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

The Tengu MCP server costs 47,106 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 Tengu MCP server's 337 tool definitions consume 47,106 tokens — 24% of a 200k context window, and 25× the median MCP server (1,920 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS tiktoken o200k_base · rank #46 of 8,127 measured servers · refreshed every build Method →
// CONTEXT WINDOW SHARE

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 24%
1M WINDOW 4.7%

Corpus context: Tengu ranks #46 of 8,127 measured MCP servers by definition cost. The median is 1,920 tokens, p90 is 12,644, and the heaviest (Ainumbers Mcp Apps) is 325,784 — 163% of a 200k window on its own. New to this? See MCP token cost and context window in the glossary.

Token cost is one axis. See the risk picture across your whole stack →

// PER-TOOL BREAKDOWN

Where the 47,106 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 140 tokens per tool.

ToolCategoryTokens% of server
tengu_v3_intel_commodities Read 503 1.1%
tengu_v3_reference_crosswalk Read 463 1.0%
tengu_v3_intel_macro_snapshot Read 406 0.9%
tengu_v3_tape_options_chain Read 406 0.9%
tengu_v3_skills_apex_equity Read 403 0.9%
tengu_v3_features_dataset Destructive 397 0.8%
tengu_v3_reference_lookup Read 378 0.8%
tengu_v3_reference_history Write 376 0.8%
tengu_v3_intel_ml_prediction Execute 374 0.8%
tengu_v3_private_markets_companies Read 359 0.8%
tengu_v3_supply_chain_relationships Execute 339 0.7%
tengu_v3_features_catalogue Read 334 0.7%
tengu_v3_supply_chain_geo_revenue Write 296 0.6%
tengu_v3_news_ticker_news Read 289 0.6%
tengu_v3_fundamentals_prices Read 280 0.6%
tengu_v3_fundamentals_screener Read 276 0.6%
tengu_v3_workforce_layoffs Execute 274 0.6%
tengu_v3_workforce_momentum Read 274 0.6%
tengu_v3_intel_insider_flow Destructive 272 0.6%
tengu_v3_reference_coverage Execute 267 0.6%
tengu_v3_intel_news_pro Read 267 0.6%
tengu_v3_intel_voter_attribution Read 264 0.6%
tengu_v3_reference_batch Read 261 0.6%
tengu_v3_supply_chain_revenue_dependence Read 260 0.6%
tengu_v3_factor_predictors Execute 259 0.5%
tengu_v3_fundamentals_pit Read 258 0.5%
tengu_v3_copilot_thesis_alerts Read 256 0.5%
tengu_v3_intel_vol_surface Read 255 0.5%
tengu_copilot_score_ticker Read 253 0.5%
tengu_v3_intel_options_flow_history Execute 251 0.5%
tengu_copilot_ticker_full Read 241 0.5%
tengu_v3_earnings_next Read 238 0.5%
tengu_v3_trade_setups Read 238 0.5%
tengu_v3_fundamentals_segments Read 235 0.5%
tengu_v3_intel_top_shareholders_current Read 234 0.5%
tengu_v3_workforce_momentum_screen Read 232 0.5%
tengu_v3_intel_cftc_cot Read 231 0.5%
tengu_v3_private_markets_search Read 231 0.5%
tengu_v3_intel_borrow_cost_history Destructive 229 0.5%
tengu_v3_intel_gex_history Execute 227 0.5%
tengu_v3_tape_bars Execute 227 0.5%
tengu_v3_fundamentals_xbrl Read 222 0.5%
tengu_v3_workforce_layoff_screen Read 221 0.5%
tengu_v3_intel_darkpool_history Execute 220 0.5%
tengu_v3_private_markets_company_relations Read 216 0.5%
tengu_v3_tape_index_bars Read 213 0.5%
tengu_v3_news_forex_by_category Read 212 0.5%
tengu_v3_transcript_text Read 209 0.4%
tengu_v3_fundamentals_pit_vintages Read 208 0.4%
tengu_copilot_universe Write 207 0.4%
tengu_v3_intel_iv_analytics Read 204 0.4%
tengu_v3_intel_model_calibration Read 201 0.4%
tengu_v3_intel_insider_form144 Read 200 0.4%
tengu_v3_credit_indices Read 197 0.4%
tengu_v3_briefing_daily Execute 196 0.4%
tengu_copilot_signal_health Read 196 0.4%
tengu_v3_private_markets_investor_relations Read 196 0.4%
tengu_v3_intel_pnl_attribution Read 195 0.4%
tengu_v3_tape_options Read 194 0.4%
tengu_v3_intel_borrow_cost Read 192 0.4%
tengu_v3_earnings_next_stream Read 190 0.4%
tengu_v2_research_read Read 187 0.4%
tengu_v3_fundamentals_historical Read 185 0.4%
tengu_v3_accounting_flags Read 184 0.4%
tengu_copilot_ticker_transparency Read 181 0.4%
tengu_v3_credit_bonds Read 178 0.4%
tengu_v3_origin_short_activity Read 177 0.4%
tengu_v3_news_sentiment_history Execute 176 0.4%
tengu_copilot_voter_ic_drift Read 176 0.4%
tengu_v3_fundamentals_price_snapshot Read 176 0.4%
tengu_v3_private_markets_company_realtime Write 176 0.4%
tengu_crypto_universe Write 173 0.4%
tengu_copilot_ticker_smartmoney Read 170 0.4%
tengu_v3_funds_mutual_fund_ownership Read 170 0.4%
tengu_v3_intel_chart Read 170 0.4%
tengu_v3_intel_voter_coverage Read 170 0.4%
tengu_v3_private_markets_service_provider_relations Execute 169 0.4%
tengu_v3_tape_futures_curve Read 169 0.4%
tengu_v3_skills_trading_plan Write 169 0.4%
tengu_copilot_decision_review Read 168 0.4%
tengu_v3_intel_street_estimates_history Read 168 0.4%
tengu_v3_private_markets_deal_relations Read 168 0.4%
tengu_v3_origin_insider_flow Write 168 0.4%
tengu_v3_intel_calendar_ratings Read 166 0.4%
tengu_v3_private_markets_company_dossier Read 166 0.4%
tengu_v3_credit_cds_history Read 165 0.4%
tengu_v3_news_category Read 165 0.4%
tengu_v3_prices_history Read 165 0.4%
tengu_v3_intel_options_chain Read 164 0.3%
tengu_v3_tape_futures Read 164 0.3%
tengu_v3_events Read 163 0.3%
tengu_v3_private_markets_fund_relations Read 162 0.3%
tengu_v2_research_datasets Read 161 0.3%
tengu_v3_credit Read 160 0.3%
tengu_v3_factor_characteristic_history Read 159 0.3%
tengu_v3_news_ratings Read 159 0.3%
tengu_v3_intel_etf_summary Read 158 0.3%
tengu_v3_news_forex_latest Read 157 0.3%
tengu_v3_private_markets_company_comparables Write 157 0.3%
tengu_v3_intel_analyst_consensus Read 156 0.3%
tengu_v3_intel_short_interest_history Read 156 0.3%
tengu_v3_news_crypto_latest Read 156 0.3%
tengu_v3_skills_ta_master Read 156 0.3%
tengu_v3_transcripts_list Read 156 0.3%
tengu_v3_private_markets_person_relations Read 155 0.3%
tengu_v3_risk_portfolio_var Read 155 0.3%
tengu_v3_intel_risk_free_rate Destructive 154 0.3%
tengu_v3_credit_loans Read 154 0.3%
tengu_v3_credit_ratings Read 154 0.3%
tengu_v3_intel_calendar_economics Read 154 0.3%
tengu_v3_news_by_topic Read 154 0.3%
tengu_v3_sec_filing_extract Read 154 0.3%
tengu_v3_intel_options_flow Read 153 0.3%
tengu_v3_intel_yield_curve Read 153 0.3%
tengu_v3_news_crypto_whale_transactions Read 153 0.3%
tengu_v3_research_web_search Read 152 0.3%
tengu_copilot_live_ic_drift Read 151 0.3%
tengu_v3_intel_calendar_conference_calls Read 151 0.3%
tengu_v3_intel_off_exchange Read 151 0.3%
tengu_v3_news_forex_economic_calendar Read 151 0.3%
tengu_v3_tape_microstructure Write 151 0.3%
tengu_crypto Read 150 0.3%
tengu_v3_fundamentals_companyfacts Read 150 0.3%
tengu_v3_intel_ml_drivers Execute 148 0.3%
tengu_v3_private_markets_company_investors Read 148 0.3%
tengu_v3_twap_plan Write 148 0.3%
tengu_v3_intel_sec13f_history Read 146 0.3%
tengu_v3_transcripts_search Read 146 0.3%
tengu_v3_cost_estimate Read 145 0.3%
tengu_v3_intel_options_flow_ticker Read 145 0.3%
