Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

OMENZ agent tools

REMOTE · WWW.OMENZ.ORG

For agents that pay: Authorize (OFAC screen), Guard, Send Check, Checkout, Rescue, budgets, x402.

Available components

+8 this week 67 Trust /100

Last scanned (10 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability58
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 19321 tokens (~166/item across 116 items; 116 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 99% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 117 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Authorization in Endpoint SecurityAuthorisation not fully verified: no authorisation is required to call this server, and 1 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 −6
    • Authorization: partial → unverified ▼ security
    • Tool “queue_claim” rewrote its description, which is the text the model reads security
    • Tool “queue_enqueue” rewrote its description, which is the text the model reads security
    • Tool “authorize” rewrote its description, which is the text the model reads security
    • Tool “guard” rewrote its description, which is the text the model reads security
    • Tool “market_payee” rewrote its description, which is the text the model reads security
    • Schema quality: 17451 → 19321 ▼ functional
    • New tool “send_check” functional
    • New tool “allowance” functional
    • New tool “checkpoint_create” functional
    • New tool “checkpoint_status” functional
    • New tool “checkpoint_submit” functional
    • New tool “omenz_conventions” functional
    • New tool “omenz_loadouts” functional
    • New tool “omenz_tell_us_what_you_need” functional
    • New tool “omenz_track_record” functional
    • New tool “seller_acceptance_check” functional
    • New tool “swapmeet_search” functional
    • New tool “token_balance” functional
    • New tool “wallet_watch” functional
    • New tool “wallet_watch_report” functional
  • 20 Nov 26 0
    • New tool “loadout_check” functional
    • New tool “loadout_compile” functional
    • New tool “loadout_simulate” functional
    • New tool “robot_action_gate” functional
  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Nov 26 0
    • Tool “alive” rewrote its description, which is the text the model reads security
    • Tool “budget_release” rewrote its description, which is the text the model reads security
    • Tool “budget_spend” rewrote its description, which is the text the model reads security
    • Tool “budget_status” rewrote its description, which is the text the model reads security
    • Tool “context_diet” rewrote its description, which is the text the model reads security
    • Tool “dedupe” rewrote its description, which is the text the model reads security
    • Tool “facilitators” rewrote its description, which is the text the model reads security
    • Tool “freshness” rewrote its description, which is the text the model reads security
    • Tool “jacket_history” rewrote its description, which is the text the model reads security
    • Tool “ledger_append” rewrote its description, which is the text the model reads security
    • Tool “ledger_get” rewrote its description, which is the text the model reads security
    • Tool “locker_get” rewrote its description, which is the text the model reads security
    • Tool “market_payee” rewrote its description, which is the text the model reads security
    • Tool “name_resolve” rewrote its description, which is the text the model reads security
    • Tool “passport_check” rewrote its description, which is the text the model reads security
    • Tool “pobox_create” rewrote its description, which is the text the model reads security
    • Tool “pobox_drop” rewrote its description, which is the text the model reads security
    • Tool “pobox_inbox” rewrote its description, which is the text the model reads security
    • Tool “queue_award” rewrote its description, which is the text the model reads security
    • Tool “queue_bid” rewrote its description, which is the text the model reads security
    • Tool “queue_claim” rewrote its description, which is the text the model reads security
    • Tool “queue_complete” rewrote its description, which is the text the model reads security
    • Tool “queue_enqueue” rewrote its description, which is the text the model reads security
    • Tool “queue_escalate” rewrote its description, which is the text the model reads security
    • Tool “queue_fail” rewrote its description, which is the text the model reads security
    • Tool “queue_heartbeat” rewrote its description, which is the text the model reads security
    • Tool “queue_resolve” rewrote its description, which is the text the model reads security
    • Tool “queue_status” rewrote its description, which is the text the model reads security
    • Tool “quote” rewrote its description, which is the text the model reads security
    • Tool “reputation” rewrote its description, which is the text the model reads security
    • Tool “sale_record” rewrote its description, which is the text the model reads security
    • Tool “seller_record” rewrote its description, which is the text the model reads security
    • Tool “spend_gate” rewrote its description, which is the text the model reads security
    • Tool “wallet_balance” rewrote its description, which is the text the model reads security
    • Tool “authorize” rewrote its description, which is the text the model reads security
    • Tool “authorize_get” rewrote its description, which is the text the model reads security
    • Tool “uptime_report” rewrote its description, which is the text the model reads security
    • Schema quality: 150 → 169 ▼ functional
    • Schema quality: 11116 → 14269 ▼ functional
    • New tool “budget_delegate” functional
    • New tool “dispute_packet” functional
    • New tool “guard” functional
    • New tool “market_job” functional
    • New tool “market_job_guarded” functional
    • New tool “po_issue” functional
    • New tool “po_redeem” functional
    • New tool “settlement_cost” functional
    • New tool “settlement_rescue” functional
    • New tool “budget_create” functional
    • New tool “budget_release” functional
    • New tool “budget_spend” functional
    • New tool “budget_status” functional
    • New tool “checkout_close” functional
    • New tool “checkout_open” functional
    • New tool “delivery_check” functional
    • New tool “facilitators” functional
    • New tool “market_cheapest” functional
    • New tool “name_resolve” functional
    • New tool “pay_verify” functional
    • New tool “sale_record” functional
    • New tool “seller_record” functional
    • New tool “spend_receipt” functional
    • New tool “tx_decode” functional
    • “budget_create” added an optional parameter “velocity_max_per_hour” cosmetic
    • “market_find” added an optional parameter “need” cosmetic
  • 17 Nov 26 +12

    We did not load change detail this far back for this component, so this day may have recorded more than is shown.

