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.

Conduit Agentic Commerce

REMOTE · MCP.AICONDUIT.APP

Search multi-merchant supply, checkout, and track orders via MCP.

0 this week 79 Trust /100

Last scanned (12 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category E-commerce

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 Security57
Transport & Reachability100
Schema Quality & AI Usability79
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 8188 tokens (~233/item across 35 items; 25 tools + 10 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 27 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 (13)

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

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.

  • 11 Nov 26 0
    • Stability: 0.97 → pass security
  • 10 Nov 26 0
    • Stability: pass → 0.97 functional
  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 5 Nov 26 0
    • Stability: 0.97 → pass security
  • 4 Nov 26 0
    • Stability: pass → 0.97 functional
  • 13 Oct 26 0
    • Tool “supply_details” rewrote its description, which is the text the model reads security
    • Tool “supply_search” rewrote its description, which is the text the model reads security
    • Server version: 2.0.4 → 2.0.5 functional
    • “supply_details” added an optional parameter “include_description_original” cosmetic
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://mcp.aiconduit.app/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.aiconduit.app CN=YE1,O=Let's Encrypt,C=US 18 Nov 2026 16 Feb 2027 ECDSA 256 ECDSA-SHA384 66934678c6cd8df97d60cd6b85e4a69e8a4
SANs: mcp.aiconduit.app
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.aiconduit.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
aiconduit.app. 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.aiconduit.app/mcp Verified 200
http (plaintext) http://mcp.aiconduit.app/mcp HTTPS enforced 301 https://mcp.aiconduit.app/mcp
MCP tools · 25 exposed · ~5,598 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_authenticate ~170

Two-step re-auth. Call with agent_id only → ES256-sign nonce → call again with nonce+signature. Prefer keys from ~/.conduit ({handle}.credentials.json or legacy credentials.json; CONDUIT_CREDENTIALS_PATH pins one file). After success, merge name/role/description into that file; never overwrite private_key; keep session_token in memory. Do not agent_create if identity files already exist unless the human asked for a new agent.

NameTypeReqDescription
agent_idstringyesAgent id from the chosen ~/.conduit credentials file, e.g. agt_...
noncestring–Challenge nonce from the first agent_authenticate call (omit to request one)
signaturestring–Signature of the nonce with the agent private key (omit with nonce to get challenge)
NameTypeReqDescription
agent_idstring––
avatar–––
business_profile–––
challengestring––
created_atstring––
default_destination–––
destination_sourcestring––
detailstring––
effective_destination–––
errorstring––
friendly_namestring––
handlestring––
hintstring––
human_descriptionstring––
mandatesarray––
nextobject––
noncestring––
open_orders–––
organization–––
organization_idstring––
payment_railsarray––
permissionsarray––
persist–––
preferences–––
public_keystring––
reputation–––
role_descriptionstring––
terminalstring––
total_orders–––

No examples provided.

agent_create ~465

Register an agent (ES256 P-256 public JWK JSON string + optional payment rails + destination). BEFORE: list ~/.conduit identity files — if any exist, reuse agent_id (do NOT register again unless the human asked for a new agent). AFTER: write persist.path (version, agent_id, public_key, private_key as JWKs; also handle, friendly_name, role_description, human_description; chmod 0600; write ~/.conduit/active). Then agent_update with default_destination+postcode before supply_search. Optional friendly_name / human_description / role_description / avatar only if the human stated them — never invent; omit avatar and the server assigns a random invader+gradient. Omit handle to auto-generate (e.g. parcel-watcher-12).