tengu_v3_governance Read 144 0.3%
tengu_v3_intel_darkpool_ticker Read 144 0.3%
tengu_v3_research_fetch_url Read 144 0.3%
tengu_v3_origin_macro_pulse Read 142 0.3%
tengu_v3_private_markets_limited_partner_relations Read 141 0.3%
tengu_v3_fundamentals_metrics Read 140 0.3%
tengu_v3_origin_ipo_pipeline Read 140 0.3%
tengu_v3_intel_sec13f_changes Destructive 139 0.3%
tengu_v3_factor_exposures Read 139 0.3%
tengu_v3_intel_street_estimates_guidance Read 137 0.3%
tengu_v3_fundamentals_cash_flow_statements Read 136 0.3%
tengu_v3_fundamentals_income_statements Read 136 0.3%
tengu_v3_origin_whale_holdings Read 136 0.3%
tengu_v3_intel_congress Read 134 0.3%
tengu_v3_intel_earnings_history Read 134 0.3%
tengu_v3_research_correlation_mesh Read 134 0.3%
tengu_v3_factor_characteristics Write 134 0.3%
tengu_v3_fundamentals_balance_sheets Read 133 0.3%
tengu_v3_news_alerts Read 133 0.3%
tengu_v3_intel_sec13f Read 131 0.3%
tengu_v3_stream_bars Read 131 0.3%
tengu_v2_intervals Read 130 0.3%
tengu_v3_intel_short_interest Read 130 0.3%
tengu_v3_news_forex_sentiment_stats Read 130 0.3%
tengu_v3_fundamentals_tickers Read 129 0.3%
tengu_v3_intel_gex Read 129 0.3%
tengu_v3_intel_news_why_moving Read 129 0.3%
tengu_v3_news_crypto_by_category Read 129 0.3%
tengu_v3_prices_corporate_actions Execute 128 0.3%
tengu_copilot_top_picks Read 128 0.3%
tengu_v3_news_multi_ticker Read 128 0.3%
tengu_v3_fundamentals_all Read 127 0.3%
tengu_v3_intel_lobbying Read 127 0.3%
tengu_v3_fundamentals_news Read 126 0.3%
tengu_v3_news_crypto_sentiment_stats Read 126 0.3%
tengu_v3_news_curated_events Read 126 0.3%
tengu_v3_news_forex_events Read 126 0.3%
tengu_v3_private_markets_company_deals Read 126 0.3%
tengu_v3_vwap_plan Write 126 0.3%
tengu_v3_intel_darkpool_recent Read 125 0.3%
tengu_v3_intel_gov_contracts Read 125 0.3%
tengu_v3_intel_street_estimates Read 125 0.3%
tengu_v3_intel_wsb Read 125 0.3%
tengu_v3_research_x_sentiment Read 125 0.3%
tengu_v3_intel_news_headlines Read 124 0.3%
tengu_v3_intel_twitter Read 124 0.3%
tengu_v3_private_markets_company Read 123 0.3%
tengu_v3_intel_exec_compensation Read 122 0.3%
tengu_v3_fundamentals_pit_coverage Read 121 0.3%
tengu_v3_fundamentals_sec_filings Read 121 0.3%
tengu_v3_intel_insider_flow_coverage Read 121 0.3%
tengu_v3_intel_options_volume Read 121 0.3%
tengu_v3_news_crypto_multi_ticker Read 121 0.3%
tengu_v3_private_markets_search_suggest Read 121 0.3%
tengu_v3_intel_gov_contracts_live Read 120 0.3%
tengu_v3_intel_news_movers Read 120 0.3%
tengu_v3_news_crypto_ticker_only Read 120 0.3%
tengu_v3_private_markets_investor Read 120 0.3%
tengu_v3_news_event_by_id Write 120 0.3%
tengu_v2_alpha_discoveries Read 119 0.3%
tengu_v3_intel_corporate_donors Read 119 0.3%
tengu_v3_intel_insider_trades Read 119 0.3%
tengu_v3_intel_news_crypto Read 119 0.3%
tengu_v3_news_sentiment_stats Read 118 0.3%
tengu_v3_private_markets_aggregates Read 118 0.3%
tengu_v3_intel_insiders Read 117 0.2%
tengu_v3_intel_patents Read 117 0.2%
tengu_v3_news_summary Read 117 0.2%
tengu_v3_research_synthesis Read 117 0.2%
tengu_v2_var Read 116 0.2%
tengu_v3_fundamentals_peers Read 116 0.2%
tengu_v3_intel_etf_holdings Read 116 0.2%
tengu_v3_intel_top_shareholders_coverage Read 116 0.2%
tengu_v3_news_latest Read 116 0.2%
tengu_v3_news_ticker_only Read 116 0.2%
tengu_v3_intel_factor_importance Read 114 0.2%
tengu_v3_private_markets_service_provider Read 114 0.2%
