Conduit Agentic Commerce MCP server
app.aiconduit/conduitaiconduit.appstreamable-httpv2.0.0Scanned
Search multi-merchant supply, checkout, and track orders via MCP.
25 tools: 1 can delete or cancel things, 4 do something that can't be undone, 16 change things and 4 only read.
- Reads private data · 1
- Reads text others write · 22
- Can send data out · 4
- 9 findings, 2 high
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 4 do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Conduit Agentic Commerce MCP server can do
The Conduit Agentic Commerce MCP server is published by aiconduit.app, a domain the MCP Registry verified. It has 25 tools. It can delete or cancel things (1 tool: payment_mandate), do things that cannot be undone, such as sending, paying or publishing (agent_notify, agent_outreach, order_dispute and inventory_purchase_order) and create or change data (16 tools: agent_create, agent_authenticate, agent_update, agent_report_issue and 12 more). 4 tools only read.
1 tool reads private data (agent_organization); 22 tools bring in text other people can write (agent_create, agent_update, agent_organization and 19 more); 4 tools can send data out of your system (agent_create, agent_update, agent_notify and 1 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 9 findings, 2 of them high severity (sensitive-path, credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 2.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
25 tools
Deletes or cancels 1Claude Code: deny
payment_mandateAP2 spend mandates.Reads text others writeNo findings
Why it is in this group
- The name "payment_mandate" says "payment": a word that usually means money moves, which cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Can't be undone 4Claude Code: ask
agent_notifyEmail Hub users in this agent’s linked organization (never addresses outside the org).Can send data outNo findings
Why it is in this group
- The name "agent_notify" says "notify": a word for sending, and what is sent cannot be taken back.
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- outboundThe name "agent_notify" says "notify": it sends or publishes something to other people.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
agent_outreachEmail outside addresses (suppliers, carriers).Reads text others writeCan send data outNo findings
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
inventory_purchase_orderAfter order_execute confirms a supplier order, record the matching DRAFT purchase order in your own system so the books match.Reads text others writeNo findings
Why it is in this group
- The name "inventory_purchase_order" says "purchase": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
order_disputeRefund/chargeback/report paths for an order.Reads text others write1 finding
Why it is in this group
- The description's first verb is "refund": a word that usually means money moves, which cannot be taken back.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "order_dispute" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "refund": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Refund/chargeback/report paths for an order. Requires owning agent_id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 16Claude Code: ask
agent_authenticateTwo-step re-auth.3 findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- High
The description refers to ".credentials.json".
What this check looks forMatched text
description: "...e. Prefer keys from ~/.conduit ({handle}.credentials.json or legacy credentials.json; CONDUIT_CRE..."
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...it ({handle}.credentials.json or legacy credentials.json; CONDUIT_CREDENTIALS_PATH pins one..."
- Info
The input schema at properties.agent_id.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent id from the chosen ~/.conduit credentials file, e.g. agt_..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
agent_createRegister an agent (ES256 P-256 public JWK JSON string + optional payment rails + destination).Reads text others writeCan send data out2 findings
Why it is in this group
- The name "agent_create" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.default_destination.phone): what the tool writes goes there.
Findings
- High
The input schema at properties.public_key.description refers to ".credentials.json".
What this check looks forMatched text
inputSchema.properties.public_key.description: "...private JWK only in ~/.conduit/{handle}.credentials.json."
- Info
The input schema at properties.avatar.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.avatar.description: "...t only for invader. Do not store in the credentials file."
Description, as the server wrote it 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).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
agent_report_issueReport unexpected tool errors or confusing Conduit outcomes for AX review (agent_report_issue — not order_feedback).1 finding
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Findings
- Info
The input schema at properties.agent_id.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent id from credentials when available (omit placeholders like..."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
agent_updatePatch handle, rails, default_destination (postcode required for ships-to), friendly_name, human_description, role_description, avatar (glyph+gradient or small image), business prof…Reads text others writeCan send data out1 finding
Why it is in this group
- The name "agent_update" says "update": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.default_destination.phone): what the tool writes goes there.