NameTypeReqDescription
avatar––Identity mark. Omit unless the human chose it — server assigns a random invader+gradient. { kind:"glyph", glyph:"invader"|emoji, tint?:invader color, gradient } or { kind:"image", src }. Tint only fo…
business_profile––Optional business profile metadata object
default_destinationobject–Where orders ship. postcode + country is enough for supply_search and delivery estimates; add address, locality and region so checkout links arrive prefilled.
friendly_namestring–Human-facing label (≠ handle), e.g. EU Restock Bot
handlestring–Optional display handle (lowercase kebab); omit to auto-generate e.g. parcel-watcher-12
human_descriptionstring–Description shown to humans on the org dashboard
payment_railsarray–Optional rail keys to seed, e.g. ["x402"]
preferences––Optional agent preference bag
public_keystringyesES256 P-256 public JWK as a JSON string (kty=EC, crv=P-256, x, y). Not PEM, hex, or base64url-wrapped JSON. Keep the matching private JWK only in ~/.conduit/{handle}.credentials.json.
role_descriptionstring–Self-instruction for this agent only, e.g. manage EU supplies
NameTypeReqDescription
agent_idstring––
avatar–––
business_profile–––
challengestring––
created_atstring––
default_destination–––
destination_sourcestring––
detailstring––
effective_destination–––
errorstring––
friendly_namestring––
handlestring––
hintstring––
human_descriptionstring––
mandatesarray––
nextobject––
noncestring––
open_orders–––
organization–––
organization_idstring––
payment_railsarray––
permissionsarray––
persist–––
preferences–––
public_keystring––
reputation–––
role_descriptionstring––
terminalstring––
total_orders–––

No examples provided.

agent_notify ~304

Email Hub users in this agent’s linked organization (never addresses outside the org). to=all or { user_id } / { role } / { email } matching agent_organization members. Optional actions (Hub URLs only), severity, idempotency_key. Channel is email.

NameTypeReqDescription
actionsarray–Optional buttons, max 3. Hosts outside Conduit are rejected.
agent_idstringyesLinked agent sending the message
bodystringyesPlain-text body, max 4000 characters. Conduit wraps HTML; do not send markup.
channelstring–Delivery channel. Email only — omit or pass email
dry_runboolean–If true, resolve recipients and from-address without sending or storing
idempotency_keystring–Replay key — same agent + key returns the original notify_id without sending again
order_idstring–Optional order correlation
search_idstring–Optional search correlation
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
severitystring–info (default), warning, or urgent — affects subject prefix and accent
titlestringyesSubject line, max 120 characters
to–yesWho to notify: "all", { user_id }, { user_ids }, { role }, { roles }, or { email } matching an org member. Never an address outside the org.
NameTypeReqDescription
channelstring––
deliverednumber––
detailstring––
dry_runboolean––
errorstring––
failednumber––
fromstring––
hintstring––
idempotent_replayboolean––
nextobject––
notify_idstring––
recipientsarray––

No examples provided.

agent_organization ~99

Read the linked organization (name, slug, country, default address) and members (user_id, name, role, email) for an agent. Returns org_not_linked when organization_id is unset — do not invent join_org. Use members to target agent_notify.

NameTypeReqDescription
agent_idstringyesAgent id whose linked organization to read
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
connectorsarray––
detailstring––
errorstring––
hintstring––
membersarray––
nextobject––
organization–––

No examples provided.

agent_outreach ~313

Email outside addresses (suppliers, carriers). to is a string email, { email }, or { emails } (max 5). Not to=all and not a Hub user_id / role — those are agent_notify. Linked agents set Reply-To to an org member (default OWNER). No action buttons. Channel is email.

NameTypeReqDescription
agent_idstringyesAuthenticated agent sending the note
bodystringyesPlain-text body, max 4000 characters. URLs stay escaped text, not buttons.
channelstring–Delivery channel. Email only — omit or pass email
dry_runboolean–If true, resolve recipients and from-address without sending or storing
idempotency_keystring–Replay key — same agent + key returns the original outreach_id without sending again
order_idstring–Optional order correlation
reply_to––Linked only: who receives replies. { email } or { role } matching a member. Omit to default to the OWNER. Unlinked agents have no Reply-To.
search_idstring–Optional search correlation
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
titlestringyesSubject line, max 120 characters
to–yesOutside address(es): a string email, { email }, or { emails } (max 5). Not to=all and not a Hub user_id / role — those are agent_notify.
NameTypeReqDescription
channelstring––
deliverednumber––
detailstring––
dry_runboolean––
errorstring––
failednumber––
fromstring––
hintstring––
idempotent_replayboolean––
nextobject––
outreach_idstring––
recipientsarray––
reply_tostring––

No examples provided.

agent_report_issue ~339

Report unexpected tool errors or confusing Conduit outcomes for AX review (agent_report_issue — not order_feedback). Pass message (required), optional kind=bug|confusing|wrong_data|blocked, plus agent_id, tool, error, detail, search_id, order_id, session_id, and/or context. Dedupes open reports with the same tool+error+correlation. Does not change reputation.

NameTypeReqDescription
agent_idstring–Agent id from credentials when available (omit placeholders like "agent_id")
contextobject–Optional structured extras (args summary, badge, etc.). Secrets are stripped.
detailstring–Optional longer detail (response excerpt, unexpected field). Do not include private_key.
errorstring–Error code from the prior tool response when present, e.g. offer_not_in_cache
kindstring–Triage kind (default confusing): bug | confusing | wrong_data | blocked
messagestringyesRequired: what went wrong or what confused you (expected vs actual). Keep actionable. This is agent_report_issue — not order_feedback.
order_idstring–order_id for correlation when the issue is order-related
search_idstring–search_id for correlation when the issue is search-related
session_idstring–Optional session id; Conduit also picks up x-conduit-session-id from the transport
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
toolstring–MCP tool that failed or confused you, e.g. supply_search or order_execute
NameTypeReqDescription
agent_idstring––
already_openboolean––
detailstring––
errorstring––
hintstring––
kindstring––
nextobject––
report_idstring––
reported_errorstring––
session_idstring––
statusstring––
toolstring––

No examples provided.

agent_update ~316

Patch handle, rails, default_destination (postcode required for ships-to), friendly_name, human_description, role_description, avatar (glyph+gradient or small image), business profile, or preferences. Set avatar only if the human chose it. Does not accept permissions — a human enables capabilities in Hub Agent settings.

NameTypeReqDescription
agent_idstringyesAgent id to patch, e.g. agt_...
avatar––Identity mark. Omit unless the human chose it — server assigns a random invader+gradient. { kind:"glyph", glyph:"invader"|emoji, tint?:invader color, gradient } or { kind:"image", src }. Tint only fo…
business_profile––Business profile patch
default_destinationobject–Where orders ship. postcode + country is enough for accurate search; add address, locality and region so checkout links arrive prefilled instead of blank.
friendly_namestring–Human-facing label (≠ handle), e.g. EU Restock Bot
handlestring–New display handle (lowercase kebab)
human_descriptionstring–Description shown to humans on the org dashboard
payment_railsarray–Replacement rail key list
preferences––Preferences patch
role_descriptionstring–Self-instruction for this agent only, e.g. manage EU supplies
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
agent_idstring––
avatar–––
business_profile–––
challengestring––
created_atstring––
default_destination–––
destination_sourcestring––
detailstring––
effective_destination–––
errorstring––
friendly_namestring––
handlestring––
hintstring––
human_descriptionstring––
mandatesarray––
nextobject––
noncestring––
open_orders–––
organization–––
organization_idstring––
payment_railsarray––
permissionsarray––
persist–––
preferences–––
public_keystring––
reputation–––
role_descriptionstring––
terminalstring––
total_orders–––

No examples provided.

inventory_levels ~209

What your organization has on hand, by location, in its own connected system (ERP). Pass skus or query. Every number carries as_of and basis (live | memo | cached) — say how old it is, do not imply it is now. Needs inventory permission. This is your OWN stock; a supplier's stock is supply_availability.

NameTypeReqDescription
agent_idstringyesAgent id; its organization owns the connected system
connection_idstring–Which connected system, when the org has several
freshboolean–Ask the system now instead of reading the last value (slower, rate limited)
querystring–Free-text item search in your own system, e.g. "carton"
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
skusarray–Item codes in your own system, e.g. ["CART-6040"]. Pass skus or query
NameTypeReqDescription
as_ofstring––
availabilityarray––
basisstring––
connection_idstring––
connectionsarray––
could_not_reachstring––
detailstring––
errorstring––
freshnessstring––
hintstring––
nextobject––
systemstring––

No examples provided.

inventory_purchase_order ~168

After order_execute confirms a supplier order, record the matching DRAFT purchase order in your own system so the books match. Always a draft: a person confirms it there. Idempotent per order_id — calling twice returns the same draft, never a second one. Needs both inventory and checkout permission. Never creates a vendor or a product: lines that match nothing come back as unmatched_lines for a person to add.

NameTypeReqDescription
agent_idstringyesAgent id; needs both inventory and checkout permission
connection_idstring–Which connected system, when the org has several
order_idstringyesConduit order id of a supplier order already placed with order_execute
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
currencystring––
detailstring––
draftboolean––
errorstring––
external_namestring––
hintstring––
nextobject––
order_idstring––
quantitynumber––
replayedboolean––
supplier_orderstring––
totalnumber––
unit–––
unmatched_linesnumber––
vendorstring––

No examples provided.

inventory_replenishment ~174

Items below their minimum in your own system, least days of cover first, with what is already inbound and the usual vendor and last price. Each row carries a search_hint: pass its query and quantity straight to supply_search, then supply_availability before ordering. Optional location scopes to one warehouse. Needs inventory permission.

