mcp server
Conduit Agentic Commerce
Search multi-merchant supply, checkout, and track orders via MCP.
Description as published by the maintainer. Source
- version 0.1.0
- archived
- retrieval
archived — The linked repository returns 404. It was deleted, renamed or made private. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.
What this server can do
17 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
agent_authenticate(nonce, agent_id, signature)- Two-step re-auth. Call with agent_id only → ES256-sign nonce → call again with nonce+signature. Prefer keys from ~/.conduit/credentials.json. Do not agent_create if credentials already exist. Required: agent_id.
agent_create(handle, public_key, preferences, friendly_name, payment_rails, business_profile, role_description, human_description, default_destination)- Register an agent (ES256 P-256 public JWK JSON string + optional payment rails + destination). BEFORE: read ~/.conduit/credentials.json — if it exists, reuse agent_id (do NOT register again). AFTER: write credentials (version, agent_id, public_key, private_key as JWKs; recommend handle; chmod 0600). Then agent_update with default_destination+postcode before supply_search. Optional friendly_name / human_description / role_description only if the human stated them. Omit handle to auto-generate (e.g. parcel-watcher-12). Required: public_key.
agent_organization(agent_id, session_token)- Read the linked organization (name, slug, country, default address) for an agent. Returns org_not_linked when organization_id is unset — dashboard claim/join is not released yet; do not invent join_org. Required: agent_id.
agent_report_issue(kind, tool, error, detail, context, message, agent_id, order_id, search_id, session_id, session_token)- 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. Required: message.
agent_update(handle, agent_id, preferences, friendly_name, payment_rails, session_token, business_profile, role_description, human_description, default_destination)- Patch handle, rails, default_destination (postcode required for ships-to), friendly_name, human_description, role_description, business profile, or preferences. Required: agent_id.
order_dispute(agent_id, order_id, session_token)- Refund/chargeback/report paths for an order. Requires owning agent_id. Required: order_id, agent_id.
order_events(agent_id, order_id, session_token)- Lifecycle timeline — transitions only. Pair with order_track. Requires owning agent_id. Required: order_id, agent_id.
order_execute(carrier, agent_id, pay_with, quantity, search_id, supply_id, session_token, idempotency_key)- Handoff or autonomous checkout. Autonomous needs badge payable_now + active mandate. Use idempotency_key. Prefer supply_delivery when only comparing delivery. Required: agent_id, supply_id.
order_feedback(notes, outcome, quality, agent_id, order_id, search_id, session_token, carrier_rating)- 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. Required: order_id, agent_id, outcome.
order_list(status, agent_id, open_only, session_token)- List orders for an agent ({ orders }). Optional status or open_only filter. Required: agent_id.
order_track(agent_id, order_id, session_token)- Honest deal-type-aware status (never fabricates carrier scans). Requires owning agent_id. Required: order_id, agent_id.
order_update_status(note, status, carrier, agent_id, order_id, search_id, tracking_id, session_token, handoff_endpoint, external_checkout_id)- Agent manual correction or degraded handoff recovery. note required except cancelled. Owning agent_id required. Required: order_id, agent_id, status.
payment_mandate(scope, action, expires, agent_id, mandate_id, session_token)- AP2 spend mandates. action=request (needs scope) → approval_url; list; update (mandate_id+scope); revoke (mandate_id). Widening needs human re-approval; narrowing applies immediately. Required: action, agent_id.
payment_methods(rail, action, agent_id, session_token)- 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. Required: agent_id, action.
supply_delivery(region, country, agent_id, quantity, supply_id, postal_code, session_token)- Non-committing checkout probe for shipping ETA/cost. Uses agent default_destination, else linked org default address, or country override. Required: supply_id.
supply_details(agent_id, search_id, supply_id, session_token)- Full normalized product detail from search cache. For shipping ETA/cost use supply_delivery. Re-run supply_search if offer_not_in_cache. Required: supply_id.
supply_search(limit, query, budget, offset, country, agent_id, quantity, search_id, fetch_limit, payable_with, session_token, include_sandbox)- 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 (testOffer=true). Always pass agent_id for mandate-aware badges. Carry search_id through supply_details / order_execute / order_feedback.
Last successful function declaration observed on . Source: https://mcp.aiconduit.app/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://mcp.aiconduit.app/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| Latest published version | 0.1.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-26 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| First listed in the MCP Registry | 2026-07-26 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | not_found | GitHub returned 404 for the repository the maintainer listed. The project was deleted, renamed or made private, so the listing points at nothing. | as of fetch | GitHub | |
| mcp tools declared | 17 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | mcp.aiconduit.app | |
| mcp endpoint status | ok | The server listed 17 functions when asked. | as of probe | mcp.aiconduit.app |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json