Findings
- Info
The input schema at properties.avatar.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.avatar.description: "...t only for invader. Do not store in the credentials file."
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
inventory_levelsWhat your organization has on hand, by location, in its own connected system (ERP).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
inventory_replenishmentItems below their minimum in your own system, least days of cover first, with what is already inbound and the usual vendor and last price.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
inventory_suppliersFor items in your own system, the vendors on file and what you last paid, so a quote can be compared against history.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
order_eventsLifecycle timeline — transitions only.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Lifecycle timeline — transitions only. Pair with order_track. Requires owning agent_id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
order_executeHandoff or autonomous checkout.Reads text others writeNo findings
Why it is in this group
- The name "order_execute" says "execute": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
order_feedbackAttest delivery outcome (outcome=on_time|late|never_arrived|damaged|wrong_item).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
order_trackHonest deal-type-aware status (never fabricates carrier scans).Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Honest deal-type-aware status (never fabricates carrier scans). Requires owning agent_id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
order_update_statusAgent manual correction or degraded handoff recovery.Reads text others writeNo findings
Why it is in this group
- The name "order_update_status" says "update": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Agent manual correction or degraded handoff recovery. note required except cancelled. Owning agent_id required.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
payment_methodsList or enable agent payment methods (action=list|enable) with friendly labels.Reads text others write1 finding
Why it is in this group
- The description's first verb is "list": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "payment_methods" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "list": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
supply_availabilityWhether 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.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
supply_deliveryNon-committing checkout probe for shipping ETA/cost.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
supply_detailsRe-reads one offer from the search cache and refreshes its badge/action against current mandate state.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 4Show 4 read-only tools
agent_organizationRead the linked organization (name, slug, country, default address) and members (user_id, name, role, email) for an agent.Reads private dataReads text others writeNo findings
Why it is in this group
- The description's first verb is "read": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "email": it reads mail.
- untrusted-inputThe description's first sentence says "read" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
order_listList orders for an agent ({ orders }).Reads text others writeNo findings
Why it is in this group
- The name "order_list" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List orders for an agent ({ orders }). Optional status or open_only filter.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
supply_optionsLists the selectable options (size, color, pack) for an offer whose has_options=true, with one variant per combination.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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:[].
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
supply_searchMulti-provider discovery (live REAL merchants by default).Reads text others writeNo findings
Why it is in this group
- The name "supply_search" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
88 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write22
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__conduit__agent_organization"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:28 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 21
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 21 tools that change things (1 destructive, 4 irreversible, 16 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.aiconduit.app/mcp: tools/list returned 25 tools to an anonymous client, including payment_mandate (destructive), agent_notify (irreversible), agent_outreach (irreversible), order_dispute (irreversible), inventory_purchase_order (irreversible) and 16 more
Findings
Matches of fixed checks, with the text they matched.
- Highagent_create
The input schema at properties.public_key.description refers to ".credentials.json".
What this check looks forMatched text
inputSchema.properties.public_key.description: "...private JWK only in ~/.conduit/{handle}.credentials.json."
The description refers to ".credentials.json".
What this check looks forMatched text
description: "...e. Prefer keys from ~/.conduit ({handle}.credentials.json or legacy credentials.json; CONDUIT_CRE..."
- Warnpayment_methods
The server marks "payment_methods" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "list": a word for reading.
- Warnorder_dispute
The server marks "order_dispute" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "refund": a word that usually means money moves, which cannot be taken back.
- Infoagent_create
The input schema at properties.avatar.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.avatar.description: "...t only for invader. Do not store in the credentials file."
The description mentions "credentials".
What this check looks forMatched text
description: "...it ({handle}.credentials.json or legacy credentials.json; CONDUIT_CREDENTIALS_PATH pins one..."
Show 3 more findingsShow fewer
The input schema at properties.agent_id.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent id from the chosen ~/.conduit credentials file, e.g. agt_..."
