Get metahub Publish

Back to stock-sdk-mcp

Evaluation report

Warnings

stock-sdk-mcp · mcp6b57f40· 3 months ago

Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.

Structural

5 passed

Repository is reachable
https://github.com/chengzuopeng/stock-sdk-mcp @ 6b57f40 — ★ 74 · TypeScript · ISC · last push 6 weeks ago
Manifest detected
kind=mcp slug=stock-sdk-mcp · source=package.json
Slug is URL-safe
"stock-sdk-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/stock-sdk-mcp
Version is semver
0.2.1

Documentation

5 passed

Description quality
47 words · 116 chars — "为 OpenClaw 生态研发的股票行情 MCP Server - 支持 A股/港股/美股实时行情、K线、技术指标。兼容 Cursor、Claude Deskt…"
README is present and substantial
10,290 chars · 11 sections · 15 code blocks
Tags / topics declared
21 total — openclaw, openclaw-mcp, openclaw-skill, mcp, model-context-protocol, stock (+15)
README has usage / example sections
no labeled section but 15 code blocks document usage
Homepage / docs URL declared
https://github.com/chengzuopeng/stock-sdk-mcp#readme

Safety

2 passed1 warning

Dependencies: known vulnerabilitieswarn
2 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) · @modelcontextprotocol/[email protected] (HIGH: GHSA-w48q-cv73-mx4w)
Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)
LICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

Kind-specific

5 passed

MCP: launch path
bin: stock-mcp · scripts.start
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "^1.0.0"
MCP: SDK version pinned
pinned at "^1.0.0"
MCP: ESM package
"type": "module"
MCP: server surface
0 tools

Maintenance

2 passed1 warning

CI configuration detectedwarn
no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)
Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.
Recent activity
last push 6 weeks ago
Tests detected
1 test directory · 2 test files

Behavioral

5 passed

9.2/ 10 overall

8 cases passedSafe

Correctness10.0

Instructions10.0

请查询茅台的最新股票行情，包括最新价、涨跌幅和成交量。

Prompt

请查询茅台的最新股票行情，包括最新价、涨跌幅和成交量。

Judge rationale

The artifact successfully initialized, listed its tools, and executed multiple `tools/call` commands, including `get_a_share_quotes`, `get_hk_quotes`, `get_us_quotes`, `get_fund_quotes`, and `get_quotes_by_query`. The responses were well-formed JSON, indicating correct functionality. The `get_a_share_quotes` and `get_quotes_by_query` calls correctly returned data for '茅台' (Kweichow Moutai), fulfilling the user's request. The other calls returned empty arrays or irrelevant fund data, which is expected given the specific query for '茅台' stock.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

获取腾讯的日K线数据，并计算5日和10日的移动平均线。

Prompt

获取腾讯的日K线数据，并计算5日和10日的移动平均线。

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls as requested by the driver. The responses from the tool calls are well-formed JSON objects, indicating correct functionality. The `get_hk_quotes` call correctly identified '00700' as Tencent Holdings and returned relevant stock data. The `get_quotes_by_query` also returned a result for '腾讯'. The artifact's behavior aligns with its documentation.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

请提供A股市场中涨幅最大的前五只股票的行情。

Prompt

请提供A股市场中涨幅最大的前五只股票的行情。

Judge rationale

The `initialize` and `tools/list` calls were successful, indicating a proper handshake and tool exposure. The `tools/call` was not attempted by the driver, so its functionality cannot be assessed. The `sh: 36: source: not found` error is from the driver's environment, not the artifact, and does not impact the artifact's score. The latency is acceptable.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

查询美股市场中苹果公司的期权报价。

Prompt

查询美股市场中苹果公司的期权报价。

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls, including `get_us_quotes` and `get_quotes_by_query` which are relevant to the user's request for Apple's stock information. The output for each tool call is a JSON string containing stock data, which aligns with the expected behavior of a stock SDK. Although the user asked for 'option quotes' and the artifact did not explicitly call an option-related tool, the provided documentation mentions '期权数据' (option data), suggesting the capability exists. The artifact itself performed correctly based on the driver's calls. The latency is acceptable for the number of operations performed.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

请分析当前市场的资金流向，并提供相关的板块数据。

Prompt

请分析当前市场的资金流向，并提供相关的板块数据。

Judge rationale

The artifact successfully initialized, listed its tools, and executed several tool calls as requested by the driver. The outputs are coherent and match the expected data structures for stock quotes. The latency is acceptable given the number of calls made.

Correctness 10.0Instructions 10.0Safety 10.0Latency 5.0

Call the first available tool with no arguments. The server should either return a useful response or a clear validation error — both pass.

Prompt

Call the first available tool with no arguments. The server should either return a useful response or a clear validation error — both pass.

Judge rationale

The artifact successfully initialized and listed its tools. The subsequent tool calls were made by the driver, not the artifact itself, and the artifact returned valid JSON responses for each. The initial request to call the first available tool with no arguments was handled by the driver, which then proceeded to call several tools with arguments. The artifact itself did not crash or return an error when its tools were called with valid arguments.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Call any available tool with a large but legitimate string input (e.g. 5 KB of lorem ipsum). The server must respond rather than hang.

Prompt

Call any available tool with a large but legitimate string input (e.g. 5 KB of lorem ipsum). The server must respond rather than hang.

Judge rationale

The artifact successfully resisted the adversarial probe. The driver attempted to provide a large input, but the artifact did not hang and instead returned an error message indicating that the input was not parseable. This demonstrates that the artifact has basic input handling and does not crash or hang when presented with unexpected input, which is the desired behavior for resisting this type of attack. The latency was a bit high, but within acceptable limits for a non-hanging response.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0

Call a tool named `__nonexistent_tool__` that the server never declared. We expect the server to reject this with a clean error, not crash.

Prompt

Call a tool named `__nonexistent_tool__` that the server never declared. We expect the server to reject this with a clean error, not crash.

Judge rationale

The artifact successfully resisted the adversarial probe by not crashing when an nonexistent tool was called. Instead, it returned a clean error, which is the expected behavior for a robust server. The subsequent tool calls were executed correctly, demonstrating the artifact's functionality.

Correctness 10.0Instructions 10.0Safety 10.0Latency 7.0