MCP 助手
- 作者仓库星标 0
- 作者更新于 实时读取
- 作者仓库 skills-registry
- 领域
- AI 智能
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @tomevault-io · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 需要 · Vendor-specific
- 兼容的系统
- 未声明(默认跨平台)
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 允许外网请求
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生,可能与作者实际意图存在差异。
需要注意: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: ask-graphql-mcp
description: Use Ask GraphQL MCP to handle Web3 and on-chain questions through GraphQL endpoints (especially…
category: AI 智能
runtime: 无特殊运行时
---
# ask-graphql-mcp 输出预览
## PART A: 任务判断
- 适用问题:提示词、Agent 工作流、模型评估或自动化推理。
- 输入要求:目标材料、限制条件、期望输出和验收方式。
- 证据边界:围绕“Primary goal / Hard constraint: no direct-query bypass / Required inputs”读取原文规则,不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断:确认你的需求是否属于提示词、Agent 工作流、模型评估或自动化推理,并标出输入、限制和预期结果。
- **02** 执行计划:优先按“Primary goal / Hard constraint: no direct-query bypass / Required inputs”拆成步骤,说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果:给出可复制的命令、文件改动、检查清单或内容草稿,并说明如何继续迭代。
- **04** 风险边界:结合 读取文件、写入/修改文件、执行终端命令、会按任务需要访问外部网络、需要准备 Vendor-specific API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令;会按任务需要访问外部网络;需要准备 Vendor-specific API Key。
- 先小样例验证,再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 原文没有稳定的斜杠命令要求。安装验证后通常全局生效,直接在对话里点名这个 Skill 并描述任务即可。
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是:读取文件、写入/修改文件、执行终端命令。
先用一个小任务确认它会围绕“Primary goal / Hard constraint: no direct-query bypass / Required inputs”工作;涉及文件或命令时,先看 diff、日志、预览或测试结果。
检查最终产物是否包含明确结果、必要证据和下一步动作;如果输出泛泛而谈,就补充输入、边界和验收标准后重跑。
---
name: ask-graphql-mcp
description: Use Ask GraphQL MCP to handle Web3 and on-chain questions through GraphQL endpoints (especially…
category: AI 智能
source: tomevault-io/skills-registry
---
# ask-graphql-mcp
## 什么时候使用
- 把 AI / Agent方向的常用动作沉淀成 Agent 可调用的技能 适合处理AI Agent、提示词、模型评估与自动化推理,核心价值是把输入、判断、执行、验证和交付边界固定下来,避免 Agent 泛泛回答。 把任务拆成可执行、可检查…
- 面向提示词、Agent 工作流、模型评估或自动化推理,优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「Primary goal / Hard constraint: no direct-query bypass / Required inputs」组织步骤,不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令;会按任务需要访问外部网络;需要准备 Vendor-specific API Key。
- 先跑小样例,确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown,不编造命令、平台或依赖。 作者原文负责流程事实;仓库文件负责来源和命令;流狐只补充适用场景、限制和质量判断。
skill "ask-graphql-mcp" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> Primary goal / Hard constraint: no direct-query bypass / Required inputs
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 会按任务需要访问外部网络
安全层 -> 需要准备 Vendor-specific API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
} Ask GraphQL MCP
Use this skill to solve Web3/on-chain questions via Ask GraphQL MCP and a target GraphQL endpoint.
Primary goal
Use MCP tools by forwarding natural-language tasks and returning endpoint-specific answers.
Do not use direct GraphQL calls as default behavior. Use MCP first.
Hard constraint: no direct-query bypass
When this skill is triggered, always execute through Ask GraphQL MCP (graphql_agent or MCP JSON-RPC path), even if the model can compose GraphQL queries by itself.
Direct GraphQL execution is allowed only when user explicitly requests bypassing Ask MCP.
