New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice
Home / Token cost / Genesis

The Genesis MCP server costs 40,388 tokens before the first call.

Every request your agent makes carries every tool definition this server exposes — context your code, documents and conversation can't use, mostly for tools the agent never calls. You don't need them all in the window, and you don't have to pay for them.

QUICK ANSWER The Genesis MCP server's 252 tool definitions consume 40,388 tokens — 20% of a 200k context window, and 22× the median MCP server (1,866 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #120 of 12,801 measured servers · refreshed every build Method →

What that costs 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 20%
1M WINDOW 4.0%

Corpus context: Genesis ranks #120 of 12,801 measured MCP servers by definition cost. The median is 1,866 tokens, p90 is 13,646, and the heaviest (Ainumbers Mcp Apps) is 442,891 — 221% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Where the 40,388 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 160 tokens per tool.

ToolCategoryTokens% of server
dials_createMessagingCampaign Write 581 1.4%
runner_startJob Execute 553 1.4%
dials_deployWorkflow Execute 551 1.4%
dials_recoverOutboundCall Read 516 1.3%
dials_createOutboundCall Write 514 1.3%
dials_validateOutboundCall Read 511 1.3%
dials_createRoutingRule Write 474 1.2%
dials_searchNumbers Read 460 1.1%
dials_createOutboundMessage Write 459 1.1%
dials_createVoiceProfile Write 450 1.1%
dials_registerEmergencyAddress Write 447 1.1%
dials_createMessagingBrand Write 440 1.1%
blinds_ownerReserve Read 419 1.0%
iam_runnerSelfExecutionGrant Read 360 0.9%
runner_getJobEvents Read 356 0.9%
hives_invoke_deployment Execute 353 0.9%
hives_invoke_function Execute 350 0.9%
dials_createHumanProfile Write 339 0.8%
dials_createMessageTemplate Write 339 0.8%
relays_createRecord Write 333 0.8%
hives_marketplace_publish Write 323 0.8%
runner_getJobResult Read 318 0.8%
runner_cancelJob Destructive 313 0.8%
runner_getJob Read 311 0.8%
blinds_ownerP256Ensure Read 303 0.8%
beacons_enrollBridgeDevice Read 300 0.7%
blinds_ownerAttach Write 296 0.7%
blinds_ownerSign Read 295 0.7%
hives_create_function Write 290 0.7%
dials_createAgent Write 286 0.7%
minds_insertEpisodicMemory Write 281 0.7%
dials_assignCampaignNumber Write 277 0.7%
hives_create_deployment Write 272 0.7%
hives_update_function Write 269 0.7%
hives_query_deployment_logs Read 264 0.7%
hives_configure_native_queue_consumer Write 262 0.6%
dials_assignNumber Write 261 0.6%
hives_create_bucket Write 253 0.6%
hives_mount_volume Read 250 0.6%
hives_query_logs Read 245 0.6%
dials_updateNumberCallerName Write 243 0.6%
foundry_createChatCompletion Write 243 0.6%
dials_provisionNumber Read 234 0.6%
dials_disableRoutingRule Write 234 0.6%
hives_generate_presigned_url Write 228 0.6%
hives_get_project_activity Read 227 0.6%
dials_deleteNumber Destructive 224 0.6%
hives_marketplace_list_packages Read 223 0.6%
hives_set_cors_config Write 221 0.5%
hives_create_volume Write 220 0.5%
dials_releaseNumber Read 215 0.5%
hives_get_function_invocations_series Read 215 0.5%
hives_send_native_queue Write 213 0.5%
hives_get_deployment_metrics Read 209 0.5%
hives_get_function_metrics Read 207 0.5%
hives_get_cron_runs Read 202 0.5%
hives_bulk_upsert_secrets Write 201 0.5%
minds_createMind Write 201 0.5%
fleets_launchAgent Execute 197 0.5%
hives_get_resource_usage Read 195 0.5%
dials_reconcileNumberInventory Read 193 0.5%
hives_list_projects Read 192 0.5%
hives_get_latency_metrics Read 190 0.5%
hives_get_request_metrics Read 190 0.5%
hives_list_deployments Read 190 0.5%
hives_marketplace_install Write 190 0.5%
hives_create_secret Write 189 0.5%
hives_get_error_metrics Read 188 0.5%
hives_get_project_metrics Read 187 0.5%
hives_create_native_queue Write 187 0.5%
dials_listRoutingRules Read 186 0.5%
hives_configure_native_queue Write 186 0.5%
hives_marketplace_update Write 186 0.5%
dials_listMessagingCampaigns Read 185 0.5%
hives_update_cron Write 185 0.5%
dials_listMessagingBrands Read 183 0.5%
dials_listMessages Read 182 0.5%
dials_listMessageTemplates Read 182 0.5%
dials_listWorkflows Read 182 0.5%
hives_upload_deployment Write 179 0.4%
fleets_submitTask Write 177 0.4%
relays_updateRecord Write 175 0.4%
beacons_issueBridgeDeviceChallenge Write 172 0.4%
flocks_activateNode Write 171 0.4%
hives_create_project Write 171 0.4%
flocks_rotateNodeCredential Destructive 169 0.4%
hives_create_cron Write 168 0.4%
hives_list_objects Read 167 0.4%
hives_update_project Write 166 0.4%
hives_rollback_deployment Read 165 0.4%
hives_update_project_settings Write 163 0.4%
iam_createOrgApiKey Write 162 0.4%
fleets_stopInstance Execute 160 0.4%
fleets_startInstance Execute 157 0.4%
hives_set_context_project Write 157 0.4%
hives_update_secret Write 156 0.4%
fleets_setConnection Write 154 0.4%
dials_getOperatingSurface Read 152 0.4%
dials_listNumberReconciliations Read 152 0.4%
hives_marketplace_list_versions Read 152 0.4%
hives_list_functions Read 151 0.4%
dials_listVoiceProfiles Read 150 0.4%
dials_getConsoleSummary Read 149 0.4%
dials_listHumanProfiles Read 149 0.4%
dials_listNumberDrift Read 147 0.4%
hives_nack_native_queue Read 147 0.4%
hives_publish_native_topic Write 147 0.4%
dials_listAgents Read 146 0.4%
dials_listCalls Read 146 0.4%