tengu_v3_fundamentals_growth Read 113 0.2%
tengu_v3_private_markets_deal Read 110 0.2%
tengu_v3_signals_mtf Read 110 0.2%
tengu_v3_intel_news_press_releases Write 110 0.2%
tengu_v3_fundamentals_full Read 109 0.2%
tengu_v3_news_aggregated Read 109 0.2%
tengu_v3_private_markets_limited_partner Read 109 0.2%
tengu_v3_private_markets_person Read 107 0.2%
tengu_v3_news_all_tickers_sentiment Read 106 0.2%
tengu_v3_news_forex_summary Read 105 0.2%
tengu_v3_fundamentals_insider_trades Read 104 0.2%
tengu_v3_intel_max_pain Read 104 0.2%
tengu_v3_news_crypto_events Read 104 0.2%
tengu_v3_stream_quotes Read 104 0.2%
tengu_v3_intel_top_shareholders Read 102 0.2%
tengu_v3_intel_voter_ic_drift Read 102 0.2%
tengu_v3_macro_treasury_curve Read 102 0.2%
tengu_v3_news_crypto_all_tickers_sentiment Read 102 0.2%
tengu_v2_strategy_evolution Read 101 0.2%
tengu_v3_kelly_uncertainty Read 101 0.2%
tengu_v3_news_crypto_summary Read 101 0.2%
tengu_copilot_track_record Read 100 0.2%
tengu_v3_accuracy Read 100 0.2%
tengu_v3_fundamentals_earnings_press_releases Write 99 0.2%
tengu_v3_fundamentals_company_facts Read 98 0.2%
tengu_v3_fundamentals_search Read 98 0.2%
tengu_v3_intel_politicians Read 98 0.2%
tengu_v3_prediction_tracker Read 98 0.2%
tengu_v3_fundamentals_institutional_ownership Read 97 0.2%
tengu_v3_news_forex_prices Read 97 0.2%
tengu_v3_universe_scan Read 97 0.2%
tengu_v3_news_events Read 96 0.2%
tengu_v2_short_interest Read 95 0.2%
tengu_v3_fundamentals_ai_analyze Read 95 0.2%
tengu_ml_top_picks Read 94 0.2%
tengu_v3_news_crypto_whale_summary Read 94 0.2%
tengu_v3_signals_fusion Read 94 0.2%
tengu_v3_smart_route Read 94 0.2%
tengu_v2_feature_importance Read 93 0.2%
tengu_v2_regime_forecast Read 93 0.2%
tengu_v3_news_structured Read 93 0.2%
tengu_ml_predict Read 92 0.2%
tengu_v3_news_crypto_ticker_price Read 92 0.2%
tengu_v3_news_forex_market_sentiment Read 92 0.2%
tengu_v3_fundamentals_metrics_snapshot Read 90 0.2%
tengu_snapshot Read 89 0.2%
tengu_v3_news_market_sentiment Read 88 0.2%
tengu_v3_news_top_mentions Read 88 0.2%
tengu_v3_news_crypto_market_sentiment Read 87 0.2%
tengu_v3_validation_trials Execute 86 0.2%
tengu_v3_fundamentals_dividends Read 86 0.2%
tengu_v2_regime_history Read 85 0.2%
tengu_v3_news_crypto_sundown Read 85 0.2%
tengu_v3_news_forex_top_mentions Read 85 0.2%
tengu_v3_private_markets_fund Read 85 0.2%
tengu_ml_weights_history Read 84 0.2%
tengu_v3_news_forex_trending Read 83 0.2%
tengu_v3_news_sundown Read 83 0.2%
tengu_regime Read 82 0.2%
tengu_v2_drift Read 82 0.2%
tengu_v3_news_forex_sundown_digest Read 81 0.2%
tengu_v3_signals_veto Read 80 0.2%
tengu_v3_agent_latest Read 79 0.2%
tengu_v3_news_crypto_top_mentions Read 79 0.2%
tengu_v3_fundamentals_screener_presets Read 78 0.2%
tengu_v3_ultimate_decision Read 78 0.2%
tengu_v3_news_crypto_trending Read 77 0.2%
tengu_v3_private_markets_relations Read 77 0.2%
tengu_v3_slippage Read 77 0.2%
tengu_v3_hedging Read 76 0.2%
tengu_copilot_macro_regime Read 75 0.2%
tengu_v3_framework_list Read 75 0.2%
tengu_v3_news_trending Read 75 0.2%
tengu_v2_crash_scenarios Read 74 0.2%
tengu_v3_strategy_signals Read 74 0.2%
tengu_macro Read 73 0.2%
tengu_v3_fundamentals_company_full Read 73 0.2%
tengu_v3_briefing_status Read 72 0.2%
tengu_v3_validation_trial_count Read 72 0.2%
tengu_v3_events_types Read 71 0.2%
tengu_v3_market_events_catchup Read 71 0.2%
tengu_v3_stream_realtime_guide Read 71 0.2%