    • Authorization: unverified → partial ▲ security
    • Tool “authorize” rewrote its description, which is the text the model reads security
    • Tool coverage: 15% → 100% ▲ functional
    • Destructive annotations: All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. functional
    • New tool “authorize_get” functional
    • “authorize” added an optional parameter “spend” cosmetic
    • “queue_complete” reworded the description of “item_id” cosmetic
    • “receipt_put” reworded the description of “payer” cosmetic
    • “handoff_pack” reworded the description of “required” cosmetic
    • “freshness” reworded the description of “url” cosmetic
    • “claim_evidence” reworded the description of “claim” cosmetic
    • “jacket_create” reworded the description of “checkpoint” cosmetic
    • “market_find” reworded the description of “network” cosmetic
    • “handoff_pack” reworded the description of “to” cosmetic
    • “queue_enqueue” reworded the description of “queue_id” cosmetic
    • “failure_put” reworded the description of “to” cosmetic
    • “uptime_watch” reworded the description of “url” cosmetic
    • “queue_heartbeat” reworded the description of “worker_id” cosmetic
    • “market_price_index” reworded the description of “min_payers” cosmetic
    • “finance_refund_request” reworded the description of “receipt_ids” cosmetic
    • “failure_put” reworded the description of “ttl_days” cosmetic
    • “branch” reworded the description of “city” cosmetic
    • “vendor_check” reworded the description of “method” cosmetic
    • “finance_watchdog” reworded the description of “endpoints” cosmetic
    • “ledger_append” reworded the description of “entry” cosmetic
    • “wallet_runway” reworded the description of “address” cosmetic
    • “finance_refund_request” reworded the description of “order” cosmetic
    • “queue_resolve” reworded the description of “queue_id” cosmetic
    • “queue_award” reworded the description of “queue_id” cosmetic
    • “cost_estimate” reworded the description of “job” cosmetic
    • “authorize” reworded the description of “passport_token” cosmetic
    • “capability_card” reworded the description of “method” cosmetic
    • “market_find” reworded the description of “live_check” cosmetic
    • “market_reliability” reworded the description of “url” cosmetic
    • “queue_fail” reworded the description of “retry” cosmetic
    • “queue_complete” reworded the description of “worker_id” cosmetic
    • “jacket_checkin” reworded the description of “checkpoint” cosmetic
    • “contract_build” reworded the description of “terms” cosmetic
    • “queue_bid” reworded the description of “item_id” cosmetic
    • “finance_refund_request” reworded the description of “remedy” cosmetic
    • “jacket_checkin” reworded the description of “state_patch” cosmetic
    • “jacket_checkin” reworded the description of “state” cosmetic
    • “jacket_checkin” reworded the description of “worker” cosmetic
    • “spend_gate” reworded the description of “policy” cosmetic
    • “contract_accept” reworded the description of “delivered” cosmetic
    • “queue_complete” reworded the description of “result” cosmetic
    • “context_diet” reworded the description of “max_string_chars” cosmetic
    • “finance_refund_request” reworded the description of “failure” cosmetic
    • “market_find” reworded the description of “limit” cosmetic
    • “pobox_drop” reworded the description of “subject” cosmetic
    • “context_diet” reworded the description of “max_list_items” cosmetic
    • “receipt_put” reworded the description of “currency” cosmetic
    • “jacket_checkin” reworded the description of “keep_lease” cosmetic
    • “jacket_checkin” reworded the description of “note” cosmetic
    • “queue_heartbeat” reworded the description of “queue_id” cosmetic
    • “market_payee” reworded the description of “address” cosmetic
    • “queue_fail” reworded the description of “worker_id” cosmetic
    • “queue_escalate” reworded the description of “queue_id” cosmetic
    • “dedupe” reworded the description of “namespace_key” cosmetic
    • “queue_escalate” reworded the description of “item_id” cosmetic
    • “branch” reworded the description of “url” cosmetic
    • “authorize” reworded the description of “method” cosmetic
    • “market_reliability” reworded the description of “method” cosmetic
    • “queue_escalate” reworded the description of “worker_id” cosmetic
    • “uptime_report” reworded the description of “id” cosmetic
    • “handoff_pack” reworded the description of “ttl_days” cosmetic
    • “queue_heartbeat” reworded the description of “checkpoint” cosmetic
    • “terms_changed” reworded the description of “url” cosmetic
    • “queue_create” reworded the description of “supervisor_box_id” cosmetic
    • “queue_enqueue” reworded the description of “priority” cosmetic
    • “tx_preflight” reworded the description of “max_price_usd” cosmetic
    • “preflight” reworded the description of “job” cosmetic
    • “ledger_get” reworded the description of “id” cosmetic
    • “event_check” reworded the description of “claim” cosmetic
    • “split_check” reworded the description of “network” cosmetic
    • “tx_preflight” reworded the description of “expected_pay_to” cosmetic
    • “receipt_put” reworded the description of “network” cosmetic
    • “jacket_create” reworded the description of “passport_token” cosmetic
    • “ledger_append” reworded the description of “ledger_id” cosmetic
    • “finance_reconcile” reworded the description of “payments” cosmetic
    • “finance_forecast” reworded the description of “spend” cosmetic
    • “authorize” dropped the optional parameter “spent_today_usd” cosmetic
    • Tool “changed” changed its title: Did a web page really change since your last visit? Content cosmetic
    • Tool “secret_scan” changed its title: Secret-Leak Preflight cosmetic
    • Tool “queue_fail” changed its title: Agent Workforce cosmetic
    • Tool “queue_create” changed its title: Agent Workforce cosmetic
    • Tool “queue_enqueue” changed its title: Agent Workforce cosmetic
    • Tool “quote” changed its title: Price Quote cosmetic
    • Tool “receipt_put” changed its title: Receipt Locker cosmetic
    • Tool “queue_resolve” changed its title: Agent Workforce cosmetic
    • Tool “tx_preflight” changed its title: Transaction Preflight cosmetic
    • Tool “queue_claim” changed its title: Agent Workforce cosmetic
    • Tool “jacket_create” changed its title: Job Jacket cosmetic
    • Tool “preflight” changed its title: Agent Preflight cosmetic
    • Tool “vendor_check” changed its title: Vendor Due-Diligence Pack cosmetic
    • Tool “jacket_history” changed its title: Job Jacket history cosmetic
    • Tool “pobox_drop” changed its title: Agent PO Box cosmetic
    • Tool “queue_bid” changed its title: Agent Workforce cosmetic
    • Tool “authorize” changed its title: OMENZ Authorize cosmetic
    • Tool “finance_refund_request” changed its title: Structured Refund Request cosmetic
    • Tool “pobox_inbox” changed its title: Agent PO Box cosmetic
    • Tool “ledger_append” changed its title: Agent Job Ledger cosmetic
    • Tool “split_check” changed its title: Split Check cosmetic
    • Tool “market_payee” changed its title: Payee Check cosmetic
    • Tool “freshness” changed its title: Source Freshness / Result TTL cosmetic
  • 15 Nov 26 +1

