Skip to main content
Glama

SocialDataX 微信 WeChat MCP

by com.52choujiang
OverviewDiscussionsAdmin

wechat_search_mp_articles

Read-only

按搜索词查找微信公众号文章，支持排序、发布时间筛选和分页；不要传文章链接或公众号账号 ID。

读取全文时，将结果的 article_url 作为 url 传给 wechat_get_mp_article_detail_by_url； 查看指定公众号发布的文章请用 wechat_get_mp_account_articles_by_account_id。 搜索卡片的展示标题和发布时间可能与详情不同，精确值以详情为准。

Input Schema

NameRequiredDescriptionDefault
keywordYes公众号文章搜索词或关键词短语；例如量子位、人工智能。不要传文章链接或公众号账号 ID。
sort_typeNo排序方式：general（综合/相关性，默认）、time_descending（最新发布）、hot（最热，顺序以平台结果为准）。general
page_tokenNo公众号文章搜索分页令牌；首次留空，继续翻页原样传回 next_page_token，并保持 keyword、sort_type 和 publish_time_range 不变。请在 3 天内续页；令牌失效后需重新搜索。
publish_time_rangeNo发布时间范围：all（不限，默认）、day（最近一天）、week（最近七天）、half_year（最近半年）。all

Output Schema

NameRequiredDescriptionDefault
itemsYes本页公众号文章搜索结果
pointsYes本次成功调用的积分消耗与调用完成时的账户积分余额。
next_page_tokenYes下一页分页令牌；空字符串表示已结束，应停止翻页；非空时完整原样传回 page_token，并保持 keyword、sort_type 和 publish_time_range 不变。请在 3 天内续页；令牌失效后需重新搜索。

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedOutput schema / properties / items / items / properties / publish_time / description
      Previous value: -"发布时间，秒级 Unix 时间戳；不可用时为 null"New value: +"搜索源返回的发布时间，秒级 Unix 时间戳；可能与详情不同，精确发布时间以详情为准；不可用时为 null"
    • changedOutput schema / properties / items / items / properties / title / description
      Previous value: -"公众号文章标题"New value: +"搜索卡片展示标题；精确标题以文章详情为准"
  2. Changed2 schema fields changed
    • changedInput schema / properties / page_token / description
      Previous value: -"公众号文章搜索分页令牌；首次留空，继续翻页原样传回 next_page_token，并保持 keyword、sort_type 和 publish_time_range 不变。"New value: +"公众号文章搜索分页令牌；首次留空，继续翻页原样传回 next_page_token，并保持 keyword、sort_type 和 publish_time_range 不变。请在 3 天内续页；令牌失效后需重新搜索。"
    • changedOutput schema / properties / next_page_token / description
      Previous value: -"下一页分页令牌；空字符串表示已结束，应停止翻页；非空时完整原样传回 page_token，并保持 keyword、sort_type 和 publish_time_range 不变。"New value: +"下一页分页令牌；空字符串表示已结束，应停止翻页；非空时完整原样传回 page_token，并保持 keyword、sort_type 和 publish_time_range 不变。请在 3 天内续页；令牌失效后需重新搜索。"
  3. Changed4 schema fields changed
    • changedInput schema / properties / page_token / description
      Previous value: -"公众号文章搜索分页令牌；首次留空，继续翻页原样传回 next_page_token，并保持搜索词不变。"New value: +"公众号文章搜索分页令牌；首次留空，继续翻页原样传回 next_page_token，并保持 keyword、sort_type 和 publish_time_range 不变。"
    • addedInput schema / properties / publish_time_range
      Added value: +{
+  "default": "all",
+  "description": "发布时间范围：all（不限，默认）、day（最近一天）、week（最近七天）、half_year（最近半年）。",
+  "enum": [
+    "all",
+    "day",
+    "week",
+    "half_year"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / sort_type
      Added value: +{
+  "default": "general",
+  "description": "排序方式：general（综合/相关性，默认）、time_descending（最新发布）、hot（最热，顺序以平台结果为准）。",
+  "enum": [
+    "general",
+    "time_descending",
+    "hot"
+  ],
+  "type": "string"
+}
    • changedOutput schema / properties / next_page_token / description
      Previous value: -"下一页分页令牌；空字符串表示已结束，应停止翻页；非空时完整原样传回 page_token，并保持 keyword 不变。"New value: +"下一页分页令牌；空字符串表示已结束，应停止翻页；非空时完整原样传回 page_token，并保持 keyword、sort_type 和 publish_time_range 不变。"
  4. Added

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations: search-card titles and publish times may differ from article details, and exact values should come from the detail endpoint. It does not need to repeat the annotation-declared read-only/open-world behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then gives concise routing guidance for alternative tools. Most sentences are useful, though the first sentence partially repeats capabilities already clear from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema and annotations covering read-only/open-world behavior, the description provides what an agent needs: purpose, misuse constraints, pagination support, and sibling routing. It also includes the important caveat that displayed search-card metadata may not match article detail values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents keyword, sort_type, page_token, and publish_time_range in detail, including pagination token continuity and expiry. The description mentions sorting, time filtering, and pagination at a high level but adds no parameter syntax beyond what the schema provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: searching WeChat official-account articles by keyword, with sorting, publish-time filtering, and pagination. It also distinguishes the tool from related siblings by telling the agent not to pass article URLs or account IDs, and by routing full-text and account-article use cases elsewhere.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit alternatives: use wechat_get_mp_article_detail_by_url for full text from an article_url, and wechat_get_mp_account_articles_by_account_id for articles from a specific account. It also warns against passing article links or account IDs as search input, which directly prevents common misuse.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SocialDataX 微信 WeChat MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources