tokens	−94%
10 granted tools	~907 tokens	−88%

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

//FAQ

Voidly token-cost questions.

How many tokens does the Voidly MCP server use?+

Its 84 tool definitions total 7,619 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 Voidly 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 Voidly's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Voidly 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 272 tokens, a 96% 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 84 catalogued Voidly tools. Counts refresh with every site build.

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

A PolicyLayer grant scopes Voidly 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.