Tethered Trust API

active

Compatibility intelligence for AI agents. Every decision is one of supported, conditional, incompatible or insufficientevidence, with evidence, the exact questions blocking a decision, and a signed receipt. Use the sandbox server while integrating: free and never charged, up to 300 calls an hour. MCP: https://tetheredtrust.com/mcp. Guide: https://tetheredtrust.com/llms.txt.

AIBasex402 v2exacttetheredtrust.com ↗︎

Settled via Coinbase.

Transactions · 30d
14
Volume · 30d
$5.82
Unique buyers · 30d
3
Uptime · 30d
100.0%
Latency p50
34ms
Reported calls · 30d
11

Endpoints (26 live)

  • POST /v1/paid/lwatch — Keep an MCP server findable: a daily launch check for 30 days (health, official MCP Registry version, Glama, x402 Bazaar, npm, PyPI, discovery files) with a signed webhook when anything changes. $3 per 30 days, renew with watch_id. $3.00 per call. Not charged for errors or "need more detail" answers. (3 USDC on Base)
  • POST /v1/paid/paycheck — Will an agent's payment to your x402 endpoint go through? One unpaid call: checks the 402 and payment request (v1/v2), the token's EIP-712 domain against the contract on-chain (the usual cause of invalid-signature payments), network, amount, payTo, timeout, CORS for browser agents, resource URL and Bazaar discovery, with exact fixes. Never pays. $0.10 per call. Not charged for errors or "need more detail" answers. (0.1 USDC on Base)
  • POST /v1/paid/verify_mcp — Is this MCP server actually working? We connect as an MCP client (initialize + tools/list), check every tool has a usable inputSchema and description, that named tools exist, and optionally run one sample call on a read-only tool. Pass / fail / couldn't-verify per check with a signed receipt. We never sign in or call tools that change things. $0.10 per call. Not charged for errors or "need more detail" answers. (0.1 USDC on Base)
  • POST /v1/paid/packet — Dispute evidence for an AI-agent purchase: given a Tethered Trust receipt_id, one printable page and JSON with the suitability decision made before buying, the products checked, sources with dates, the linked order / AP2 mandate / ACP or UCP checkout, records and recall notices that changed since, reported outcomes and Ed25519 signature verification. $1.50 per call. Not charged for errors or "need more detail" answers. (1.5 USDC on Base)
  • POST /v1/packet — Dispute evidence for an AI-agent purchase: given a Tethered Trust receipt_id, one printable page and JSON with the suitability decision made before buying, the products checked, sources with dates, the linked order / AP2 mandate / ACP or UCP checkout, records and recall notices that changed since, reported outcomes and Ed25519 signature verification. $1.50 per call. Not charged for errors or "need more detail" answers. (1.5 USDC on Base)
  • POST /v1/paid/regpub — Get an MCP server into the official MCP Registry without mcp-publisher or DNS: host one line we give you at /.well-known/mcp-registry-auth, we publish server.json under your domain namespace and re-publish every new version automatically for 90 days. $5, charged only when published. $5.00 per call. Not charged for errors or "need more detail" answers. (5 USDC on Base)
  • POST /v1/listing/watch — Keep an MCP server findable: a daily launch check for 30 days (health, official MCP Registry version, Glama, x402 Bazaar, npm, PyPI, discovery files) with a signed webhook when anything changes. $3 per 30 days, renew with watch_id. $3.00 per call. Not charged for errors or "need more detail" answers. (3 USDC on Base)
  • POST /v1/paid/launch — Is this MCP server findable by agents? Checks it works, then looks it up in the official MCP Registry (and whether the listed version is current), Glama, PulseMCP, the x402 Bazaar, npm and PyPI, plus its server card, llms.txt and robots.txt. Score, ordered fix plan and a ready-to-publish server.json. $0.25 per call. Not charged for errors or "need more detail" answers. (0.25 USDC on Base)
  • POST /v1/paid/launch-plan — Launch Plan for sellers of MCP servers and paid agent APIs: 30 days of official MCP Registry publishing on every new version, a daily listing watch (registry, Glama, x402 Bazaar, npm, PyPI, health) and daily x402 payment checks of up to 10 endpoints, one signed webhook. $12 per 30 days, renew with plan_id. $12.00 per call. Not charged for errors or "need more detail" answers. (12 USDC on Base)
  • POST /v1/paid/registry-publish — Get an MCP server into the official MCP Registry without mcp-publisher or DNS: host one line we give you at /.well-known/mcp-registry-auth, we publish server.json under your domain namespace and re-publish every new version automatically for 90 days. $5, charged only when published. $5.00 per call. Not charged for errors or "need more detail" answers. (5 USDC on Base)
  • POST /v1/paid/lplan — Launch Plan for sellers of MCP servers and paid agent APIs: 30 days of official MCP Registry publishing on every new version, a daily listing watch (registry, Glama, x402 Bazaar, npm, PyPI, health) and daily x402 payment checks of up to 10 endpoints, one signed webhook. $12 per 30 days, renew with plan_id. $12.00 per call. Not charged for errors or "need more detail" answers. (12 USDC on Base)
  • POST /v1/launch-plan — Launch Plan for sellers of MCP servers and paid agent APIs: 30 days of official MCP Registry publishing on every new version, a daily listing watch (registry, Glama, x402 Bazaar, npm, PyPI, health) and daily x402 payment checks of up to 10 endpoints, one signed webhook. $12 per 30 days, renew with plan_id. $12.00 per call. Not charged for errors or "need more detail" answers. (12 USDC on Base)
  • POST /v1/paid/verify — Independent check that a public web page actually works before an agent reports it done: it loads, given text is visible (desktop or mobile), a link or button leads to the expected address, no script errors, no broken same-site links. Pass / fail / couldn't-verify per check, a screenshot and a signed receipt. Read-only. $0.10 per call. Not charged for errors or "need more detail" answers. (0.1 USDC on Base)
  • POST /v1/paid/x402-check — Will an agent's payment to your x402 endpoint go through? One unpaid call: checks the 402 and payment request (v1/v2), the token's EIP-712 domain against the contract on-chain (the usual cause of invalid-signature payments), network, amount, payTo, timeout, CORS for browser agents, resource URL and Bazaar discovery, with exact fixes. Never pays. $0.10 per call. Not charged for errors or "need more detail" answers. (0.1 USDC on Base)
  • POST /v1/paid/recalls — Is this product or vehicle recalled? US government recall notices: CPSC consumer products by brand + model or UPC, NHTSA vehicles by year/make/model. Hazard, remedy, which units are affected and the official link; never calls a product 'safe'. $0.02 per call. Not charged for errors or "need more detail" answers. (0.02 USDC on Base)
  • POST /v1/paid/listing-watch — Keep an MCP server findable: a daily launch check for 30 days (health, official MCP Registry version, Glama, x402 Bazaar, npm, PyPI, discovery files) with a signed webhook when anything changes. $3 per 30 days, renew with watch_id. $3.00 per call. Not charged for errors or "need more detail" answers. (3 USDC on Base)
  • POST /v1/paid/verify-mcp — Is this MCP server actually working? We connect as an MCP client (initialize + tools/list), check every tool has a usable inputSchema and description, that named tools exist, and optionally run one sample call on a read-only tool. Pass / fail / couldn't-verify per check with a signed receipt. We never sign in or call tools that change things. $0.10 per call. Not charged for errors or "need more detail" answers. (0.1 USDC on Base)
  • POST /v1/checkout/check — Check a UCP / ACP agent checkout (or plain line items) right before paying: safe_to_checkout, what to resolve first (adapters, questions), per-line decisions and a signed receipt. $0.25 per call. Not charged for errors or "need more detail" answers. (0.25 USDC on Base)
  • POST /v1/fit — Will an appliance physically fit a space? Compares dimensions with installation clearances and required connections, with the margin on each side. $0.05 per call. Not charged for errors or "need more detail" answers. (0.05 USDC on Base)
  • POST /v1/parts — List the verified parts that fit a model (water and air filters, batteries, memory, SSDs, chargers, bags), with the manufacturer source for each. $0.05 per call. Not charged for errors or "need more detail" answers. (0.05 USDC on Base)

+6 more endpoints.

MCP tools (23)

Tethered Trust https://tetheredtrust.com/mcp

  • attach_order — Call this right after placing an order you checked with check_cart_before_checkout, validate_purchase_plan or check_compatibility: link the receipt_id to the order number, AP2 cart or intent mandate, ACP checkout session, UCP checkout or payment reference. This makes a Decision Record: if the purchase is ever disputed ("the agent bought the wrong thing"), anyone can show what was checked, from which sources, and what changed since. Free.
  • check_batch — Up to 25 independent compatibility checks in one call (e.g. ranking candidate products for one device). Each result has its own decision, evidence and receipt.
  • check_cart_before_checkout — Checks a cart at checkout. Takes the checkout session exactly as a commerce protocol returns it (a UCP checkout or an ACP CheckoutSession) or plain line items, plus what the customer already owns. Returns a decision per line item, safe_to_checkout, an action (proceed, resolve_conditions, do_not_checkout, ask_customer), questions, substitutions, a signed receipt, and a com.tetheredtrust.shopping.compatibility extension object to attach to the checkout.
  • check_compatibility — Call this whenever you're about to recommend, link to or buy a part, accessory, charger, filter, cartridge, lens, battery, memory, mount or adapter for something the person already owns, or they ask "will X work with Y" / "is this compatible". Pass both exact models. Covers anything that has to fit, plug in, mount, run on or charge with something someone owns (list_coverage shows the verified catalog). Returns a decision (supported / conditional / incompatible / insufficient_evidence), the rules checked, caveats, required accessories, the questions to ask when it can't decide, evidence links and a signed receipt. When the text matches several models it returns each candidate's answer.
  • check_fit — Will this appliance physically fit this space? Compares dimensions plus typical installation clearances and required connections (power, water, gas).
  • check_recalls — Call this before recommending, buying or selling anything used or secondhand, any baby or kids' product, appliance, heater, battery-powered device or vehicle, or when the person asks if something is safe or recalled. Searches US government recall notices: CPSC for consumer products (appliances, furniture, kids' products, electronics, tools; by brand and model or UPC) and NHTSA for vehicles (by year, make and model). Use before buying, selling or recommending something, especially used or secondhand. Returns decision (recalled / possible_recall / no_recall_found / insufficient_evidence) with each notice's hazard, remedy, which units it applies to and the official link. 'no_recall_found' is not a safety guarantee.
  • decision_status — Call this right before acting on a watched decision: still_holds, changed (a record it rested on was updated), recall_on_record (a recall notice names one of the products), or expired, with what changed and what isn't monitored.
  • dispute_packet — Call this when an agent purchase is disputed, returned as wrong, or charged back and a Tethered Trust receipt exists for it: we assemble the evidence (the decision, products checked, sources with dates, the linked order or mandate, records and recall notices that changed since, reported outcomes, and signature verification) into one printable page and JSON anyone can verify. For merchants, platforms and buyers. $1.50 per packet.
  • file_claim — Call this when a product we said would work didn't (within 60 days of the check): send the receipt_id and what happened. Decided within 10 business days; if our answer or data was wrong, the fee paid for that check is refunded and the data corrected. Free. For a plain fit/no-fit report without a claim, use report_outcome.
  • find_parts — Call this when the person names a device or appliance they own and needs a replacement or add-on ("what filter does my fridge take", "which RAM can I add", "what battery fits my drill") before you search shops or guess. Which parts and accessories fit this model? OEM parts first, then verified alternatives: e.g. a refrigerator's water filter, a printer's cartridges, a camera's lenses and batteries, a tool's batteries, or the RAM, SSDs and chargers that fit a computer.
  • fix_purchase_plan — When a plan comes back incompatible or conditional: the smallest set of changes that makes it work (swap a part for a verified one that fits everything else, add a missing cooler, hub or adapter, trim quantities that exceed slots), re-validated, with the reason for each change. Fewest changes and verified products first; no prices.
  • how_it_works — What Tethered Trust is, what it covers, where its data comes from, pricing and terms.
  • identify_from_photo — Read the brand, model and part numbers from a photo of a label or nameplate and match them to products. Matches are returned as candidates, with what was read. The photo isn't stored.
  • identify_product — Call this when the person gives a shop link, ASIN, barcode or vague product name and you need the exact model and what it's compatible with. Identify a product from a URL, model number, SKU, ASIN, UPC/EAN or description, and get its compatibility profile: the standards it takes and provides (mounts, sockets, connectors, platforms, part numbers, sizes), numeric limits (OS version, watts, weight, screen size), evidence and freshness. Products not in our reviewed catalog are researched on demand from the manufacturer's page and returned with status read_from_manufacturer_page (unreviewed) or unconfirmed (not enough to decide on). Use first when the product could be anything.
  • list_coverage — Which product categories and models are in the compatibility graph, with counts. Pass a category to list its models. Covers anything that has to fit, plug in, mount, run on or charge with something someone owns. Verified catalog (specs checked against cited manufacturer sources): computers & consoles (RAM, M.2 SSDs, USB-C chargers), phones/tablets/watches (USB-C PD, MagSafe, Qi2, watch bands), cameras (lens mounts, adapters, batteries, memory cards), cordless power tools (battery platforms), printers (ink, toner, drums), appliances (refrigerator water and air filters, dryer vents and power cords, installation fit), vacuums (bags, filters, batteries, robot-vacuum parts), air quality (purifier filters, HVAC media, humidifier pads), e-bikes (batteries and chargers by drive system), smart home (Matter, Thread, Zigbee, hubs, bulb bases), PC building (CPU sockets, cooler mounts, memory, clearances, power), cars & EV charging (tire sizes by trim, NACS/J1772/CCS1 and approved adapters, home ch
  • list_standards — Call this before sending products described by their specs instead of model numbers (e.g. specs_from or a custom product), or to map your own catalog fields onto ours: returns every standard family with its reviewed values (lens mounts, battery platforms, memory types, connectors, filters), the formats for new values and the numeric limit keys. Not needed for normal checks with model numbers. Free, read-only.
  • plan_upgrade — Call this when the person asks what they can upgrade or add to a device they own ("can I add more RAM to my laptop", "what SSD does my PC take", "what GPU fits my case") before suggesting parts: returns memory type, slots and maximum, M.2 slots, lengths and PCIe generation, power, CPU and cooler support for motherboards, GPU and cooler clearance for cases, the parts in our graph that fit (verified first) and the manufacturer's notes. Pass the exact model.
  • recheck_plan — Re-run a saved purchase plan against today's data before ordering, and see what changed since it was issued: decisions, product records, or receipt status.
  • report_outcome — After a purchase, report whether it actually fit. Free, safe to call, and only the first report per check counts. Reports are weighted by level: self_reported (website), agent_reported (anonymous API/MCP), partner_reported (API key holders) and order_confirmed (order evidence we've confirmed). Only the last two can raise future confidence.
  • resolve_product — Call this to confirm exactly which model the person means before checking or buying ("which Galaxy S25 is this?") or to read a product's structured specs: looks it up by name or model number and returns its specs, what it accepts (mounts, battery platforms, cartridges, protocols) and what it fits. When the text matches several models it returns them all as candidates (ambiguous: true) so you can ask the person which one. For a yes/no fit answer use check_compatibility instead.
  • validate_purchase_plan — Call this before you recommend or order two or more items that have to work together or with what the person owns (a PC build or upgrade, a camera kit, a smart-home setup, a charger plus cable). Check a whole purchase before recommending or ordering it: the setup the person owns (with current configuration) plus everything in the cart. Returns one decision (supported / conditional / incompatible / insufficient_evidence), a result per part, configuration limits across the plan (memory slots and capacity, M.2 slots), adapters or hubs still needed, substitutions for parts that won't work, the exact questions blocking a decision, evidence, and a signed receipt. Covers anything that has to fit, plug in, mount, run on or charge with something someone owns. Verified catalog (specs checked against cited manufacturer sources): computers & consoles (RAM, M.2 SSDs, USB-C chargers), phones/tablets/watches (USB-C PD, MagSafe, Qi2, watch bands), cameras (lens mounts, adapters, batteries, memory card
  • verify_receipt — Check a Tethered Trust receipt: is the signature ours, is it still within valid_until, and have the records behind it changed since? A valid receipt proves what we said and when; it doesn't guarantee the verdict was right.
  • watch_decision — Call this after a compatibility check, purchase plan, verify_page or verify_mcp result that someone will rely on later (an order next week, an install, a resale, the next agent in a handoff). For product decisions we watch the records, manufacturer sources and US recall notices behind it; for page and MCP checks we re-run the same checks daily. Watches last 30 days and need only the receipt_id. Free during early access.

First seen · last seen · last active