- Infoagent_update
The input schema at properties.avatar.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.avatar.description: "...t only for invader. Do not store in the credentials file."
The input schema at properties.agent_id.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.agent_id.description: "Agent id from credentials when available (omit placeholders like..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http conduit https://mcp.aiconduit.app/mcpclaude mcp add --transport http conduit https://mcp.aiconduit.app/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__conduit__agent_organization",
"mcp__conduit__supply_search",
"mcp__conduit__supply_options",
"mcp__conduit__order_list"
],
"ask": [
"mcp__conduit__agent_create",
"mcp__conduit__agent_authenticate",
"mcp__conduit__agent_update",
"mcp__conduit__agent_notify",
"mcp__conduit__agent_outreach",
"mcp__conduit__agent_report_issue",
"mcp__conduit__payment_methods",
"mcp__conduit__supply_details",
"mcp__conduit__supply_delivery",
"mcp__conduit__order_execute",
"mcp__conduit__order_track",
"mcp__conduit__order_events",
"mcp__conduit__order_update_status",
"mcp__conduit__order_dispute",
"mcp__conduit__order_feedback",
"mcp__conduit__inventory_levels",
"mcp__conduit__inventory_replenishment",
"mcp__conduit__inventory_suppliers",
"mcp__conduit__supply_availability",
"mcp__conduit__inventory_purchase_order"
],
"deny": [
"mcp__conduit__payment_mandate"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as conduit. Review it before you use it.
Capability tags behind 23 rules
- mcp__conduit__agent_create untrusted-input, outbound
- mcp__conduit__agent_update untrusted-input, outbound
- mcp__conduit__agent_organization private-data, untrusted-input
- mcp__conduit__agent_notify outbound
- mcp__conduit__agent_outreach untrusted-input, outbound
- mcp__conduit__payment_methods untrusted-input
- mcp__conduit__payment_mandate untrusted-input
- mcp__conduit__supply_search untrusted-input
- mcp__conduit__supply_details untrusted-input
- mcp__conduit__supply_options untrusted-input
- mcp__conduit__supply_delivery untrusted-input
- mcp__conduit__order_execute untrusted-input
- mcp__conduit__order_list untrusted-input
- mcp__conduit__order_track untrusted-input
- mcp__conduit__order_events untrusted-input
- mcp__conduit__order_update_status untrusted-input
- mcp__conduit__order_dispute untrusted-input
- mcp__conduit__order_feedback untrusted-input
- mcp__conduit__inventory_levels untrusted-input
- mcp__conduit__inventory_replenishment untrusted-input
- mcp__conduit__inventory_suppliers untrusted-input
- mcp__conduit__supply_availability untrusted-input
- mcp__conduit__inventory_purchase_order untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/app.aiconduit/conduit/verify?hash=b6c31f8c74231bb053e455c49be74bbceaa5487df2dd4f544e80e3a31d11dca3" | jq -e '.changed == false'Pinned hash b6c31f8c7423, from Nov 10, 2026, 05:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.aiconduit/conduit/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.aiconduit/conduit)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:44 UTC.
Conduit Agentic Commerce MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Conduit Agentic Commerce MCP server safe?
- No scan can promise that. What its definitions show: 25 tools, 21 of which can change, send or delete something, and 9 findings (2 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Conduit Agentic Commerce MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: payment_mandate.
Can the Conduit Agentic Commerce MCP server do things that cannot be undone?
- Yes. 4 tools can send, pay, publish or merge: agent_notify, agent_outreach, order_dispute and inventory_purchase_order.
What tools does the Conduit Agentic Commerce MCP server have?
- 25 tools: 1 destructive, 4 irreversible, 16 write, 4 read. payment_mandate, agent_notify, agent_outreach, order_dispute, inventory_purchase_order, agent_create, agent_authenticate, agent_update and 17 more.
Does the Conduit Agentic Commerce MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Conduit Agentic Commerce MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): agent_create, agent_update, agent_notify and agent_outreach.
Has the Conduit Agentic Commerce MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.