AgentsIndex

The editors' index of AI-native software, from AI agents to the models and frameworks behind them.

我该使用它吗

质量与安全性

B
描述质量
98%
模式完整度
88%
命名质量
97%
投毒风险
40%
权限匹配度
100%
协议合规性
100%

发现(4)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domain在 submit_listing 中
  • MEDIUMTool description contains URL to non-standard domain在 list_offers 中
  • MEDIUMTool description contains URL to non-standard domain在 my_listings 中

基于对工具定义和协议合规性的自动分析。

上下文开销

~2,235token 数(工具定义)
~591 B典型响应大小
对注意力有中等影响(占 128k 上下文窗口的 1.75%)

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高,可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中:

{
  "mcpServers": {
    "mcp": {
      "url": "https://agentsindex.ai/mcp"
    }
  }
}

远程端点

https://agentsindex.ai/mcpstreamable-http

它能做什么

工具清单

工具(12)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢search_listings(query, limit)

Full-text search over AgentsIndex's Published tools. Returns compact records (name, slug, tagline, url). Fetch depth with get_listing.

输入模式

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "What to search for."
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 10, cap 25)."
    }
  },
  "required": [
    "query"
  ]
}
🟢get_listing(slug)

One tool in full, as answer-first markdown: the summary, then every question on the sheet with its answer, the vendor's own words for it and the URL that proves it. Identical to /{slug}.md and to the HTML page.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The listing slug (from search_listings or the URL)."
    }
  },
  "required": [
    "slug"
  ]
}
🟢list_categories

AgentsIndex's taxonomy with live listing counts.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢compare_listings(a, b)

Two tools side by side, as markdown: taglines, pricing, API availability, tags — the researched compare facts, honest about unknowns.

输入模式

{
  "type": "object",
  "properties": {
    "a": {
      "type": "string",
      "description": "First listing slug."
    },
    "b": {
      "type": "string",
      "description": "Second listing slug."
    }
  },
  "required": [
    "a",
    "b"
  ]
}
🟢get_best_of(category)

The Published tools in one category, in the order its category page prints (ranked by what we can confirm: a public price, an API and docs, independent sources, stated limits), as a markdown answer sheet. Payment never moves a row.

输入模式

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "The category slug (from list_categories)."
    }
  },
  "required": [
    "category"
  ]
}
🟡submit_listing(url)

Submit a tool to AgentsIndex: the url alone; we write its name and description from its own pages. Requires an existing signed-in account with verified email; send its session Cookie header on the MCP request, or an agent key the account made at https://agentsindex.ai/dashboard/agents as Authorization: Bearer. Identity and email come only from that session or key. Sign in or explicitly create an account at https://agentsindex.ai/login?next=%2Fsubmit and verify its email before retrying. This tool creates no account and sends no verification email. Returns {httpStatus:201, id, slug, status:'Draft'}; research + the quality gate decide publication. Your own (url, session email) replay within 24h returns httpStatus:200. The fit check starts at once and usually answers within a minute: poll GET https://agentsindex.ai/api/submissions/{id} and wait the Retry-After seconds it sends while fit is "checking". fit then reads "accepted" (it goes live, and the account is mailed), "rejected" (mailed with the reason) or "undecided" (a person looks within 2 days). No session: {httpStatus:401, error:'sign_in_required', message, loginUrl}. Unverified session: {httpStatus:403, error:'email_unverified', message, email, remediation}. Company gate: the account's address, or an address it proved with a code, must be on the submitted website's domain; otherwise {httpStatus:403, error:'domain_unverified', message, domain, remediation} — POST /api/domain-proof/start {url, email} mails a 6-digit code to an address at that domain, POST /api/domain-proof/verify {proofId, code} redeems it, then submit again. Personal mailboxes (gmail, outlook…) never prove a domain. No refusal creates a listing. Validation returns 400; duplicate/claim responses return 409. Read tools remain keyless.

输入模式

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The website being submitted (https)."
    }
  },
  "required": [
    "url"
  ]
}
🟡send_lead(name, email, message, consent, listingSlug, ...)