tengu_v3_system_health Read 71 0.2%
tengu_v2_factor_decay Read 70 0.1%
tengu_v3_signals_cross_asset Read 70 0.1%
tengu_v3_strategies_list Read 70 0.1%
tengu_v3_api_quotas Read 68 0.1%
tengu_v3_stream_status Read 68 0.1%
tengu_v3_agents_list Read 67 0.1%
tengu_ml_weights Read 66 0.1%
tengu_v2_stress Read 66 0.1%
tengu_insider_clusters Read 65 0.1%
tengu_v3_stream_news_publisher_status Read 65 0.1%
tengu_v3_stream_tick_writer_status Read 64 0.1%
tengu_v2_signal_correlation Read 63 0.1%
tengu_v3_stream_market_events Read 63 0.1%
tengu_v3_stream_ticks Read 63 0.1%
tengu_ml_health Read 62 0.1%
tengu_v3_stream_decision_generator_status Read 61 0.1%
tengu_v3_thresholds Read 61 0.1%
tengu_v3_optimizer_latest Execute 60 0.1%
tengu_v3_stream_ingest_status Read 60 0.1%
tengu_v3_self_healing Read 59 0.1%
tengu_v3_stream_signal_generator_status Read 59 0.1%
tengu_v3_market_universe Write 59 0.1%
tengu_v3_backtest_run_detail Execute 57 0.1%
tengu_v3_believability Read 57 0.1%
tengu_v3_stream_universe_status Read 57 0.1%
tengu_v3_agent_status Read 55 0.1%
tengu_v3_memory_recall Read 55 0.1%
tengu_v3_strategy_metrics Read 54 0.1%
tengu_ready Read 53 0.1%
tengu_logs Read 52 0.1%
tengu_v3_metrics Read 52 0.1%
tengu_cache_stats Read 51 0.1%
tengu_v3_lab_strategies Read 48 0.1%
tengu_status Read 47 0.1%
tengu_v3_backtest_runs Read 47 0.1%
tengu_v3_memory_reflections Read 47 0.1%
tengu_v3_alerts_active Read 44 0.1%
tengu_v3_stream_events Read 42 0.1%
tengu_v3_stream_decisions Read 38 0.1%
tengu_v3_lab_deployments Read 36 0.1%
tengu_v3_portfolio_risk_parity_latest Read 36 0.1%
tengu_v3_position_monitor Read 36 0.1%
tengu_v3_stream_news Read 36 0.1%
tengu_v3_stream_signals Read 36 0.1%
tengu_v3_stream_alerts Read 35 0.1%
tengu_v3_resolver_status Read 30 0.1%
tengu_research_knowledge Read 28 0.1%
// CUT THE COST

Your agent uses a handful of these tools. It pays for all 337.

You don't need all 337 of those definitions in the window. PolicyLayer is an MCP gateway that sits in front of Tengu: 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 337 tools (no gateway) 47,106 tokens —
3 granted tools ~419 tokens −99%
5 granted tools ~699 tokens −99%
10 granted tools ~1,398 tokens −97%

The risk dividend: 5 of these 337 tools are critical-risk (destructive or financial) and cost 1,191 tokens (3% 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 Tengu — 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 TENGU TOKEN COST →

Instant setup, no code required.

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

//FAQ

Tengu token-cost questions.

How many tokens does the Tengu MCP server use?+

Its 337 tool definitions total 47,106 tokens — 24% 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 Tengu 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 Tengu's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Tengu 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 419 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.

// METHOD & REVIEW

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 05-09-2026 from the PolicyLayer scan database over all 337 catalogued Tengu tools. Counts refresh with every site build.

THIS SERVER: All Tengu tools Tengu policy Token-cost calculator

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

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

CUT TENGU TOKEN COST →

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.