NameTypeReqDescription
agent_idstringyesAgent id; its organization owns the connected system
connection_idstring–Which connected system, when the org has several
freshboolean–Ask the system now instead of reading the last value
locationstring–Warehouse or store name to scope the worklist, e.g. "Jebel Ali". Omit for all
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
as_ofstring––
basisstring––
connection_idstring––
connectionsarray––
could_not_reachstring––
detailstring––
errorstring––
freshnessstring––
hintstring––
nextobject––
next_to_watch–––
provenance–––
rowsarray––
systemstring––
window–––

No examples provided.

inventory_suppliers ~122

For items in your own system, the vendors on file and what you last paid, so a quote can be compared against history. Needs inventory permission. Does not contact any vendor.

NameTypeReqDescription
agent_idstringyesAgent id; its organization owns the connected system
connection_idstring–Which connected system, when the org has several
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
skusarrayyesItem codes in your own system whose usual vendors and last prices to read
NameTypeReqDescription
as_ofstring––
basisstring––
connection_idstring––
connectionsarray––
detailstring––
errorstring––
freshnessstring––
hintstring––
nextobject––
suppliersarray––
systemstring––

No examples provided.

order_dispute ~80

Refund/chargeback/report paths for an order. Requires owning agent_id.

NameTypeReqDescription
agent_idstringyesOwning agent id (required for authorization)
order_idstringyesOrder id to resolve refund/chargeback/report paths for
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
chargeback–––
detailstring––
errorstring––
hintstring––
nextobject––
order_idstring––
refund–––
report_to_conduit–––

No examples provided.

order_events ~76

Lifecycle timeline — transitions only. Pair with order_track. Requires owning agent_id.

NameTypeReqDescription
agent_idstringyesOwning agent id (required for authorization)
order_idstringyesOrder id whose lifecycle events to list
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
detailstring––
errorstring––
eventsarray––
hintstring––
nextobject––
order_idstring––

No examples provided.

order_execute ~323

Handoff or autonomous checkout. Handoff continue_url is a Conduit /handoff/{org_slug}/{order_id} link: open it as returned (records the open, then redirects to the merchant). Autonomous needs badge payable_now (covering mandate fits). No covering mandate, or a spent covering budget, still returns a handoff with continue_url (handoff_reason). Use idempotency_key. Prefer supply_delivery when only comparing delivery.

NameTypeReqDescription
agent_idstringyesOwning agent id
carrierstring–The shipping rate to buy, as the option's own `title` from supply_delivery. Conduit selects it on the merchant checkout, so the buyer opens the page on that rate instead of the merchant's default, wh…
idempotency_keystring–Client idempotency key — reuse to safely retry the same execute
pay_withstring–Rail key to pay with when multiple are enabled
payment_term_idstring–Payment term id from supply_details payment_terms[] (e.g. net 30). Omit to pay immediately
quantityinteger–Units to buy (default 1)
search_idstring–search_id from supply_search for correlation
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
supply_idstringyesOffer supply id to purchase
NameTypeReqDescription
address_statusstring––
bill_breakdown–––
bill_total–––
continue_urlstring––
created_atstring––
detailstring––
errorstring––
external_checkout_idstring––
handoff_endpointstring––
handoff_qualitystring––
hintstring––
idempotent_replayboolean––
nextobject––
notestring––
order_idstring––
pay_withstring––
product–––
purchase_draft–––
quantitynumber––
rail_keystring––
shipping_optionstring––
shipping_selectedboolean––
shortfall–––
simulatedboolean––
statusstring––
supplier–––
supplier_order–––
supply_idstring––

No examples provided.

order_feedback ~234

Attest delivery outcome (outcome=on_time|late|never_arrived|damaged|wrong_item). Requires owning agent_id. Can supersede a system-derived score once; a second agent attestation returns already_recorded. Poor outcomes next→order_dispute. Omit quality/carrier_rating if unknown.

