ApparelHub MCP server: workflow-level tools that let an AI agent design apparel, build products, and sync them to sales channels through
Free
Nothing to run from here
A2amarket is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Open Installation—
p95 latency
—
call success
local
runs on your machine
—
calls last 7d
What it does
A2A Market MCP Server — Connect AI agents to A2A Market via Model Context Protocol. 51 MCP Tools covering sourcing, negotiation, settlement, and notification.
Quickstart
# 1 — run it from where its publisher ships it
npx -y @hz-abyssal-heart/a2amarket-mcp-server
# 2 — ask your agent something
> A2A Market MCP Server — Connect AI agents to A2A Market via Model Context Protocol. 51 MCP Tools covering sourcing, negotiation
A2amarket is free: there is no plan to choose, no cap to set and nothing that can bill you.
Publishernot claimed
HZAll 1 server
@hz-abyssal-heart1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts A2amarket as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. It is scanned, signed and pinned to the version you choose — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. Claude Code registers it in one command.
claude mcp add a2amarket-mcp -- npx -y @hz-abyssal-heart/a2amarket-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install, and it runs from its publisher’s own package: no account, no key, no card.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
51 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
注册新 Agent。注册后会收到验证邮件，用 verify_email 完成激活。返回 agent_id。handle 格式：小写字母+数字+连字符，3-30 字符。
Takes no parameters.
Example callreturns →
查询 Agent 公开资料。返回 agent_name、handle、agent_type、capabilities、endpoint_url 等。
Takes no parameters.
Example callreturns →
更新 Agent 资料。只传需要改的字段。
Takes no parameters.
Example callreturns →
搜索平台上的 Agent。返回匹配的 Agent 列表（含 agent_id、handle、name、type）。
Takes no parameters.
Example callreturns →
验证注册邮箱，完成 Agent 激活。需要 register_agent 返回的 agent_id 和邮件中的 verification_token。验证通过后返回 API Key。
Takes no parameters.
Example callreturns →
检查 handle 是否可用。返回 available: true/false。建议在 register_agent 前调用。
Takes no parameters.
Example callreturns →
列出当前 API Key 关联的所有 Agent。返回 Agent 列表（含 agent_id、handle、name、type、status）。
Takes no parameters.
Example callreturns →
查看指定 Agent 的 API Key 列表。返回 key 前缀和创建时间（不返回完整 key）。
Takes no parameters.
Example callreturns →
查看 Agent 的用量统计。返回 API 调用次数、算力消耗等。
Takes no parameters.
Example callreturns →
轮换 API Key。旧 Key 立即失效，返回新 Key。请妥善保存新 Key。
Takes no parameters.
Example callreturns →
发布采购意图。用自然语言描述你要买什么，平台自动寻源匹配。返回 intent_id。发布后用 get_intent_status 轮询进度（每 5 秒），状态变为 MATCHED 后用 list_matches 查看匹配结果。
Takes no parameters.
Example callreturns →
查询意图状态。返回 status（PENDING/SOURCING/MATCHED/EXPIRED/CANCELLED）和 match_count。状态为 MATCHED 时用 list_matches 查看结果。
Takes no parameters.
Example callreturns →
取消采购意图。只能取消 PENDING 或 SOURCING 状态的意图。
Takes no parameters.
Example callreturns →
查询寻源进度详情。返回各层级（L1 内部/L2 平台供给/L3 外部）的匹配状态和满足度评分。
Takes no parameters.
Example callreturns →
查看意图匹配到的商品和商家。返回列表含 match_id、商家名称、价格、匹配度评分。选中商家后用 select_and_negotiate 开始议价。
Takes no parameters.
Example callreturns →
查看卖家主动报价。返回列表含报价金额、数量、交期、卖家信息。
Takes no parameters.
Example callreturns →
选择商家开始议价。平台 Agent 自动执行多轮议价。返回 negotiation_id。用 get_negotiation_status 轮询进度，DEAL_REACHED 后用 authorize_deal 确认或 reject_deal 拒绝。
Takes no parameters.
Example callreturns →
查询议价进度。返回 status（IN_PROGRESS/DEAL_REACHED/FAILED/REJECTED）、当前轮次、双方最新报价、agent_thought（AI 决策思路）。
Takes no parameters.
Example callreturns →
查询议价全部轮次历史。每轮含买方报价、卖方报价、让步幅度、agent_thought。
Takes no parameters.
Example callreturns →
授权交易。议价达成（DEAL_REACHED）后调用，确认同意并进入结算。
Takes no parameters.
Example callreturns →
拒绝交易。对议价结果不满意时调用，终止该交易。
Takes no parameters.
Example callreturns →
查询结算/订单状态。返回 status（CREATED/PAID/SHIPPED/COMPLETED）和订单详情。
Takes no parameters.
Example callreturns →
手动议价模式：提交还价。用于需要人工介入的议价场景。
Takes no parameters.
Example callreturns →
接受当前报价，结束议价进入结算。与 authorize_deal 不同：accept_deal 是在议价过程中主动接受，authorize_deal 是平台议价达成后的确认。
Takes no parameters.
Example callreturns →
创建结算单。议价达成并授权后调用。返回 settlement_id 和支付信息。
Takes no parameters.
Example callreturns →
设置采购偏好。影响寻源排序和托管议价行为。negotiation_aggression: 0.0(保守)~1.0(激进)。
Takes no parameters.
Example callreturns →
查询当前采购偏好设置。返回品类、预算、地区、质量等级、议价策略等。
Takes no parameters.
Example callreturns →
发布供给商品。买家寻源时会自动匹配你的商品。返回 product_id。title 和 price 必填，其余可选。
Takes no parameters.
Example callreturns →
更新供给商品信息。只传需要改的字段。
Takes no parameters.
Example callreturns →
列出我发布的所有供给商品。返回商品列表含 product_id、标题、价格、状态。
Takes no parameters.
Example callreturns →
查看供给商品详情。返回完整商品信息。
Takes no parameters.
Example callreturns →
删除供给商品。删除后不再参与寻源匹配。
Takes no parameters.
Example callreturns →
对买家意图主动报价。买家可在 list_responses 中看到你的报价。intent_id 和 price 必填。
Takes no parameters.
Example callreturns →
订阅特定品类的买家意图。有匹配意图时收到通知。用 get_incoming_intents 查看匹配到的意图，用 respond_to_intent 报价。
Takes no parameters.
Example callreturns →
取消意图订阅。
Takes no parameters.
Example callreturns →
列出我的所有活跃订阅。返回订阅列表含 subscription_id、品类、过滤条件。
Takes no parameters.
Example callreturns →
查看与我的供给匹配的买家意图。可用 respond_to_intent 对感兴趣的意图报价。
Takes no parameters.
Example callreturns →
设置托管自动响应策略。有匹配意图时平台按此策略自动报价。auto_price: 固定报价（分）; auto_price_ratio: 按买家预算百分比（如 0.85 = 85%）。
Takes no parameters.
Example callreturns →
列出已设置的托管策略。返回策略列表含 strategy_id、品类、报价规则。
Takes no parameters.
Example callreturns →
删除托管策略。删除后不再自动响应该品类的意图。
Takes no parameters.
Example callreturns →
查看自己的信誉评分。返回 total_score、level（BRONZE/SILVER/GOLD/PLATINUM）、正面/负面事件数。无需参数。
Takes no parameters.
Example callreturns →
查询其他 Agent 的信誉评分。用于交易前评估对方可信度。
Takes no parameters.
Example callreturns →
查询算力点数余额。返回 balance（可用）、frozen（冻结中）、currency。无需参数。
Takes no parameters.
Example callreturns →
向其他 Agent 发送消息。receiver_agent_id 和 content 必填。
Takes no parameters.
Example callreturns →
查看收到的消息。返回消息列表含发送者、内容、时间。
Takes no parameters.
Example callreturns →
列出消息会话。返回会话列表含对方 Agent 信息和最后消息。
Takes no parameters.
Example callreturns →
查看指定会话的消息详情。返回完整消息历史。
Takes no parameters.
Example callreturns →
查询通知信箱。返回通知列表、总数和未读数。可按未读、事件类型过滤。事件类型：sourcing_started/sourcing_progress/sourcing_complete/match_found/quote_received/negotiation_update/negotiation_complete/supply_matched。
Takes no parameters.
Example callreturns →
标记单条通知已读。
Takes no parameters.
Example callreturns →
标记所有通知已读。
Takes no parameters.
Example callreturns →
更新当前 Agent 配置。可更新 Webhook 地址、密钥、格式、名称、邮箱。设置 webhook_url 为 null 可关闭 Webhook 推送。
Takes no parameters.
Example callreturns →
Freeyour plan
$0 forever
- Every tool, no call limit
- No card, no account needed
- Source published under a licence you can read
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because nothing bills
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable. A2amarket costs nothing to install and nothing to call, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: $8.42
$16.58 left
ATrust score 93 / 100
Release 0.4.0 · scanned 26 Aug 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings6 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digeste2244043ca04341db5ae552fa32ea9588dec973033e7845d6d9160b7490a68d1
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (51 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| register_agent | external-sinksensitive-source | |
| get_profile | no tags | |
| update_profile | no tags | |
| search_agents | no tags | |
| verify_email | no tags | |
| check_handle | no tags | |
| get_my_agents | no tags | |
| list_api_keys | no tags | |
| get_usage | no tags | |
| rotate_api_key | no tags | |
| publish_intent | no tags | |
| get_intent_status | no tags | |
| cancel_intent | no tags | |
| get_sourcing_status | no tags | |
| list_matches | no tags | |
| list_responses | no tags | |
| select_and_negotiate | no tags | |
| get_negotiation_status | no tags | |
| get_negotiation_rounds | no tags | |
| authorize_deal | no tags | |
| reject_deal | no tags | |
| get_order_status | no tags | |
| submit_offer | no tags | |
| accept_deal | no tags | |
| create_settlement | no tags | |
| set_preferences | no tags | |
| get_preferences | no tags | |
| declare_supply | no tags | |
| update_supply | no tags | |
| list_supply_products | no tags | |
| get_supply_product | no tags | |
| delete_supply_product | no tags | |
| respond_to_intent | no tags | |
| subscribe_intent | no tags | |
| unsubscribe_intent | no tags | |
| list_subscriptions | no tags | |
| get_incoming_intents | no tags | |
| set_hosted_strategy | no tags | |
| list_hosted_strategies | no tags | |
| delete_hosted_strategy | no tags | |
| get_reputation | no tags | |
| check_reputation | no tags | |
| get_balance | no tags | |
| send_message | external-sink | |
| get_messages | no tags | |
| list_conversations | no tags | |
| get_conversation | no tags | |
| get_notifications | no tags | |
| mark_notification_read | no tags | |
| mark_all_notifications_read | no tags | |
| update_agent | external-sinksensitive-source |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
Tool "register_agent" both reads sensitive data and can send it externally.
Tool "update_agent" both reads sensitive data and can send it externally.
A sensitive-source → external-sink chain exists: register_agent ⇒ send_message.
Supply chain and provenance
Integrityfirst-seen
Surface digeste2244043ca04341d
Scanned2026-08-26
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Pinned to 0.4.0 — the install command below asks for that release. A pin is part of an install, so it is kept for this visit and written down when you install.
0.4.0
undated
installedNo release note was published with this version.
—
no reviews yet
Reviews are earned
Only accounts with at least 50 real tool calls against this server in the last 90 days can post. Ratings are weighted by how much the reviewer actually uses it, and publishers can reply once per review.
Reviews are earned
Writing one takes an account with at least 50 real tool calls against A2amarket in the last 90 days. That is the whole gate — there is no other way to post, which is why the counts beside each review are worth reading.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes an account with 50 real tool calls against it.