dials_listNumbers Read 145 0.4%
hives_list_secrets Read 145 0.4%
hives_ack_native_queue Read 144 0.4%
hives_receive_native_queue Read 144 0.4%
hives_list_project_environment Read 143 0.4%
hives_upload_object Write 142 0.4%
minds_searchMemory Read 137 0.3%
hives_upload_object_by_key Write 136 0.3%
hives_list_volumes Read 135 0.3%
beacons_acknowledgeBridgeDeviceRevocation Read 134 0.3%
silos_createProject Write 133 0.3%
flocks_enrollNode Read 132 0.3%
flocks_exchangeJoinToken Read 130 0.3%
hives_unmount_volume Read 129 0.3%
genesis_search_tools Read 128 0.3%
hives_replay_native_queue Read 128 0.3%
henry_createRun Write 128 0.3%
hives_marketplace_installed Read 127 0.3%
fleets_commandAgent Write 127 0.3%
hives_delete_volume Destructive 125 0.3%
hives_get_volume Read 125 0.3%
hives_subscribe_native_topic Read 125 0.3%
beacons_provisionBridgeFleet Write 125 0.3%
henry_commandRun Execute 123 0.3%
hives_list_buckets Read 123 0.3%
minds_getEpisodicMemory Read 123 0.3%
hives_marketplace_get_package Read 122 0.3%
henry_decideApproval Read 121 0.3%
hives_list_crons Read 121 0.3%
hives_list_domains Read 119 0.3%
hives_select_runtime Write 119 0.3%
hives_delete_dlq_native_queue Destructive 118 0.3%
hives_unsubscribe_native_topic Destructive 118 0.3%
hives_reveal_project_environment Read 117 0.3%
beacons_updateBridgeDevice Write 117 0.3%
hives_marketplace_reconcile Execute 113 0.3%
relays_createZone Write 113 0.3%
hives_delete_object Destructive 109 0.3%
hives_get_dashboard_metrics Read 109 0.3%
flocks_heartbeatNode Read 108 0.3%
relays_listRecords Read 108 0.3%
hives_update_project_environment Write 107 0.3%
hives_marketplace_get_installation Read 106 0.3%
hives_marketplace_uninstall Destructive 105 0.3%
hives_download_object_by_key Read 105 0.3%
hives_add_domain Write 105 0.3%
hives_delete_object_by_key Destructive 104 0.3%
hives_reconcile Write 104 0.3%
hives_reveal_secret Read 102 0.3%
hives_purge_dlq_native_queue Destructive 101 0.3%
hives_dlq_stats_native_queue Read 101 0.3%
henry_putCredential Write 100 0.2%
hives_create_native_topic Write 99 0.2%
hives_purge_native_queue Destructive 97 0.2%
hives_consumers_native_queue Read 97 0.2%
hives_dead_letters_native_queue Read 97 0.2%
hives_get_cors_config Read 96 0.2%
hives_subscriptions_native_topic Read 96 0.2%
hives_promote_deployment Write 95 0.2%
hives_get_secret Read 94 0.2%
hives_inspect_native_queue Read 94 0.2%
hives_inspect_native_topic Read 94 0.2%
hives_pause_native_queue Read 94 0.2%
hives_stats_native_queue Read 94 0.2%
minds_listMinds Read 94 0.2%
flocks_renameNode Write 94 0.2%
hives_resume_native_queue Write 94 0.2%
hives_trigger_cron Execute 93 0.2%
flocks_createJoinToken Write 93 0.2%
hives_delete_native_queue Destructive 92 0.2%
hives_delete_native_topic Destructive 92 0.2%
hives_pause_cron Read 91 0.2%
hives_resume_cron Write 91 0.2%
hives_get_cron Read 90 0.2%
foundry_createNativeCreditCheckout Write 90 0.2%
hives_delete_bucket Destructive 89 0.2%
hives_delete_cron Destructive 89 0.2%
foundry_ensureBillingProfile Read 89 0.2%
genesis_call Read 89 0.2%
hives_get_bucket Read 89 0.2%
hives_get_deployment Read 89 0.2%
hives_delete_secret Destructive 87 0.2%
hives_get_function Read 87 0.2%
foundry_createEmbedding Write 87 0.2%
hives_cancel_deployment Destructive 86 0.2%
minds_getMind Read 86 0.2%
hives_remove_native_queue_consumer Destructive 85 0.2%
fleets_listInstances Read 85 0.2%
hives_get_native_queue_consumer Read 85 0.2%
hives_stop_deployment Execute 84 0.2%
relays_listZones Read 83 0.2%
hives_marketplace_featured Read 82 0.2%
iam_listOrgApiKeys Read 82 0.2%
hives_delete_function Destructive 81 0.2%
relays_deleteRecord Destructive 81 0.2%
hives_marketplace_categories Read 80 0.2%
hives_delete_deployment Destructive 79 0.2%
relays_getDnssec Read 79 0.2%
beacons_listBridgeDeviceRevocations Read 77 0.2%
hives_get_realtime_metrics Read 74 0.2%
fleets_listTasks Read 73 0.2%
hives_list_project_runtimes Read 73 0.2%
fleets_recoverAgent Read 72 0.2%
hives_list_native_queue Read 72 0.2%
hives_list_native_topic Read 72 0.2%
silos_getProject Read 72 0.2%
fleets_stopAgent Execute 71 0.2%
henry_getRun Read 71 0.2%
hives_get_project_settings Read 71 0.2%
fleets_getTaskReceipt Read 70 0.2%
beacons_revokeBridgeDevice Destructive 69 0.2%
fleets_cancelTask Destructive 69 0.2%
fleets_getAgent Read 69 0.2%
fleets_getInstance Read 69 0.2%
flocks_revokeNode Destructive 68 0.2%
fleets_getTask Read 67 0.2%
foundry_getRegistryModel Read 67 0.2%
hives_get_project Read 67 0.2%
hives_get_runtime Read 67 0.2%
iam_revokeApiKey Destructive 66 0.2%
relays_enroll Read 66 0.2%
relays_getZone Read 65 0.2%
henry_listRuns Read 62 0.2%
flocks_getEnrollmentReadiness Read 61 0.2%
relays_getEnrollment Read 59 0.1%
flocks_listNodes Read 58 0.1%
henry_getConfig Read 58 0.1%
runner_listJobs Read 57 0.1%
foundry_readNativeCreditBalance Read 55 0.1%
hives_list_runtimes Read 55 0.1%
fleets_deleteConnection Destructive 54 0.1%
hives_detach_context_project Destructive 54 0.1%
fleets_getConnection Read 54 0.1%
hives_list_regions Read 54 0.1%
runner_getCatalog Read 54 0.1%
silos_listProjects Read 54 0.1%
beacons_listBridgeDevices Read 53 0.1%
fleets_listAgents Read 52 0.1%
foundry_readBillingProfile Read 52 0.1%
hives_get_context_project Read 52 0.1%
foundry_listApiKeys Read 46 0.1%
foundry_listRegistryModels Read 46 0.1%
foundry_listModels Read 43 0.1%