NameTypeReqDescription
agent_idstringyesOwning agent id (required for authorization)
carrier_ratingnumber–Carrier rating 1-5 — omit if unknown; used in reputation when provided
notesstring–Free-text delivery/quality notes
order_idstringyesOrder id to attest
outcomestringyesObserved fulfillment outcome. Sets status (on_time/late→DELIVERED, damaged/wrong_item→DISPUTED, never_arrived→FAILED) and reputation.
qualitynumber–Product quality 1-5 — omit if unknown (do not invent)
search_idstring–Optional search_id for analytics correlation
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
already_recordedboolean––
detailstring––
errorstring––
hintstring––
nextobject––
okboolean––
order_idstring––
outcome–––
statusstring––
supersededboolean––
updated–––

No examples provided.

order_list ~133

List orders for an agent ({ orders }). Optional status or open_only filter.

NameTypeReqDescription
agent_idstringyesOwning agent id whose orders to list
open_onlyboolean–If true, only in-flight orders (PENDING, CONFIRMED, IN_TRANSIT). Ignored when status is set.
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
statusstring–Optional status filter: PENDING, CONFIRMED, IN_TRANSIT, DELIVERED, ABANDONED (or CANCELLED), FAILED, DISPUTED
NameTypeReqDescription
detailstring––
errorstring––
hintstring––
nextobject––
ordersarray––

No examples provided.

order_track ~74

Honest deal-type-aware status (never fabricates carrier scans). Requires owning agent_id.

NameTypeReqDescription
agent_idstringyesOwning agent id (required for authorization)
order_idstringyesOrder id to track
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
address_statusstring––
agent_status_lockedboolean––
carrierstring––
checkout_idstring––
continue_urlstring––
detailstring––
errorstring––
handoff_expires_atstring––
hintstring––
merchant_observed–––
nextobject––
order_idstring––
product–––
purchase_draft–––
recovery–––
statusstring––
status_sourcestring––
supplier_order–––
trackableboolean––
trackingstring––
tracking_idstring––
tracking_sourcestring––

No examples provided.

order_update_status ~225

Agent manual correction or degraded handoff recovery. note required except cancelled. Owning agent_id required.

NameTypeReqDescription
agent_idstringyesOwning agent id (required for authorization)
carrierstring–Carrier name when attaching tracking
external_checkout_idstring–Merchant checkout id to recover degraded handoff polling
handoff_endpointstring–Merchant handoff/status endpoint URL for poll recovery
notestring–Required note except when status=CANCELLED
order_idstringyesOrder id to update
search_idstring–Optional search_id for analytics correlation
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
statusstringyesNew status, e.g. PENDING, CONFIRMED, SHIPPED, DELIVERED, CANCELLED
tracking_idstring–Carrier tracking id when recovering handoff
tracking_urlstring–Carrier's public tracking page for tracking_id, when you have it. Never invent one.
NameTypeReqDescription
agent_status_lockedboolean––
carrierstring––
continue_urlstring––
detailstring––
errorstring––
external_checkout_idstring––
handoff_endpointstring––
hintstring––
merchant_observed–––
nextobject––
order_idstring––
quantitynumber––
statusstring––
tracking_idstring––

No examples provided.

payment_mandate ~257

AP2 spend mandates. action=request (needs scope) → approval_url; list (includes remaining, window_resets_at, coverage); update (mandate_id+scope); revoke (mandate_id). update NEVER approves. Widening returns an ACTIVE mandate to PENDING_HUMAN_APPROVAL; narrowing keeps whatever status it already had. monthly_cap is a rolling 30-day window from create. Same category set as a live mandate replaces it at approval and keeps this period's spend. No covering mandate at checkout is handoff, not an error.

NameTypeReqDescription
actionstringyesrequest = create mandate (needs scope); list = enumerate; update = change scope (needs mandate_id+scope); revoke = revoke (needs mandate_id)
agent_idstringyesOwning agent id
expiresstring–Optional ISO-8601 expiry, e.g. 2026-12-31T00:00:00Z
mandate_idstring–Mandate id required for update/revoke
scopeobject–Spend limits — required for action=request and action=update
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
appliedstring––
approval_urlstring––
detailstring––
errorstring––
hintstring––
mandate_idstring––
mandatesarray––
nextobject––
statusstring––

No examples provided.

payment_methods ~129

List or enable agent payment methods (action=list|enable) with friendly labels. Defaults: cod + x402. invoice (B2B) is coming_soon. bank_card is handoff-only.