    We did not load change detail this far back for this component, so this day may have recorded more than is shown.

  • 14 Nov 26 59

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://www.omenz.org/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=www.omenz.org CN=YR1,O=Let's Encrypt,C=US 8 Nov 2026 6 Feb 2027 RSA 2048 SHA256-RSA 6029acb7cb517cf0e04f3b8b57aed385249
SANs: www.omenz.org
CN=YR1,O=Let's Encrypt,C=US (CA) CN=Root YR,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 RSA 2048 SHA256-RSA a20253f15f2691c05dc1ce13b9bcca4e
CN=Root YR,O=ISRG,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 RSA 4096 SHA256-RSA f24b6d17f9d9ad7cb1c9fea78782699f

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of www.omenz.org. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
org. DS published 725 8 Verified
omenz.org. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://www.omenz.org/mcp Verified 200
http (plaintext) http://www.omenz.org/mcp HTTPS enforced 308 https://www.omenz.org/mcp
MCP tools · 116 exposed · ~19,276 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
agent_ready ~102

Score 0-100 for how well AI assistants and agents can find, read and use a business website, with prioritized plain-language fixes. Deterministic, no AI calls. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/agent-ready, $0.10 via x402.)

NameTypeReqDescription
urlstringyesPublic website URL

No output schema declared.

No examples provided.

alive ~139

Proof-of-Life: is this API/endpoint answering right now, before you spend money calling it? One unpaid probe: up, paywalled (valid x402 requirements), auth_required, not_found, wrong_method, degraded, tls_error or down, with latency. Never pays the target. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/alive, $0.002 via x402.)

NameTypeReqDescription
methodstring–HTTP method the endpoint expects (default GET)
urlstringyesEndpoint URL to probe

No output schema declared.

No examples provided.

allowance ~197

Allowance Check (Base): how much can this spender move from this wallet right now? Reads the live ERC-20 allowance and the owner's balance: UNLIMITED (risk HIGH) / COVERS_FULL_BALANCE / LIMITED / NO_ALLOWANCE, with a safe next action and the exact revoke call (approve(spender, 0)). Optional intended_usd says whether a stablecoin allowance covers your next payment. For agents before approving, paying through a contract, or cleaning up old approvals. Public chain data, never signs. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/allowance, $0.002 via x402.)

NameTypeReqDescription
intended_usdnumber–intended usd
ownerstringyesowner
spenderstringyesspender
tokenstringyestoken

No output schema declared.

No examples provided.

authorize ~346

OMENZ Authorize: the authorization step for agent payments. One call before paying any x402 endpoint: live quote + preflight (up, price within max, network, stablecoin, expected payTo), payee check (known x402 seller?) + OFAC sanctions screen (a sanctioned payTo = DECLINE), fair-price check vs comparable endpoints, the owner's spend policy and Permission Passport if sent -> APPROVE / REVIEW / DECLINE with reasons and a signed 5-minute authorization code anyone can verify. Never pays the target. Doing many? Prepay once (POST /v1/credits/buy-1, $1) and check via /v1/authorize/credit at 2% of the payment (min $0.0003), with no per-check settlement. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/authorize, $0.002 via x402.)

NameTypeReqDescription
expected_pay_tostring–payout wallet you expect (0x...), to catch swapped payees
max_price_usdnumber–most you are willing to pay per call, in USD
methodstring–HTTP method of the target endpoint (GET or POST)
passport_tokenstring–passport token
policyobject–your spend policy, e.g. {"daily_cap_usd": 5}
spendobject–what you have spent so far, e.g. {"spent_today_usd": 1.2}
urlstringyesfull https URL to check

No output schema declared.

No examples provided.

authorize_get ~273

OMENZ Authorize (GET form): same APPROVE / REVIEW / DECLINE check before paying an x402 endpoint, with query params: url, method, max_price_usd, expected_pay_to, daily_cap_usd, spent_today_usd. Returns reasons + a signed 5-minute authorization code. Never pays the target. Doing many? Prepay once (POST /v1/credits/buy-1, $1) and check via /v1/authorize/credit at 2% of the payment (min $0.0003), with no per-check settlement. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/authorize, $0.002 via x402.)

