// MCP TOKEN COST

The Agent Passport System — Cryptographic Identity for AI Agents MCP server costs 23,268 tokens before the first call.

Connect Agent Passport System — Cryptographic Identity for AI Agents and its 150 tool definitions are loaded into the model's context on every request — 12% of a 200k window spent before your agent does anything.

QUICK ANSWER The Agent Passport System — Cryptographic Identity for AI Agents MCP server's tool definitions consume 23,268 tokens — 12× the median MCP server (1,905 tokens). A scoped grant exposing only the tools you use cuts that roughly in proportion.

MEASURED FROM SCHEMAS 150 tools · 23,268 tokens · 12% of 200k · 2.3% 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 12%

1M WINDOW 2.3%

Corpus context: Agent Passport System — Cryptographic Identity for AI Agents ranks #47 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 23,268 tokens go.

Each row is one tool definition as a tools/list entry — name, description and input schema — counted with o200k_base. Average: 155 tokens per tool.

Tool	Category	Tokens	% of server
mutualAuthBuildCertificate	Execute	455	2.0%
create_charter	Write	379	1.6%
create_task_brief	Write	375	1.6%
aps_capability_evaluate_authority	Read	333	1.4%
aps_compute_data_axis_weights	Read	333	1.4%
aps_capability_issue_challenge	Write	330	1.4%
create_decision_lineage_receipt	Write	326	1.4%
aps_aggregate_settlement	Execute	324	1.4%
aps_construct_attribution_primitive	Execute	317	1.4%
create_derivation_receipt	Write	306	1.3%
aps_create_attribution_receipt	Write	304	1.3%
register_data_source	Write	300	1.3%
aps_capability_sign_effect	Read	297	1.3%
mutualAuthVerifyAttest	Read	289	1.2%
generate_governance_block	Write	274	1.2%
create_reserve_attestation	Write	259	1.1%
generate_aps_txt	Write	255	1.1%
governance_360	Execute	252	1.1%
review_evidence	Read	249	1.1%
aps_compute_compute_axis_weights	Execute	248	1.1%
submit_evidence	Write	232	1.0%
create_chained_governance_block	Write	228	1.0%
aps_create_provisional	Write	221	0.9%
define_emergency_pathway	Read	219	0.9%
review_promotion	Write	210	0.9%
issue_passport	Write	205	0.9%
create_intent	Write	202	0.9%
rotate_key	Read	198	0.9%
aps_verify_settlement	Read	197	0.8%
create_artifact_provenance	Write	197	0.8%
create_outcome_record	Write	197	0.8%
aps_capability_mint_receipt	Read	196	0.8%
aps_record_owner_confirmation	Read	194	0.8%
register_agora_public	Write	194	0.8%
create_principal	Write	192	0.8%
verify_issuer	Read	190	0.8%
aps_build_contributor_query	Execute	186	0.8%
compare_timestamps	Read	186	0.8%
create_access_receipt	Write	185	0.8%
submit_deliverable	Write	183	0.8%
create_agent_context	Write	180	0.8%
endorse_agent	Read	178	0.8%
create_delegation	Write	176	0.8%
send_message	Write	176	0.8%
execute_with_context	Execute	172	0.7%
check_tier	Read	170	0.7%
post_agora_message	Write	170	0.7%
apply_reputation_downgrade	Write	169	0.7%
assign_agent	Write	169	0.7%
update_reputation	Write	169	0.7%
aps_check_escalation_required	Read	168	0.7%
mutualAuthVerifyTrustBundle	Read	167	0.7%
evaluate_threshold	Read	166	0.7%
request_intro	Read	166	0.7%
mutualAuthDeriveSession	Read	165	0.7%
supersede_v2_delegation	Read	164	0.7%
is_evidence_fresh	Read	161	0.7%
sub_delegate	Read	160	0.7%
check_jurisdiction_transfer	Read	159	0.7%
check_aggregate_constraints	Read	154	0.7%
evaluate_intent	Read	154	0.7%
create_approval_request	Write	153	0.7%
handoff_evidence	Read	150	0.6%
create_access_snapshot	Write	150	0.6%
aps_withdraw_provisional	Financial	149	0.6%
check_combination_permitted	Read	149	0.6%
request_human_approval	Read	148	0.6%
generate_settlement	Write	148	0.6%
aps_verify_attribution_projection	Read	147	0.6%
commerce_preflight	Execute	146	0.6%
file_data_dispute	Read	146	0.6%
create_v2_delegation	Write	145	0.6%
vouch_reputation	Write	145	0.6%
aps_project_attribution	Read	143	0.6%
aps_promote_statement	Write	142	0.6%
gateway_process_tool_call	Read	139	0.6%
list_tools_for_scope	Read	138	0.6%
complete_action	Write	138	0.6%
add_principal_report	Write	137	0.6%
broadcast	Write	136	0.6%
aps_check_artifact_citations	Read	135	0.6%
classify_evidence_quality	Read	135	0.6%
resolve_authority	Write	134	0.6%
compute_action_ref	Read	133	0.6%
aps_check_projection_consistency	Read	132	0.6%
aps_compute_attribution_action_ref	Read	132	0.6%
search_matches	Read	131	0.6%
sign_charter	Write	131	0.6%
respond_to_intro	Read	130	0.6%
validate_temporal_rights	Read	129	0.6%
create_policy_context	Write	129	0.6%
get_passport_grade	Read	126	0.5%
revoke_delegation	Destructive	122	0.5%
check_retention_expired	Read	122	0.5%
gateway_approve	Write	122	0.5%
aps_sign_attribution_consent	Read	121	0.5%
check_purpose_permitted	Read	120	0.5%
declare_reidentification_risk	Read	120	0.5%
verify_governance_block	Read	119	0.5%
detect_purpose_drift	Read	117	0.5%
aps_verify_attribution_primitive	Read	115	0.5%
identify	Read	112	0.5%
add_approval_signature	Write	111	0.5%
complete_task	Write	111	0.5%
create_gateway	Write	111	0.5%
aps_verify_promotion	Read	108	0.5%
activate_emergency	Write	108	0.5%
register_agora_agent	Write	106	0.5%
get_commerce_spend	Read	105	0.5%
is_key_active	Read	104	0.4%
query_contributions	Read	104	0.4%
revoke_endorsement	Destructive	102	0.4%
create_hybrid_timestamp	Write	102	0.4%
get_behavioral_sequence	Read	101	0.4%
create_disclosure	Write	101	0.4%
check_usage_permitted	Read	100	0.4%
create_data_enforcement_gate	Write	100	0.4%
resolve_lineage	Write	99	0.4%
resolve_path_terms	Write	99	0.4%
check_messages	Read	98	0.4%
compute_governance_taint	Read	98	0.4%
attest_to_floor	Read	97	0.4%
verify_aps_txt	Read	95	0.4%
aps_verify_attribution_consent	Read	94	0.4%
resolve_rights_propagation	Write	88	0.4%
aps_attribution_receipt_id	Read	84	0.4%
evaluate_revocation_impact	Read	84	0.4%
parse_governance_block_html	Execute	79	0.3%
get_evidence	Read	79	0.3%
verify_charter	Read	79	0.3%
remove_intent_card	Destructive	78	0.3%
verify_endorsement	Read	78	0.3%
verify_rotation_chain	Read	78	0.3%
list_agents	Read	77	0.3%
accept_assignment	Read	74	0.3%
get_task_detail	Read	74	0.3%
verify_delegation	Read	73	0.3%
get_agora_thread	Read	72	0.3%
load_values_floor	Read	72	0.3%
list_issuance_records	Read	69	0.3%
get_digest	Read	68	0.3%
get_agora_by_topic	Read	66	0.3%
gateway_stats	Read	58	0.2%
list_profiles	Read	58	0.2%
get_my_role	Read	49	0.2%
get_agora_topics	Read	48	0.2%
get_fleet_status	Read	48	0.2%
get_promotion_history	Read	46	0.2%
generate_keys	Write	46	0.2%
list_tasks	Read	43	0.2%

// SCOPED GRANT

Most agents use a handful of these tools. They pay for all 150.

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 (155 tokens each).

Grant scope	Definition cost	Reduction
All 150 tools (no gateway)	23,268 tokens	—
3 granted tools	~465 tokens	−98%
5 granted tools	~776 tokens	−97%
10 granted tools	~1,551 tokens	−93%

Model your own stack in the token-cost calculator, or see the Agent Passport System — Cryptographic Identity for AI Agents policy for what a sensible grant looks like.

//FAQ

Agent Passport System — Cryptographic Identity for AI Agents token-cost questions.

How many tokens does the Agent Passport System — Cryptographic Identity for AI Agents MCP server use?+

Its 150 tool definitions total 23,268 tokens — 12% 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 Agent Passport System — Cryptographic Identity for AI Agents 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 Agent Passport System — Cryptographic Identity for AI Agents's token usage?+

Expose fewer tools. A PolicyLayer grant scopes Agent Passport System — Cryptographic Identity for AI Agents 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 465 tokens, a 98% 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 07-06-2026 from the PolicyLayer scan database over all 150 catalogued Agent Passport System — Cryptographic Identity for AI Agents tools. Counts refresh with every site build.