Pollen — Managed Agent-Readiness Layer

Manage your Pollen account: sync, enrich, fix, and publish your store's catalog for AI agents.

我该使用它吗

质量与安全性

A
描述质量
98%
模式完整度
59%
命名质量
92%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~3,239token 数(工具定义)
~470 B典型响应大小
对注意力有显著影响(占 128k 上下文窗口的 2.53%)

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": {
    "pollen": {
      "url": "https://pollen.elytron.in/mcp"
    }
  }
}

远程端点

https://pollen.elytron.in/mcpstreamable-http

它能做什么

工具清单

工具(24)

🟢 只读🟡 写入🔴 删除⚪ 未知
🟢get_account_summary

Get a high-level summary of the merchant's Pollen account: plan, agent-ready %, product counts, last sync/enrichment/writeback timestamps. Use this first if the user asks 'where do I stand?' or 'what's my status?'

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_deep_audit

The Deep Audit report: the AI answer-visibility test (frozen shopper questions asked to Claude and Gemini - cited or not, with evidence), the catalog fix plan, and the worst-scoring products with their missing attributes. Access requires the $9 one-time purchase or any paid plan; without access this returns what the report contains and how to unlock it.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢list_products(enrichmentStatus, search, limit, sortBy)

List products in the merchant's catalog with optional filters. Useful for 'show me products that haven't been enriched yet' or 'find products with the lowest scores'. Returns up to 50 per call.

输入模式

{
  "type": "object",
  "properties": {
    "enrichmentStatus": {
      "type": "string",
      "enum": [
        "PENDING",
        "COMPLETED",
        "FAILED",
        "RUNNING"
      ],
      "description": "Filter by enrichment status"
    },
    "search": {
      "type": "string",
      "description": "Match against title/vendor/type"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 25
    },
    "sortBy": {
      "type": "string",
      "enum": [
        "score_asc",
        "score_desc",
        "updated_desc"
      ],
      "default": "updated_desc"
    }
  },
  "additionalProperties": false
}
🟢get_product(productId)

Fetch full enriched detail for one product by ID. Includes the structured facts, agent description, missing attributes, cultural references, and score breakdown.

输入模式

{
  "type": "object",
  "properties": {
    "productId": {
      "type": "string",
      "description": "Pollen internal product ID"
    }
  },
  "required": [
    "productId"
  ],
  "additionalProperties": false
}
🟢get_pipeline_status

Read live pipeline status for the merchant's shop: sync, enrichment (with progress), and writeback. Use when the user asks 'is anything running?' or 'how far along is enrichment?'

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_network_insights(category)

Fetch Hive cross-merchant signal for the merchant's catalog: category benchmarks (avg images, top angles, etc.) alongside the merchant's own catalog stats for comparison. Use when the user asks 'how do I compare to similar stores?'

输入模式

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Optional category to benchmark against (apparel, beauty, home_decor, food_beverage, furniture, jewelry, footwear, fitness, electronics, diy_hardware). If omitted, returns insights across the most common category in the catalog."
    }
  },
  "additionalProperties": false
}
⚪sync_catalog

Trigger a full product sync from the merchant's platform (Shopify, WC, BC) into Pollen. Use before enrichment if products are missing or out of date.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢enrich_product(productId)

Run Pollen's multimodal enrichment on a single product. Returns immediately with a job reference; check `get_pipeline_status` for progress.

输入模式

{
  "type": "object",
  "properties": {
    "productId": {
      "type": "string",
      "description": "Pollen internal product ID"
    }
  },
  "required": [
    "productId"
  ],
  "additionalProperties": false
}
🟢enrich_all_products

Run enrichment across the merchant's full catalog (PENDING + FAILED products). Returns a job reference; check `get_pipeline_status` for progress. This is the primary 'do the work' action.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡write_back_to_store

Push enriched data back to the merchant's platform as metafields/meta_data. Run after enrichment completes. Use when the user says 'publish' or 'push to my store'.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_fix_opportunities

Analyze the catalog's agent-readiness gaps and what can be done about each: points lost per score dimension, counts fixable automatically by Pollen (empty SEO meta, missing image alt text, thin tags), the 'needs you' checklist of physical facts only the merchant knows (SKU, barcode, weight, brand, photos) with product names, and per-product description candidates awaiting merchant approval. Start here when the user asks 'what's wrong?' or 'how do I improve my score?'.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡apply_fixes(fixType)

Run one of Pollen's automated catalog-wide fixes on the merchant's store: 'seo' (fill empty SEO titles + meta descriptions), 'tags' (add tags from enrichment facts to products with fewer than 3), 'altText' (fill empty image alt texts), or 'brand' (fill missing brand from enrichment or the store's own name - Shopify vendor / WC Brands). Fill-only-empty: values the merchant already set are NEVER touched. Queued on the worker - poll get_fix_opportunities fixStatuses for progress.

输入模式

{
  "type": "object",
  "properties": {
    "fixType": {
      "type": "string",
      "enum": [
        "seo",
        "tags",
        "altText",
        "brand"
      ]
    }
  },
  "required": [
    "fixType"
  ],
  "additionalProperties": false
}
🔴apply_description(productId)

Replace ONE product's shopper-visible store description with Pollen's SANITIZED enriched version - the storefrontDescriptionCandidate shown by get_product, NOT the raw agentDescription (hedged sentences and enrichment meta-commentary are stripped before anything touches the store). This overwrites human-facing content, so you MUST show the merchant that exact candidate first and get their explicit approval before calling. Only applies when the store's current description is thin (<200 chars).

输入模式

{
  "type": "object",
  "properties": {
    "productId": {
      "type": "string",
      "description": "Pollen internal product ID"
    }
  },
  "required": [
    "productId"
  ],
  "additionalProperties": false
}
🔴update_product_facts(updates)

Write merchant-supplied physical facts to the store - the 'only you know this' gaps Pollen can't fill from enrichment: SKU, barcode (GTIN/UPC/EAN), weight, and brand. Use when the merchant provides values ('all tees weigh 180 grams', 'barcodes from my supplier sheet'). sku/barcode/weight are per-variant: products with multiple variants need variantId (list them via get_product). Up to 25 updates per call; each returns applied + previous values and the product's new score.

输入模式

{
  "type": "object",
  "properties": {
    "updates": {
      "type": "array",
      "minItems": 1,
      "maxItems": 25,
      "items": {
        "type": "object",
        "properties": {
          "productId": {
            "type": "string",
            "description": "Pollen internal product ID"
          },
          "variantId": {
            "type": "string",
            "description": "Pollen internal variant ID - required when the product has multiple variants and sku/barcode/weight are being set"
          },
          "sku": {
            "type": "string"
          },
          "barcode": {
            "type": "string",
            "description": "GTIN/UPC/EAN"
          },
          "weight": {
            "type": "number"
          },
          "weightUnit": {
            "type": "string",
            "enum": [
              "g",
              "kg",
              "oz",
              "lb"
            ],
            "description": "Shopify only (default g). WooCommerce uses the store's configured unit."
          },
          "brand": {
            "type": "string",
            "description": "Brand name - written to Shopify vendor / WooCommerce Brands (WC 9.6+)"
          }
        },
        "required": [
          "productId"
        ],
        "additionalProperties": false
      }
    }
  },
  "required": [
    "updates"
  ],
  "additionalProperties": false
}
🟢get_setup_instructions

Get the merchant-side setup steps Pollen cannot do via API - platform plugin/extension activation, SEO plugin note, surface connections still pending. Each section says exactly what to do and why. Use when onboarding or when the user asks 'what's left to set up?'.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡set_llm_provider(provider)

Set the LLM provider used for enrichment. Affects only future runs.

输入模式

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "enum": [
        "gemini",
        "claude"
      ],
      "description": "LLM provider"
    }
  },
  "required": [
    "provider"
  ],
  "additionalProperties": false
}
🟢connect_google

Start (or restart) connecting the merchant's Google Merchant Center to Pollen. Returns an authUrl that the HUMAN must open in a browser to grant Google consent - an agent cannot click it. After they approve, call get_google_connect_status to see where the flow landed (it may pause on an account picker or Terms-of-Service acceptance; resume with pick_google_account / accept_google_terms). Once active, Pollen publishes the enriched catalog automatically.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_google_connect_status

Where the Google connection stands. status: none|selecting_account (call pick_google_account with one of the returned candidates)|tos_required (call accept_google_terms)|verifying|awaiting_approval|connector_pending (Pollen is finishing setup server-side - just re-check later)|active|claim_conflict|not_admin|error. When active, includes the live funnel stage (publishing/in_review/live) and approval counts.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢pick_google_account(accountId)

Resume a Google connect paused on the account picker (status selecting_account). Pass the accountId of one of the candidates returned by get_google_connect_status. On success Pollen finishes the handshake and publishes the catalog automatically.

输入模式

{
  "type": "object",
  "properties": {
    "accountId": {
      "type": "string",
      "description": "Merchant Center account ID from the candidates list"
    }
  },
  "required": [
    "accountId"
  ],
  "additionalProperties": false
}
🟢accept_google_terms

Resume a greenfield Google connect paused on Terms-of-Service acceptance (status tos_required). Only call this after the merchant has confirmed they accept the Google Merchant Center ToS (termsUrl from get_google_connect_status). Creates their Merchant Center account and finishes the handshake.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢connect_meta

Start (or restart) connecting the merchant's Meta (Facebook/Instagram) Business catalog to Pollen. Returns an authUrl that the HUMAN must open in a browser to approve via Facebook Login - an agent cannot click it. Afterwards call get_meta_connect_status; the flow may pause on a business or catalog picker (resume with pick_meta_business / pick_meta_catalog). Once active, Pollen publishes the enriched catalog automatically.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_meta_connect_status

Where the Meta connection stands. status: none|selecting_business (call pick_meta_business with a candidate)|selecting_catalog (call pick_meta_catalog with a candidate id or "__create__" for a fresh Pollen-managed catalog)|not_admin (the Facebook account isn't a Business admin - reconnect with the right account)|active|error. When active, includes the live funnel stage and approval counts.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢pick_meta_business(businessId)

Resume a Meta connect paused on the business picker (status selecting_business). Pass the businessId of a candidate from get_meta_connect_status. May advance to the catalog picker (selecting_catalog) or go straight active.

输入模式

{
  "type": "object",
  "properties": {
    "businessId": {
      "type": "string",
      "description": "Business portfolio ID from the candidates list"
    }
  },
  "required": [
    "businessId"
  ],
  "additionalProperties": false
}
🟡pick_meta_catalog(catalogId)

Resume a Meta connect paused on the catalog picker (status selecting_catalog). Pass a candidate catalog id, or "__create__" to create a dedicated "Pollen - {shop}" catalog. NEVER pick an existing catalog without the merchant's explicit confirmation - Pollen will manage (add/remove) products in it.

输入模式

{
  "type": "object",
  "properties": {
    "catalogId": {
      "type": "string",
      "description": "Catalog ID from the candidates list, or \"__create__\""
    }
  },
  "required": [
    "catalogId"
  ],
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本24 个工具
已验证未记录版本24 个工具