Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wjxcom/wjx-ai-kit --skill wjx-mcp-usegit clone --depth 1 https://github.com/wjxcom/wjx-ai-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wjxcom/wjx-ai-kit/wjx-mcp-use)<a href="https://agentmods.dev/skills/wjxcom/wjx-ai-kit/wjx-mcp-use"><img src="https://agentmods.dev/badge/skills/wjxcom/wjx-ai-kit/wjx-mcp-use/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wjxcom/wjx-ai-kit/wjx-mcp-use"><img src="https://agentmods.dev/badge/skills/wjxcom/wjx-ai-kit/wjx-mcp-use.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00113 | $0.05502 |
| Opus 5.5 | $0.00045 | $0.02201 |
| Sonnet 5.5 | $0.00023 | $0.01100 |
| Haiku 4.5 | $0.00011 | $0.00550 |
Grade A, and why
wjx-mcp-use scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wjx-mcp-server Usage Guide
wjx-mcp-server 提供 MCP 工具、参考资源和 prompt 模板,覆盖问卷星核心业务子集;CLI 是主入口,工作站能力(初始化、配置、补全、Skill 安装)保持 CLI-only。完整差异以仓库 capabilities/capability-matrix.json 为准。
HTTP 凭据边界
本地优先使用 stdio,并通过 WJX_API_KEY 提供上游凭据。HTTP 模式中,MCP_AUTH_TOKEN 只保护 /mcp 的 Authorization: Bearer 访问 gate;单租户上游仍使用 WJX_API_KEY。启用 MCP_TENANT_MODE=1 时,每个请求必须提供 X-WJX-API-Key,服务端按 session 隔离且不回退进程级 key。只有显式设置 MCP_LEGACY_BEARER_API_KEY=1 才允许 Bearer 兼作上游 API Key;/health 不要求 Bearer。不要在消息、日志或 URL 中输出完整凭据。
HTTP 服务配置
如果使用已部署的 MCP HTTP 服务,无需在本机安装 wjx-mcp-server 或配置本地
WJX_API_KEY。在支持 MCP HTTP 的客户端配置中添加:
{
"mcpServers": {
"wjx": {
"type": "http",
"url": "https://alifc.wjx.cn/mcp/latest",
"headers": {
"Authorization": "Bearer sk-wjx-xxx"
}
}
}
}
将 sk-wjx-xxx 替换为服务端分配的 HTTP 访问令牌。保存配置后完全重启客户端;启用多租户模式时,还需按服务端要求提供 X-WJX-API-Key。
Agent 前门
MCP 任务遵循“发现意图 -> 预检 -> 计划 -> 确认 -> 执行 -> 读回验证 -> 报告”。Prompt 只提供指导,不执行工具也不保证验证;Agent 必须根据工具返回的 isError 和 result 字段判断成功。WorkBuddy、Cowork、Codex Work、Qianwen Work 都先按 宿主中立握手与路由 检查真实能力,不根据宿主名称猜测配置或 API。创建、发布、提交、设置替换、清理和凭据相关操作先说明副作用,高风险和队列消费操作需要确认;网络超时后的结果按 unknown 处理并优先读回。风险、重试、验证和 JSONL 题型以生成的 agent-contract/jsonl-qtypes 资料及对应只读资源为准。 其中包括 wjx://reference/jsonl-qtypes。
query_responses_realtime 会消费服务端实时答卷队列,因此 Agent contract 将它标记为高风险且不可重放;调用前先向用户说明会移除/消费队列中的记录并取得确认。该标记是 MCP/Agent 层的安全策略,不改变 CLI 的 response realtime metadata 或退出码。
外部问卷产品的常见入口可这样映射:question builder 对应 create_survey_by_json 的 JSONL;preview 对应 build_preview_url;publish 对应 update_survey_status;collect 对应 query_responses/download_responses;analyze 对应分析工具。分支、随机、配额和 piping 只有在生成 profile 明确列出并通过 SDK 校验时才可使用,否则视为未验证能力。
AI Agent 行为准则(必读)
规则 0:按场景选择 JSONL 或 XML DSL
问卷可通过 create_survey_by_json(JSONL)或 create_survey_from_definition(完整 XML DSL)创建。修改使用 update_survey_from_definition,查询 DSL 使用 query_wjx_dsl;XML DSL 的生成与校验使用 generate_wjx_dsl。所有 DSL 输入必须符合 wjx-dsl 1 规范并经过校验。
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +3 lines f2f7ac7bef60
- 1mo ago Changed · -9 lines 31220c383554
- 1mo ago Changed · +5 lines 1d8a992f33f7
- 1mo ago Changed · +16 lines · -5 tokens per session c16b6f7a3052
- 1mo ago Changed · +27 lines 12545257f5b6
- 1mo ago Changed · +1 tokens per session bf3a92178f79
- 1mo ago First seen · 208 lines · 117 tokens per session scan A 5c41438ba53a
wjx-mcp-use is a skill published in the GitHub repository wjxcom/wjx-ai-kit (22 stars, last pushed 6d ago), licensed MIT. It adds 113 tokens to every session and 5,502 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pipefy-ai-agents
Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Includes pre-flight validation and pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For traditional automations and AI…
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). For AI agents (conversational), see pipefy-ai-agents.
pipefy-pipes-and-cards
Use this skill when the user wants to read, create, update, or delete pipes, phases, phase fields, labels, cards, comments, or field conditions. Use the seed-pipe-across-phases workflow when populating empty phases for demos or QA.
pipefy-portal-setup
Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Uses Interfaces and internalapi. Not for pipes/cards, and not for HTML interfaces (use pipefy-html-interfaces).
pipefy-api-fallback
Use this skill when a toolkit operation fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow…
pipefy-ipaas
Use when the user wants to build, test, publish, or manage iPaaS (Advanced Automations) flows: multi-step integrations with external apps (Slack, Gmail, Google Sheets), incoming webhooks, schedules, routers, code steps, or iPaaS data tables. Driven through a per-pipe catalog discovered at runtime. For native if/then…