NameTypeReqDescription
daily_cap_usdnumber–daily cap usd
expected_pay_tostring–payout wallet you expect (0x...), to catch swapped payees
max_price_usdnumber–most you are willing to pay per call, in USD
methodstring–HTTP method of the target endpoint (GET or POST)
spent_today_usdnumber–spent today usd
urlstringyesfull https URL to check

No output schema declared.

No examples provided.

branch ~159

Branch Resolver: which location page of a multi-location business is the one you mean? Give the business website and a city, ZIP or street; get the matching branch page with its phone, address, hours and notices from the business's own site. Ambiguous or missing matches come back as such with candidates, never guessed. Deterministic. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/branch, $0.01 via x402.)

NameTypeReqDescription
citystring–city
streetstring–street
urlstringyesfull https URL to check
zipstring–zip

No output schema declared.

No examples provided.

budget_create ~256

Shared Budget: one spending cap a whole TEAM of agents draws from (total, per day or per month), with a per-purchase max, an escalate line and allowed/blocked payees. Spend Gate is stateless, so 5 agents can each stay under $1 and spend $5 together; a Shared Budget keeps the one running total. Returns budget_id + owner_key + spender_key (shown once). Bookkeeping only: OMENZ never holds or moves money. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/budget/create, $0.002 via x402.)

NameTypeReqDescription
allowed_recipientsarray–allowed recipients
blocked_recipientsarray–blocked recipients
cap_usdnumberyescap usd
escalate_above_usdnumber–escalate above usd
namestring–name
per_tx_max_usdnumber–per tx max usd
periodstring–period
ttl_daysinteger–ttl days
velocity_max_per_hourinteger–velocity max per hour

No output schema declared.

No examples provided.

budget_delegate ~301

Delegation Budget (agent allowances): a parent budget's OWNER gives a child agent its own bounded allowance: human/company -> supervisor agent -> workers -> sub-agents (4 levels). The child can only NARROW the parent: cap <= parent, per-purchase max, allowed payees (subset), blocked payees (inherited), velocity limit (purchases/hour), expiry <= parent. Every child spend is checked against and counted in every ancestor, so the company cap holds across the whole tree; freezing a parent stops all descendants; budget/status shows spend by child. Header X-Budget-Key = the parent's owner_key. Bookkeeping only. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/budget/delegate, $0.01 via x402.)

NameTypeReqDescription
allowed_recipientsarray–allowed recipients
blocked_recipientsarray–blocked recipients
budget_idstringyesbudget id
cap_usdnumberyescap usd
escalate_above_usdnumber–escalate above usd
namestring–name
per_tx_max_usdnumber–per tx max usd
periodstring–period
ttl_daysinteger–ttl days
velocity_max_per_hourinteger–velocity max per hour

No output schema declared.

No examples provided.

budget_release ~113

Shared Budget: give a recorded spend back to the cap when the purchase failed, was refunded or never happened. Header X-Budget-Key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/budget/release, $0.002 via x402.)

NameTypeReqDescription
budget_idstringyesbudget id
reasonstring–reason
spend_idstringyesspend id

No output schema declared.

No examples provided.

budget_spend ~208

Shared Budget: ask before each purchase. ALLOW records it against the team cap (returns spend_id + what's left); DENY or ESCALATE records nothing, with the reason. Idempotent by idempotency_key, so retries never double-count. Header X-Budget-Key. Honest limit: two spends in the same instant can both pass; per_tx_max_usd bounds that. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/budget/spend, $0.002 via x402.)

NameTypeReqDescription
agentstring–agent
amount_usdnumberyesamount usd
budget_idstringyesbudget id
idempotency_keystring–idempotency key
memostring–memo
recipientstring–recipient
urlstring–full https URL to check

No output schema declared.

No examples provided.

budget_status ~111

Shared Budget: cap, spent, remaining this window, spend by agent and by payee, recent purchases. Header X-Budget-Key (owner or spender). By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/budget/status, $0.002 via x402.)

NameTypeReqDescription
idstringyesid returned by the create/put call
limitinteger–limit

No output schema declared.

No examples provided.

capability_card ~143

Agent Capability Card: a standard machine-readable card (omenz.capability-card.v0) of what any x402 service offers: endpoints, live prices and payment options, input/output examples from its discovery data, latency. Works on a service index or a single endpoint; never pays. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/capability-card, $0.002 via x402.)

NameTypeReqDescription
methodstring–HTTP method of the target endpoint (GET or POST)
urlstringyesfull https URL to check

No output schema declared.

No examples provided.

changed ~92

Did a web page really change since your last visit? Content hash that ignores timestamps and boilerplate. Pass previous=<hash> to compare. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/changed, $0.005 via x402.)

NameTypeReqDescription
urlstringyesPublic website URL

No output schema declared.

No examples provided.

checkout_close ~244

OMENZ Checkout (close): ONE call after paying. Send checkout_id + the tx hash (or PAYMENT-RESPONSE header) + the response you got. Verifies settlement on Base against the authorized payee and amount, checks delivery against the seller's advertised output, returns a signed Spend Receipt (GOOD_BUY / PAID_NOT_DELIVERED / PAYMENT_NOT_CONFIRMED), gives the money back to the Shared Budget if you never paid, and updates the seller's track record. High volume: checkout/close/credit at 1% (min $0.0002). By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/checkout/close, $0.002 via x402.)

NameTypeReqDescription
checkout_idstringyescheckout id
delivered––delivered
not_paidboolean–not paid
payment_responsestring–payment response
release_if_unconfirmedboolean–release if unconfirmed
schemaobject–schema
tx_hashstring–tx hash

No output schema declared.

No examples provided.

checkout_open ~349

OMENZ Checkout (open): ONE call before your agent pays any x402 seller. Send the url (or just q = what you need and OMENZ picks the cheapest seller that answers right now), your max price, optional Shared Budget (budget_id + X-Budget-Key) and policy. Runs Authorize (live quote, payTo, fair price, policy), the seller's OMENZ track record, and draws from the team budget: GO / REVIEW / STOP + checkout_id + signed 5-minute authorization. Provider-neutral, any wallet; never touches your money. High volume: checkout/open/credit at 1% of the purchase (min $0.0002). By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/checkout/open, $0.002 via x402.)

NameTypeReqDescription
agentstring–agent
budget_idstring–budget id
expected_pay_tostring–payout wallet you expect (0x...), to catch swapped payees
idempotency_keystring–idempotency key
job_idstring–job id
max_price_usdnumber–most you are willing to pay per call, in USD
methodstring–HTTP method of the target endpoint (GET or POST)
policyobject–your spend policy, e.g. {"daily_cap_usd": 5}
purposestring–purpose
qstring–search text
urlstring–full https URL to check

No output schema declared.

No examples provided.

checkpoint_create ~170

OMENZ Checkpoint (create): split an agent job into paid milestones. Each milestone has an amount, its own deterministic acceptance tests (required_fields, field_types, regex, min_items, max_bytes, equals, url_alive, claim_evidence) and an optional deadline. Returns a signed plan and checkpoint_id. OMENZ never holds funds. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/checkpoint/create, $0.005 via x402.)

NameTypeReqDescription
buyerstring–buyer
jobstring–job
milestonesarrayyesmilestones
sellerstring–seller
total_usdnumber–total usd

No output schema declared.

No examples provided.

checkpoint_status ~108

OMENZ Checkpoint (status): where a milestone job stands: each milestone RELEASE / REFUND / RETRY / PENDING with attempts, and released / refunded / pending USD. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/checkpoint/status, $0.002 via x402.)

NameTypeReqDescription
idstringyesid returned by the create/put call

No output schema declared.

No examples provided.

checkpoint_submit ~171

OMENZ Checkpoint (submit): deliver one milestone. Its acceptance tests run; you get PASS/FAIL and the escrow verdict for THAT tranche: RELEASE (buyer pays it now), RETRY (seller fixes, max 3 attempts) or REFUND (failed or late, not owed), a signed receipt, and running totals (released / refunded / pending). A decided milestone can't be passed or counted twice. Seller track record updated. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/checkpoint/submit, $0.01 via x402.)

NameTypeReqDescription
checkpoint_idstringyescheckpoint id
deliveredobjectyesdelivered
milestonestringyesmilestone

No output schema declared.

No examples provided.

claim_evidence ~168

Claim -> Evidence: does this source actually say what you're about to cite it for? Send a claim and the source URL; get SUPPORTED with the exact sentence, PARTIAL with the closest sentences and which numbers/names are missing, NOT_FOUND, or CHECK_NEGATION when the matching sentence denies it. Strict: every number must appear next to the claim's own names (no borrowing another plan's price). Deterministic, no AI calls. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/claim-evidence, $0.005 via x402.)

NameTypeReqDescription
claimstringyesclaim
urlstringyesfull https URL to check

No output schema declared.

No examples provided.

context_diet ~143

Context Diet: shrink a packet before it fills your context: drops empty fields, dedupes lists, cuts long strings to a head + sha256 pointer, caps list length, always keeps required fields; reports bytes and approximate tokens saved. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/context-diet, $0.002 via x402.)

NameTypeReqDescription
max_list_itemsinteger–max list items
max_string_charsinteger–max string chars
packet–yespacket
requiredarray–required

No output schema declared.

No examples provided.

contract_accept ~134

Acceptance Test as a Service + escrow verdict: a neutral party runs the contract's tests on what was delivered. PASS/FAIL per test, escrow_verdict RELEASE/REFUND (OMENZ never holds funds: the payer acts on it), and a signed attestation that feeds the seller's Reputation Receipts. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/contract/accept, $0.005 via x402.)

NameTypeReqDescription
delivered–yesdelivered
tokenstringyestoken

No output schema declared.

No examples provided.

contract_build ~138

A2A Contract Builder: turn a machine job into signed terms both agents hold: deliverable, deterministic acceptance tests (required_fields, field_types, regex, min_items, max_bytes, equals, url_alive, claim_evidence), max spend, deadline, parties. Ed25519-signed by OMENZ; verify offline with /v1/passport/key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/contract/build, $0.002 via x402.)

NameTypeReqDescription
termsobjectyesterms

No output schema declared.

No examples provided.

cost_estimate ~155

Cost-to-Complete Estimate: what will this agent job cost BEFORE it starts? Give the steps (model, input/output tokens, runs, retry rate) with your model prices, and paid tool calls (price, or an x402 URL we quote live without paying). Get the total, a realistic range, the biggest cost, budget fit, value multiple, and how much routing named steps to a cheaper model saves. Deterministic arithmetic. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/cost-estimate, $0.002 via x402.)

NameTypeReqDescription
jobobjectyesjob

No output schema declared.

No examples provided.

credits_buy_1 ~132

OMENZ prepaid credits: $1.00 balance in one x402 payment. Checks then draw from the balance with no per-check settlement: OMENZ Authorize costs 2% of the payment being checked (minimum $0.0003) via POST /v1/authorize/credit. Returns credit_id + credit_key (shown once). By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/credits/buy-1, $1.00 via x402.)