NameTypeReqDescription
actionstringyeslist = enumerate rails; enable = turn on one rail
agent_idstringyesAgent id whose methods to list or enable
railstring–Rail key required when action=enable, e.g. x402 (not bank_card vault)
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
approval_urlstring––
detailstring––
errorstring––
hintstring––
labelstring––
methodsarray––
nextobject––
rail_keystring––
statusstring––

No examples provided.

supply_availability ~246

Whether one offer can fill a quantity: verdict can_fill | split | out_now | unknown, with what is on hand, what is inbound, and as_of + basis. Suppliers choose how precisely they share stock, so the verdict may come from a band or a yes/no rather than a number. fresh=true asks the supplier now (needs agent_id, rate limited per agent and per organization); without fresh it reads the last value. Call this before order_execute on any connector offer.

NameTypeReqDescription
agent_idstring–Agent id. Required for fresh, and it is what reveals your negotiated prices
freshboolean–Ask the supplier now rather than reading the last value. Needs agent_id, and is rate limited per agent and per organization
quantityinteger–Quantity to fill (default 1)
quoteboolean–Also return the supplier's exact total with tax for this quantity, computed without saving anything. Needs agent_id and an account with the supplier
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
supply_idstringyesOffer supply id from supply_search / supply_details
NameTypeReqDescription
as_ofstring––
basisstring––
could_not_reachstring––
detailstring––
errorstring––
fresh_refusedboolean––
freshnessstring––
hintstring––
incoming–––
kindstring––
link_statestring––
locations–––
nextobject––
quantitynumber––
quote–––
quote_errorstring––
stock–––
supply_idstring––
unit–––
verdict–––

No examples provided.

supply_delivery ~272

Non-committing checkout probe for shipping ETA/cost. Uses agent default_destination, else linked org default address, or country override. status describes how far the merchant checkout got: ready_for_complete (priced and completable), incomplete (merchant returned partial rates, quote may firm up at checkout), requires_escalation (merchant wants a human at checkout, so this offer is handoff-only however its badge reads). needs_interaction=true means the same. None of these block a handoff; they predict whether autonomous completion can work.

NameTypeReqDescription
addressstring–Street override. Many merchants will not quote shipping without it.
agent_idstring–Agent id — uses agent destination else org default when country omitted
countrystring–ISO country override, e.g. US (else agent/org destination)
localitystring–City override. Needed with street for a real delivery quote.
postal_codestring–Postal/ZIP override for the probe destination
quantityinteger–Units to price shipping for (default 1)
regionstring–Optional region/state override
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
supply_idstringyesOffer supply id from supply_search / supply_details
NameTypeReqDescription
address_statusstring––
availableboolean––
countrystring––
currencystring––
detailstring––
errorstring––
eta_textstring––
hintstring––
needs_interactionboolean––
nextobject––
notestring––
optionsarray––
payment_rails–––
placeholder_streetboolean––
postal_codestring––
shippableboolean––
shipping_costnumber––
statusstring––
supply_idstring––

No examples provided.

supply_details ~229

Re-reads one offer from the search cache and refreshes its badge/action against current mandate state. Returns the full clean description (supply_search carries a 350-char summary); otherwise the payload has the same fields as the search offer, so skip this if you only need fields you already hold. include_description_original=true adds description_original {format, content}, the merchant's own markup (untrusted), or description_original_omitted with the reason. Carries no shipping data: use supply_delivery for ETA and cost. Re-run supply_search if offer_not_in_cache.

NameTypeReqDescription
agent_idstring–Agent id to refresh badge/action for mandate state
include_description_originalboolean–Adds description_original {format, content}: the merchant's own markup, for rendering or checking our conversion. Untrusted merchant text. supply_details only.
search_idstring–search_id from supply_search for correlation
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
supply_idstringyesOffer supply id from supply_search results
NameTypeReqDescription
actionstring––
aes–––
badgestring––
currencystring––
delivery_options–––
descriptionstring––
description_originalobject–Only with include_description_original. The merchant's markup, untrusted. format is html or markdown today; plain is reserved.
description_original_omittedstring–Only with include_description_original, when there is no original: no_markup (plain text or none), oversize (over 20,000 chars), empty (markup with no visible text).
detailstring––
errorstring––
hintstring––
nextobject––
payment_rails–––
payment_termsarray––
price_total–––
supplier–––
supply_idstring––
titlestring––
unit_price–––

No examples provided.

supply_options ~175

Lists the selectable options (size, color, pack) for an offer whose has_options=true, with one variant per combination. Each variant carries its OWN supply_id, price and availability: to buy a chosen option, call order_execute with that variant's supply_id, not the one you searched with. Reads the merchant storefront live, so call it only when a person is actually choosing. Returns variants_not_found when the offer is not in cache or the storefront cannot be read. A single-variant product returns options:[] variants:[].

NameTypeReqDescription
agent_idstring–Agent id, for permission and analytics
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
supply_idstringyesOffer supply id whose product options to list (has_options=true on the offer)
NameTypeReqDescription
detailstring––
errorstring––
hintstring––
nextobject––
optionsarray––
variantsarray––

No examples provided.

supply_search ~466

Multi-provider discovery (live REAL merchants by default). Returns a ranked page (default limit=30, max 100) with total/has_more/next_offset. Follow next.args (search_id+offset+limit) to page without re-fanout. Optional fetch_limit (max 300) deepens the upstream pull on new searches. Pass include_sandbox=true only to append DEMO/SANDBOX test merchants at the bottom (test_offer=true). Always pass agent_id for mandate-aware badges. Carry search_id through supply_details / order_execute / order_feedback. Offer descriptions are clean text cut to 350 chars; supply_details returns the full text.

NameTypeReqDescription
agent_idstring–Agent id for mandate-aware badges (always pass when available)
budget––Max total budget — number means USD; or { amount, currency }
countrystring–ISO country for ships-to, e.g. US
fetch_limitinteger–Optional override for per-merchant upstream pull (default max(20, limit*2), max 300). Ignored when paging via search_id+offset
include_sandboxboolean–Include DEMO/SANDBOX merchants (listed last, test_offer=true). Default false — live REAL merchants only. Use only when testing Conduit checkout flows.
limitinteger–Page size of ranked offers to return (default 30, max 100)
offsetinteger–0-based offset into the ranked set for this search_id (default 0). For page 2+, pass search_id from the prior response and follow next.args
payable_witharray–Filter to rails the agent can pay with, e.g. ["x402"]
quantityinteger–Desired quantity (default 1)
querystring–Product search query, e.g. USB-C charger 65W. Required for a new search; omit when paging with search_id + offset
search_idstring–Resume paging into a prior ranked set (with offset>0, or offset 0 without query). New searches with query mint a fresh search_id
session_tokenstring–Session token from agent_authenticate — required whenever agent_id is passed
NameTypeReqDescription
badge_counts–––
countrystring––
country_default–––
degradedboolean––
detailstring––
errorstring––
has_moreboolean––
hintstring––
include_sandboxboolean––
limitnumber––
nextobject––
next_offset–––
offersarray––
offsetnumber––
partial–––
recommended–––
sandbox_includednumber––
search_idstring––
totalnumber––
withheldarray––

No examples provided.

Install

How do I install the Conduit Agentic Commerce MCP server?

Conduit Agentic Commerce is a hosted endpoint at https://mcp.aiconduit.app/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 · mcp.aiconduit.app

# add to Claude Code
claude mcp add --transport http app-aiconduit-conduit 'https://mcp.aiconduit.app/mcp'
Common questions

What is the Conduit Agentic Commerce MCP server?

Conduit Agentic Commerce is an MCP server listed in the public MCP registry as app.aiconduit/conduit. Search multi-merchant supply, checkout, and track orders via MCP. This page covers its hosted endpoint (https://mcp.aiconduit.app/mcp).

Is the Conduit Agentic Commerce MCP server safe to use?

Conduit Agentic Commerce scores 79 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 Conduit Agentic Commerce MCP server expose?

Conduit Agentic Commerce exposes 25 tools: agent_create, agent_authenticate, agent_update, agent_organization, agent_notify, and 20 more. Their descriptions and schemas cost roughly 5,598 tokens of context every time the server is loaded.

Does the Conduit Agentic Commerce MCP server require authentication?

No. We connected to Conduit Agentic Commerce without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Conduit Agentic Commerce MCP server still maintained?

Conduit Agentic Commerce 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 Conduit Agentic Commerce MCP server?

VerifyMCP ran 13 checks on Conduit Agentic Commerce, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.