Your agent uses a handful of these tools. It pays for all 252.

You don't need all 252 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Genesis: only the tools you grant are exposed to the agent, the rest never load. A smaller window means a sharper agent — less noise when it picks a tool — and every request costs less:

Grant scopeDefinition costReduction
All 252 tools (no gateway) 40,388 tokens —
3 granted tools ~481 tokens −99%
5 granted tools ~801 tokens −98%
10 granted tools ~1,603 tokens −96%

The risk dividend: 27 of these 252 tools are critical-risk (destructive or financial) and cost 2,824 tokens (7% of the definition load). Block them — the recommended starter policy — and you reclaim that context before tuning anything else.

  1. Create a free account and register Genesis — nothing to install.
  2. Grant only the tools you use — ungranted definitions never enter the context window.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CUT GENESIS TOKEN COST →

Instant setup, no code required.

Genesis token-cost questions.

How many tokens does the Genesis MCP server use?+

Its 252 tool definitions total 40,388 tokens — 20% 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 Genesis 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 Genesis's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Genesis 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 481 tokens, a 99% 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 21-10-2026 from the PolicyLayer scan database over all 252 catalogued Genesis tools. Counts refresh with every site build.

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

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

Instant setup, no code required.

46,500+ MCP servers and 515,000+ 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.