Loading ToolBench

Reading the current corpus…

weixin-articles-mcp MCP server · D · ToolBench

← Browse

weixin-articles-mcp

github.com/prairiemimosajamestown413/weixin-articles-mcp

MCP server for reading WeChat (微信) Official Account articles, with native multimodal output (images + video keyframes).

<=2025-11-25STDIO1 tools

55/100

Definition Quality68

Protocol Readiness47

Supportability38

Spec posture

Inferred effective spec <=2025-11-25·current baseline 2026-07-28

Static source inference · medium confidence · detected: Logging

Deprecated protocol patterns detected

Summary

Single tool 'read_article' has a clear, detailed description (194 chars) and proper input schema with type and description. However, output schema is explicitly set to null (output_schema=None), preventing validation and documentation of the multimodal response structure. Parameter descriptions are present but minimal. No error handling guidance for LLMs (e.g., 'if fetch fails, try again' or 'check URL format'). Tool is read-only and well-scoped, but lacks the structured output documentation and error recovery patterns expected of production tools.

Tools (1)

read_articleread onlysource verified68/100

Read a WeChat Official Account article (mp.weixin.qq.com/s/...) and return its content as a multimodal block list: - First text block: title, account, publish time, cover URL, video count, and the full article body in Markdown. - Image blocks: the article's PNG/JPG images (GIFs filtered out, capped at 10) returned as native image content so the LLM can see them directly. - Per-video groups: a text marker `video kind=... vid=... keyframes=N` followed by N evenly-spaced keyframe images (capped at 3 videos). On failure the response is a single text block starting with "Error:".

Issues (5)

HIGHresponse-shaper ↗

Output schema explicitly set to null; multimodal response structure (text blocks, image blocks, video keyframes) is undocumented and unvalidated. LLMs cannot infer the response format or plan downstream processing.

read_article

HIGHrecovery-guide ↗

Error responses are unstructured text blocks starting with 'Error:' (e.g., 'Error: fetch failed: ...'). No error classification (retryable vs. fatal), no recovery guidance, no structured error object. LLMs cannot distinguish transient failures from permanent ones.

read_article

MEDIUMtool-description ↗

Parameter 'url' description is minimal ('A WeChat article URL, format: https://mp.weixin.qq.com/s/xxx'). Does not explain what happens on invalid URLs, whether redirects are followed, or timeout behavior. Baseline for param descriptions is 72 chars; this is ~50 chars.

read_article

MEDIUMtool-description ↗

Recommendations

Define and document the output schema as a structured object: {type: 'object', properties: {blocks: {type: 'array', items: {oneOf: [{type: 'object', properties: {type: 'text', text: {type: 'string'}}, ...}, {type: 'object', properties: {type: 'image', source: {type: 'object', ...}}, ...}]}}}}. This enables LLM planning and validation.
Implement structured error responses with a 'code' field (e.g., 'invalid_url', 'fetch_timeout', 'parse_error') and a 'recovery' field with actionable guidance (e.g., 'Verify the URL starts with https://mp.weixin.qq.com/s/ and try again').
Expand parameter description for 'url' to ~100 chars: 'A WeChat Official Account article URL (format: https://mp.weixin.qq.com/s/xxx). Must be a valid, publicly accessible article. Redirects are followed. Timeout: 20s.'
Add tool description details on limits and behavior: 'Images are capped at 10 per article (GIFs excluded). Videos are capped at 3; each returns up to 3 keyframes. If the article exceeds these limits, the response includes only the first N items.'
Migrate from STDIO to HTTP+SSE or Streamable HTTP transport to enable remote access and integration with hosted MCP clients.

Spec posture evidence

Inferred effective spec: <=2025-11-25.

Relies on Logging (deprecated) - log to stderr or use OpenTelemetry

Score history

Overall score trend

First recorded score · v2 rubric

55/100

Scored	Grade	Overall	Spec posture	Rubric
2026-09-23	D	55	<=2025-11-25	v2