Send a buyer-intent enquiry (lead) to a tool or a whole category on AgentsIndex. Keyless. Requires consent:true, a real name, a permanent (non-disposable) email, a message of at least 20 chars, and a target (listingSlug OR categorySlug). Returns { ok, delivered }. Idempotent by (email, target) within 7 days. Nothing here changes a listing's rank, tier or copy.

输入模式

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Your name."
    },
    "email": {
      "type": "string",
      "description": "A permanent contact email (non-disposable)."
    },
    "message": {
      "type": "string",
      "description": "The enquiry — real demand, at least 20 chars."
    },
    "consent": {
      "type": "boolean",
      "description": "Must be true — you agree your details go to the provider(s)."
    },
    "listingSlug": {
      "type": "string",
      "description": "Target listing slug (this OR categorySlug)."
    },
    "categorySlug": {
      "type": "string",
      "description": "Target category slug (this OR listingSlug)."
    },
    "company": {
      "type": "string",
      "description": "Optional company name."
    }
  },
  "required": [
    "name",
    "email",
    "message",
    "consent"
  ]
}
🟢list_offers

What a listing owner can buy on AgentsIndex, with prices in US cents (VAT included), each offer's term and what it needs. Keyless. Same answer as GET https://agentsindex.ai/api/agent/catalogue. Listing on AgentsIndex is free and never sold: submit_listing.

输入模式

{
  "type": "object",
  "properties": {}
}
🟢get_quote(offer, listing)

A signed price for one offer (from list_offers) on one listing, valid for a short time, and whether the listing can have it now. Only the account that owns the listing gets one: send its session Cookie header, or its agent key as Authorization: Bearer, on the MCP request. Refusals say why and what to do (httpStatus 401 sign_in_required, 403 not_owner with the claim page, 409 not_accepted, already_bought, category_full). Nothing is reserved or charged.

输入模式

{
  "type": "object",
  "properties": {
    "offer": {
      "type": "string",
      "description": "An offer id from list_offers, e.g. boost."
    },
    "listing": {
      "type": "string",
      "description": "The listing id or slug (from search_listings or get_listing)."
    }
  },
  "required": [
    "offer",
    "listing"
  ]
}
🟡create_order(quote_id, idempotency_key)

Turns a quote (from get_quote) into an order, payable for 24 hours. Same account as the quote: its session Cookie header, or its agent key as Authorization: Bearer (order scope). Returns the order with payment.url: POST it without a credential for a 402 card challenge (MPP, method stripe, a Stripe Shared Payment Token), then again with Authorization: Payment. Pass idempotency_key to make a retry return the same order. The price includes any VAT. Nothing is charged by this tool.

输入模式

{
  "type": "object",
  "properties": {
    "quote_id": {
      "type": "string",
      "description": "The quote_id from get_quote."
    },
    "idempotency_key": {
      "type": "string",
      "description": "Optional: your own key, the same on every retry of this order."
    }
  },
  "required": [
    "quote_id"
  ]
}
🟢my_listings(slug)

What the AgentsIndex owner dashboard shows about the listings an account owns: each one's status (in review with the expected date, accepted and going live on a day, live, or not accepted with the reason), the listing as it shows, 30 days of real numbers with the 30 before, where AI answers named the product or cited its page, and what it can buy here at this site's prices. Only for the account itself: send its session Cookie header, or its agent key with "Read your listings" as Authorization: Bearer. Same answer as GET https://agentsindex.ai/api/owner/listings. Read-only: corrections go through the dashboard's request form.

输入模式

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Optional: one listing, by its slug. Without it, every listing the account owns."
    }
  }
}
⚪subscribe_newsletter(email, source)

Single opt-in subscribe to the AgentsIndex digest of new and freshly re-verified tools. Provide an email; returns { ok }. Every issue carries a one-click unsubscribe.

输入模式

{
  "type": "object",
  "properties": {
    "email": {
      "type": "string",
      "description": "The email to subscribe."
    },
    "source": {
      "type": "string",
      "description": "Optional: where the subscribe came from."
    }
  },
  "required": [
    "email"
  ]
}

社区

评价此服务器

证据

最近观测

已验证未记录版本12 个工具