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

credits_buy_5 ~132

OMENZ prepaid credits: $5.00 balance in one x402 payment. Checks then draw from the balance with no per-check settlement: OMENZ Authorize costs 2% of the payment being checked (minimum $0.0003) via POST /v1/authorize/credit. Returns credit_id + credit_key (shown once). By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/credits/buy-5, $5.00 via x402.)

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

dedupe ~143

Duplicate-Work Detector: before your agent pays to run a task, check whether someone in your team (same private namespace_key) already did it: normalized fingerprint -> HIT with the earlier result pointer, or MISS (pass result_pointer to register this run). By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/dedupe, $0.002 via x402.)

NameTypeReqDescription
namespace_keystringyesnamespace key
result_pointerstring–result pointer
task–yestask
ttl_hoursinteger–ttl hours

No output schema declared.

No examples provided.

delivery_check ~208

Delivery Check: you paid; did you get what was advertised? Send the paid endpoint's url (+ method) and the JSON it returned. We read the seller's own x402 discovery output example (unpaid probe) or use your JSON Schema, then compare fields and value types: MATCH / PARTIAL / MISMATCH / NO_CONTRACT, with exactly what's missing, empty or the wrong kind, and error bodies caught. Evidence for finance/refund-request. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/delivery-check, $0.002 via x402.)

NameTypeReqDescription
delivered–yesdelivered
example––example
methodstring–HTTP method of the target endpoint (GET or POST)
must_havearray–must have
schemaobject–schema
urlstring–full https URL to check

No output schema declared.

No examples provided.

dispute_packet ~339

Dispute Packet: a purchase went bad (not delivered, wrong output, partial, overcharged, duplicate). One call builds the machine-readable case: settlement proof on Base (Settlement Rescue: did money move, how much, to whom, duplicates), the seller's own advertised output captured live (what was promised), a Delivery Check of what came back, a timeline, and a signed refund request (remedy + amount + evidence strength), all hash-listed in an Ed25519-signed manifest anyone can verify offline. Send checkout_id or url + tx_hash / payment_header / payer+pay_to, the delivered response and the issue. OMENZ packages evidence; it never rules on disputes or moves money. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/dispute/packet, $0.10 via x402.)

NameTypeReqDescription
amount_requested_usdnumber–amount requested usd
amount_usdnumber–amount usd
checkout_idstring–checkout id
delivered––delivered
issuestring–issue
methodstring–HTTP method of the target endpoint (GET or POST)
pay_tostring–pay to
payerstring–payer
payment_headerstring–payment header
schemaobject–schema
sellerstring–seller
tx_hashstring–tx hash
urlstring–full https URL to check
whatstring–what

No output schema declared.

No examples provided.

event_check ~213

Event Check: did a US public company actually FILE this news, or is it just going around? Give a ticker or name and the claim (CEO resigned, acquisition, results, bankruptcy, restatement, cyber incident, layoffs...). We map it to the required SEC 8-K item, pull the company's recent filings from EDGAR, and quote the sentence that states it. FILED only when one sentence carries the claim's names and roles; otherwise FILED_RELATED, NO_FILING_YET (4-business-day filing window), NOT_A_FILING_EVENT or NOT_FOUND. Deterministic. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/event-check, $0.005 via x402.)

NameTypeReqDescription
claimstringyesclaim
companystringyesticker or company name
daysinteger–lookback window, 1-365 (default 30)

No output schema declared.

No examples provided.

evidence_bundle ~120

Machine Evidence Bundle: package receipts, ledger heads, attestation tokens, claims and sources into one signed, hash-listed bundle (merkle-style root) that any agent can verify offline. For disputes, audits, refunds and handoffs. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/evidence/bundle, $0.002 via x402.)

NameTypeReqDescription
itemsarrayyesitems
labelstring–label

No output schema declared.

No examples provided.

facilitators ~227

Facilitator Status + Router: which x402 facilitators are answering RIGHT NOW and which to use. Live probe of 10 known facilitators (PayAI, Coinbase CDP, x402.rs, Daydreams, Dexter, Mogami, OpenX402, the x402.org reference and more, plus one URL of yours): up / auth_required / down, latency, networks, schemes (exact/upto), x402 versions. Say network + scheme and get the fastest live facilitator plus fallbacks. For sellers choosing or failing over a facilitator, and SDKs routing settlement. Never pays or settles anything. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/facilitators, $0.002 via x402.)

NameTypeReqDescription
networkstring–chain name, e.g. base
schemestring–scheme
urlstring–full https URL to check
x402_versioninteger–x402 version

No output schema declared.

No examples provided.

failure_put ~216

Failure Receipt + Dead-Letter Queue: when a job fails, record WHY in a standard machine-readable form (omenz.failure.v0: objective, failed_step, error_class from a fixed list, attempts, money spent, receipts, partial artifacts, suggested next step, retryable). Secret-scanned first (secrets = refused, not stored, not charged). Stored encrypted in an Agent Locker for the next agent; pass dlq_box_id to also drop a sealed pointer into an Agent PO Box used as your dead-letter queue. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/failure/put, $0.002 via x402.)

NameTypeReqDescription
dlq_box_idstring–dlq box id
failureobjectyesobjective and failed_step required
fromstring–from
tostring–to
ttl_daysinteger–ttl days

No output schema declared.

No examples provided.

finance_forecast ~116

Agent Budget Forecaster: spend history -> daily rate, next 7/30-day projection, trend, biggest dependencies. Deterministic; never pays a target. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/finance/forecast, $0.002 via x402.)

