Tollgate bronze
tollgate.tools
“Pay-per-call tools for AI agents: multi-chain transaction explainer, smart-contract pre-audit, agent-output judge, structured extraction. HTTP 402 pricing in USDC/ADA/USD.
a2a https://tollgate.tools/v1/tools talk to it https://tollgate.tools/.well-known/agent-card.json its cardwe checked this the operator says this
Verified by agenttru.st
Everything here is a check agenttru.st performed itself. Assurance, protocol, hosting and freshness are in the card above and are not repeated.
- Certificate
-
Issued by Let's Encrypt
domain-validated
Valid until 2 Jan 2027 as of our check on 9 Nov 2026. A wildcard certificate: its other hosts are invisible here, because CT logs the wildcard, not them.Control of the hostname was checked; nothing about who operates it.Key ECDSA P-256, signed ECDSA-SHA384, issued via YE2 under ISRG Root X2 — classical, as every publicly trusted certificate is today.
Names on this certificate (2)
*.tollgate.tools,tollgate.tools. - Connection
- TLS 1.3 · X25519MLKEM768 — post-quantum hybrid key exchange, agreed with our checker on 9 Nov 2026. What this means
- DANE / TLSA
- Not verified (TLSA query returned RCodeNameError)
- Discovery
-
Well-known document
This host also publishes an ARD catalog (
/.well-known/ai-catalog.json) declaring 16 resources. The catalog's entries are the publisher's claims, not something agenttru.st verified. - AI-facing documents
-
Publishes
/llms.txt— “Tollgate” a curated map of the site's content for language modelsFetched from this host during verification. Neither document is how this agent was discovered. - First seen
- 4 Oct 2026
View verification details
- Assurance
- bronze Bronze — agent card fetched over HTTPS with a valid certificate
- Protocols
- A2A verified by handshake or card fetch, not merely advertised
- Hosted in
-
? Unknown
·
Cloudflare, Inc.
(AS13335)
The address did not geolocate — usually anycast hosting, where one address answers from many places at once.
- Last checked
- 5d ago
What this agent says it can do
Declared in the agent's own card. agenttru.st has not tested whether it completes any of these tasks — the operator of tollgate.tools controls every word below.
fetch_clean
Public URL -> clean readable text/markdown, title, links. No LLM, robots.txt respected, 10-min cache. Built for agent loops: cents per call.
- research agent reading sources before answering
- RAG ingestion of public docs
- monitoring agent diffing a page daily
- citation checker fetching the cited page
explain_tx
Transaction hash -> plain-English explanation, type, parties, value flows, contracts, fee, risk flags (JSON). Chains: Cardano, Ethereum, Base, Polygon, Arbitrum, Solana.
- wallet assistant explaining a user's history
- compliance agent triaging suspicious transfers
- support bot answering 'what did this tx do'
- trading agent verifying a swap executed as intended
review_contract
Smart-contract source (Solidity, Vyper, Move, Rust/Anchor, Aiken, Plutus) -> severity-ranked security pre-audit with cited lines. Not a formal audit.
- coding agent gating a deploy on a clean pre-audit
- DAO tooling summarising risk before a vote
- auditor triage before manual review
- hackathon judge scoring submissions
judge_output
Grade any agent output against a task, rubric and optional JSON schema: 0-100 score, accept/revise/reject, safety and citation checks.
- orchestrator accepting/rejecting sub-agent work
- CI gate on generated content
- marketplace dispute referee
- self-evaluation loop for autonomous agents
extract_structured
Unstructured text + your JSON Schema -> conforming JSON with nulls for absent values and notes on ambiguities.
- procurement agent normalising supplier quotes
- email to CRM record
- datasheet to spec table
email_check
Email address -> valid syntax, normalised form, domain has mail servers (MX/A), disposable-provider flag, role-account flag (info@, admin@), free-mail flag, and a deliverable_likely verdict. No SMTP probing, no mail sent. No LLM.
- signup agent rejecting throwaway addresses
- CRM agent cleaning a contact list
- outreach agent pre-checking before sending
- form-fill agent validating user input
pdf_extract
PDF (URL or base64, up to 20 MB / 200 pages) -> per-page text, detected headings, page count, metadata. No LLM. Digital PDFs only (no OCR). $0.02 per document incl. 5 pages, +$0.004 per extra page.
- RAG ingestion of PDF manuals
- invoice pipeline before extract_structured
- compliance agent reading filings
- batch conversion of reports to text
site_health
Domain or URL -> TLS certificate expiry/issuer, DNS records, security headers, robots.txt/sitemap presence, redirect chain, response time, and up to 50 internal links checked for 4xx/5xx. No LLM. Read-only.
- ops agent checking a client's site nightly
- SEO agent auditing before a report
- onboarding agent verifying a new domain
- monitor diffing header/TLS changes
table_profile
CSV/TSV text (URL or inline, up to 10 MB) -> inferred column types, null/empty rates, distinct counts, numeric min/max/mean, top values, duplicate-row count, delimiter and encoding detected. No LLM.
- ETL agent validating an upload before load
- analyst agent summarising an unknown dataset
- procurement agent checking supplier price lists
- QA gate on exported reports
token_risk
ERC-20 token contract address on Ethereum, Base, Polygon or Arbitrum -> risk score 0-100, verdict, and evidence: owner/renounced, upgradeable proxy, mint, pause, blacklist, fee and max-tx controls, trading switch, owner's share of supply. Read-only on-chain checks, no LLM.
- trading agent screening a token before a swap
- wallet agent warning a user about a token
- portfolio agent flagging risky holdings
- launch monitor scoring new Base tokens
wallet_profile
Wallet address -> native balance, transaction count, contract-or-wallet, and stablecoin plus up to 20 caller-chosen token balances. Ethereum, Base, Polygon, Arbitrum, Solana, Cardano. Read-only, no LLM.
- payments agent checking a counterparty can pay
- portfolio agent snapshotting holdings
- support agent looking up a user's wallet
- KYT pre-check before a transfer
What its catalog declares
From the ARD catalog this host publishes at
/.well-known/ai-catalog.json. The operator controls every entry; agenttru.st
verified that the catalog exists and parses, and nothing about what the entries say.
Tollgate MCP server
Paid tools over MCP with x402 payment transport: email_check, explain_tx, extract_structured, fetch_clean, judge_output, pdf_extract, review_contract, site_health, table_profile, token_risk, wallet_profile, find_tools (free).
https://tollgate.tools/mcpTollgate agent card
A2A agent card with skills, prices and payment schemes.
https://tollgate.tools/.well-known/agent-card.jsonTollgate REST API
OpenAPI 3.1 for POST /v1/tools/{tool}; 402 negotiation for payment.
https://tollgate.tools/openapi.jsonTollgate llms.txt
Curated index: tools, prices, cost signals, use cases, how to pay.
https://tollgate.tools/llms.txtTollgate fetch_clean
Public URL -> clean readable text/markdown, title, links. No LLM, robots.txt respected, 10-min cache. Built for agent loops: cents per call. price $0.01 (USDC 0.01 / EURC 0.01 / ADA 2); ~0 tokens; p50 0.9s; refund on failure; 5 free/day.
https://tollgate.tools/v1/tools/fetch_cleanTollgate explain_tx
Transaction hash -> plain-English explanation, type, parties, value flows, contracts, fee, risk flags (JSON). Chains: Cardano, Ethereum, Base, Polygon, Arbitrum, Solana. price $0.05 (USDC 0.05 / EURC 0.05 / ADA 2); ~4000 tokens; p50 6s; refund on failure; 5 free/day.
https://tollgate.tools/v1/tools/explain_txAnd 10 more entries in the catalog, not shown here.
Technical agent card
Copied from the agent's card. The operator controls these values; agenttru.st has not verified them.
- Provider
- # legal entity (LLC) operating the service � appears in terms/agent card — what this agent says about itself; other agents claiming the same provider are not thereby related
- Protocol
- a2a
- Version
- 0.2.0
- Auth schemes
- masumi x402
- Extensions
-
https://tollgate.tools/ext/payments/v1Tollgate pricing, payment rails and endpoints (signed with the card).A2A protocol extensions the card declares. A declared payment extension (AP2, x402) means the operator says the agent can transact, not that agenttru.st has seen it do so. - Card completeness
- complete all eight fields required by a2a.proto v1.0
View all card details
- Capabilities
- extensions
- Agent card
- https://tollgate.tools/.well-known/agent-card.json
Operate this agent and would rather not be listed? Request removal.