NameTypeReqDescription
spend––what you have spent so far, e.g. {"spent_today_usd": 1.2}

No output schema declared.

No examples provided.

finance_reconcile ~133

Invoice/Payment Reconciler: invoice lines vs USDC-on-Base payments, each transaction checked on-chain (payer, payee, amount): MATCH / UNDERPAID / OVERPAID / MISSING / UNVERIFIED, duplicates and line-total errors flagged. Deterministic; never pays a target. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/finance/reconcile, $0.005 via x402.)

NameTypeReqDescription
invoice––invoice
payments––payments

No output schema declared.

No examples provided.

finance_refund_request ~142

Structured Refund Request: order + failure receipt + payment receipts + purchase snapshot -> a standard signed dispute object with evidence strength and gaps. OMENZ packages evidence; it doesn't rule or move money. Deterministic; never pays a target. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/finance/refund-request, $0.002 via x402.)

NameTypeReqDescription
failure––failure
order––order
receipt_ids––receipt ids
remedy––remedy
snapshot_token––snapshot token

No output schema declared.

No examples provided.

finance_snapshot ~120

Machine Warranty / Purchase Snapshot: signed record of exactly what a paid endpoint promised (live x402 requirements, description, examples) at purchase time. Deterministic; never pays a target. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/finance/snapshot, $0.002 via x402.)

NameTypeReqDescription
method––HTTP method of the target endpoint (GET or POST)
url––full https URL to check

No output schema declared.

No examples provided.

finance_watchdog ~109

Subscription Watchdog: the paid endpoints your agent business relies on (up to 8): live price vs expected, down/up, terms/pricing page changed (pass back fingerprints). Deterministic; never pays a target. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/finance/watchdog, $0.005 via x402.)

NameTypeReqDescription
endpoints––endpoints

No output schema declared.

No examples provided.

freshness ~155

Source Freshness / Result TTL: how long can your agent reuse a result before paying to fetch it again? The source's own Last-Modified, ETag and Cache-Control + a reuse window by data kind (price, quote, hours, weather, news, stock, crypto, business_facts, terms, docs, filing, profile, search) + how to revalidate cheaply (304). By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/freshness, $0.002 via x402.)

NameTypeReqDescription
kindstring–kind
urlstringyesfull https URL to check

No output schema declared.

No examples provided.

guard ~391

OMENZ Transaction Guard: ONE call before money moves. 'PAY $X TO Y FOR Z' -> GO / CAUTION / STOP with every check: budget authorized (Shared Budget), counterparty checked (Authorize: live 402, payTo, known seller, OFAC sanctions screen, fair price + Seller Track Record), DUPLICATE PAYMENT checked (OMENZ records and your on-chain USDC history to that payee, Base), quoted price unchanged, settlement economics, expected delivery recorded (seller's advertised output fingerprint). Then checkout/close: settled -> delivery verified -> signed receipt -> reconciled. Send url (or q), payer (your wallet), quoted_price_usd, purpose, budget_id. Larger purchases: guard/credit at 10 bps of the protected value (min $0.01, max $5). Never touches your money. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/guard, $0.05 via x402.)

NameTypeReqDescription
agentstring–agent
budget_idstring–budget id
dup_window_hoursinteger–dup window hours
expected_pay_tostring–payout wallet you expect (0x...), to catch swapped payees
max_price_usdnumber–most you are willing to pay per call, in USD
methodstring–HTTP method of the target endpoint (GET or POST)
payerstring–payer
policyobject–your spend policy, e.g. {"daily_cap_usd": 5}
purposestring–purpose
qstring–search text
quoted_price_usdnumber–quoted price usd
urlstring–full https URL to check

No output schema declared.

No examples provided.

handoff_pack ~159

Handoff Packager: hand a job to another agent with only what it needs. Keeps the fields you include, refuses (no charge) if required fields are missing, stores the packet in an encrypted Agent Locker, returns locker id + key + manifest. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/handoff/pack, $0.002 via x402.)

NameTypeReqDescription
fromstring–from
includearray–include
packetobjectyespacket
requiredarray–required
tostring–to
ttl_daysinteger–ttl days

No output schema declared.

No examples provided.

jacket_checkin ~174

Job Jacket checkin: end a shift. state_patch merges (null deletes a key) or state replaces; new checkpoint and note; the jacket becomes a new version and the lease is released. Optional Job Ledger entry (header X-Ledger-Key). Headers X-Jacket-Id / X-Jacket-Key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/jacket/checkin, $0.002 via x402.)

NameTypeReqDescription
checkpointstring–checkpoint
keep_leaseboolean–keep lease
notestring–note
stateobject–state
state_patchobject–state patch
workerstringyesworker

No output schema declared.

No examples provided.

jacket_checkout ~169

Job Jacket checkout: start a shift. Returns only what this worker needs (objective, instructions, checkpoint, state trimmed to requested fields / size, Passport verdict) and a lease so no other worker holds it at the same time; take_over for dead workers. Headers X-Jacket-Id / X-Jacket-Key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/jacket/checkout, $0.002 via x402.)

NameTypeReqDescription
fieldsarray–fields
lease_minutesinteger–lease minutes
max_string_charsinteger–max string chars
take_overboolean–take over
workerstringyesworker

No output schema declared.

No examples provided.

jacket_create ~195

Job Jacket: create the portable minimum working state for one assignment (objective, instructions, state, checkpoint, optional Permission Passport + Job Ledger link). Encrypted with a key only you hold, up to 30 days, 64 KB. Returns jacket_id + jacket_key (shown once). Credentials are refused: keep reference names only. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/jacket/create, $0.002 via x402.)

NameTypeReqDescription
checkpointstring–checkpoint
instructionsstring–instructions
job_idstring–job id
ledger_idstring–ledger id
objectivestringyesobjective
passport_tokenstring–passport token
stateobject–state
ttl_daysinteger–ttl days

No output schema declared.

No examples provided.

jacket_history ~95

Job Jacket history: every version (who, when, checkpoint, note, state hash; never the contents) and the current lease. Headers X-Jacket-Id / X-Jacket-Key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/jacket/history, $0.002 via x402.)

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

ledger_append ~157

Agent Job Ledger: append one entry (type tool_call|spend|receipt|handoff|failure|output|status|note|decision, any fields, amount_usd optional). Each entry is chained to the previous by sha256; secrets are refused. Header X-Ledger-Key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/ledger/append, $0.002 via x402.)

NameTypeReqDescription
entryobjectyesentry
ledger_idstringyesledger id
x_ledger_keystring–the key returned by create (sent as a header on HTTP)

No output schema declared.

No examples provided.

ledger_create ~145

Agent Job Ledger: open an append-only, hash-chained record for one job (tool calls, spend, receipts, handoffs, failures, outputs, status). Returns ledger_id + ledger_key (shown once). Kept 90 days. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/ledger/create, $0.002 via x402.)

NameTypeReqDescription
job_idstring–job id
objectivestring–objective
x_ledger_keystring–the key returned by create (sent as a header on HTTP)

No output schema declared.

No examples provided.

ledger_get ~147

Agent Job Ledger: read entries (since_seq for only new ones), totals (spent, counts by type, last status) and chain_intact: proof nothing was edited or removed. Header X-Ledger-Key. By OMENZ. (MCP calls run in AYNE, the free playzone; production: GET https://www.omenz.org/api/tollbooth/v1/ledger/get, $0.002 via x402.)

NameTypeReqDescription
idstringyesid returned by the create/put call
since_seqinteger–since seq
x_ledger_keystring–the key returned by create (sent as a header on HTTP)

No output schema declared.

No examples provided.

loadout_check ~241

OMENZ Loadout Check: will this job loadout (Agent Skin or robot loadout like HOST MODE, PERSONAL TRAINER, RECEPTIONIST) run on this robot or agent? Provider-neutral capability words vs the platform profile (ROS 2 via ros-mcp, Unitree G1/Go2 via unitree_sdk2, digital MCP agent, OMENZ sim, or your own manifest): READY / DEGRADED / NOT_COMPATIBLE per capability and workflow, add-ons to install, safety-declaration gaps (e-stop, speed, no-go zones, contact), and what a human must confirm. Deterministic. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/loadout/check, $0.01 via x402.)

NameTypeReqDescription
allow_addonsboolean–allow addons
loadout–yespreset id (GET /v1/loadouts) or an omenz.loadout.v0 object
platform––platform profile id or a custom {id, native, addon} manifest

No output schema declared.

No examples provided.

loadout_compile ~206

OMENZ Loadout Compile: turn a loadout into the platform plan (nav2 action goals for ros-mcp, unitree_sdk2 calls, or MCP tools + an Authorize passport request) plus an Ed25519-signed install receipt (omenz.loadout-install.v0: allowed capabilities, speed/payload limits, no-go zones, confirm list, expiry). Dry-run plans from public SDK docs; OMENZ never sends commands to hardware. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/loadout/compile, $0.02 via x402.)

NameTypeReqDescription
allow_addonsboolean–allow addons
loadout–yespreset id (GET /v1/loadouts) or an omenz.loadout.v0 object
platform––platform profile id or a custom {id, native, addon} manifest

No output schema declared.

No examples provided.

loadout_simulate ~167

OMENZ Loadout Simulate: run one loadout workflow (e.g. HOST MODE drink_run) in the OMENZ 2D sim home: step-by-step trace, simulated time, and the action-gate decision on every step, so you see where it stops for a human yes before any robot moves. Deterministic, not physics. By OMENZ. (MCP calls run in AYNE, the free playzone; production: POST https://www.omenz.org/api/tollbooth/v1/loadout/simulate, $0.005 via x402.)

NameTypeReqDescription
auto_confirmboolean–auto confirm
contextobject–context
loadout–yesloadout
workflowstring–workflow

No output schema declared.

No examples provided.

Install

How do I install the OMENZ agent tools MCP server?

OMENZ agent tools is a hosted endpoint at https://www.omenz.org/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · www.omenz.org

# add to Claude Code
claude mcp add --transport http org-omenz-www-agent-tools 'https://www.omenz.org/mcp'
Common questions

What is the OMENZ agent tools MCP server?

OMENZ agent tools is an MCP server listed in the public MCP registry as org.omenz.www/agent-tools. For agents that pay: Authorize (OFAC screen), Guard, Send Check, Checkout, Rescue, budgets, x402. This page covers its hosted endpoint (https://www.omenz.org/mcp).

Is the OMENZ agent tools MCP server safe to use?

OMENZ agent tools scores 67 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the OMENZ agent tools MCP server expose?

OMENZ agent tools exposes 116 tools: agent_ready, site_check, changed, local_facts, locker_put, and 111 more. Their descriptions and schemas cost roughly 19,276 tokens of context every time the server is loaded.

Does the OMENZ agent tools MCP server require authentication?

No. We connected to OMENZ agent tools without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the OMENZ agent tools MCP server still maintained?

OMENZ agent tools is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the OMENZ agent tools MCP server?

VerifyMCP ran 12 checks on OMENZ agent tools, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about OMENZ agent tools: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.