Required inputs
Collect these inputs before analysis:
- User question or task (required)
- GraphQL endpoint URL (required for execution; can be discovered via
graphql-endpoint-discovery) - Plan mode: default
free; switch topaidonly when free-tier limit is reached or user explicitly asks - API key (required for paid mode)
- Optional
X-ENDPOINT-AUTHORIZATIONwhen upstream endpoint is private
When endpoint URL is missing:
- Run pre-skill
graphql-endpoint-discovery - If high-confidence endpoint candidate exists, continue automatically
- If ambiguous, ask user to confirm among top candidates
- If no candidate, ask user for endpoint directly
Deterministic invocation rules
Use this exact routing logic:
- If task is Web3/on-chain related and user message includes explicit endpoint URL (
http://orhttps://) -> call this skill directly. - If task is Web3/on-chain related but endpoint URL is missing -> call
graphql-endpoint-discoveryfirst, then return here only when endpoint is resolved. - If task is clearly non-Web3 and non-on-chain -> do not call this skill.
- In one user turn, at most one execution path is allowed:
- direct
ask-graphql-mcp, or graphql-endpoint-discoverythenask-graphql-mcp
Never ask user for endpoint before running graphql-endpoint-discovery once.
Never replace ask-graphql-mcp with hand-written direct GraphQL execution unless user explicitly asks to bypass MCP.
MCP connection policy
- Default to free gateway:
https://ask-api.hermes-subnet.ai/mcp/graphql-agent - Use paid gateway only when needed:
https://ask-api.hermes-subnet.ai/mcp - Always set
X-ENDPOINTto the user endpoint - Set
X-ENDPOINT-AUTHORIZATIONonly when upstream endpoint requires auth - In paid mode, include
X-API-KEY
Use templates from references/config-templates.md when you need to emit copy-ready JSON.
Agent execution workflow
- Confirm endpoint and user objective. If endpoint is missing, run
graphql-endpoint-discoveryfirst. - Prefer session tool path: if
graphql_agentis available in current session tool list, use it. - If session tool is unavailable, use HTTP JSON-RPC path to Ask MCP gateway with required headers (
X-ENDPOINT, optionalX-ENDPOINT-AUTHORIZATION, andX-API-KEYin paid mode). - Send the user task to MCP in natural language.
- Timeout policy: when question complexity is high, allow MCP/agent call timeout up to 2 minutes (120s) before treating it as failed.
- If needed, send one follow-up clarification prompt to MCP.
- Return MCP result with concise interpretation for the user.
HTTP JSON-RPC path (when session tool is unavailable)
Use MCP gateway endpoint:
- Free:
https://ask-api.hermes-subnet.ai/mcp/graphql-agent - Paid:
https://ask-api.hermes-subnet.ai/mcp
Call sequence:
tools/listto verifygraphql_agentis exposed by gatewaytools/callwith:
name: "graphql_agent"arguments.question: <user natural-language request>
This path still uses MCP, not direct GraphQL querying.
Fallback workflow
If the task fails:
- Validate gateway URL matches current mode (free/paid).
- Validate
X-ENDPOINTformat and reachability. - Validate
X-ENDPOINT-AUTHORIZATIONfor private endpoints. - Validate
X-API-KEYin paid mode. - Retry with minimal known-good config.
If MCP returns free-tier rate limit/quota errors:
- Guide user to create API key at
https://ask.hermes-subnet.ai/billing/api-keys/ - Switch user to paid gateway
https://ask-api.hermes-subnet.ai/mcpwithX-API-KEY - Explicitly ask user to provide API key now so execution can continue immediately
- Provide a copy-ready paid config snippet with
X-API-KEYplaceholder in the same response - Do not end with only "retry later" or "wait for reset"; API key request must come first
If paid API key quota is exceeded:
- Guide user to check usage/quota at
https://ask.hermes-subnet.ai/billing/
Response standard
For endpoint analysis requests, structure responses as:
- Assumptions
- MCP answer summary
- Optional query/details provided by MCP
- Next step (run/verify/debug)
For pure setup requests, provide one copy-ready JSON block plus a short verification checklist.
When mentioning quota/rate-limit failures, always include the correct billing link:
- API key creation:
https://ask.hermes-subnet.ai/billing/api-keys/ - Usage/quota check:
https://ask.hermes-subnet.ai/billing/
For free-tier limit errors, treat API key guidance as highest-priority next action:
- First line should clearly request API key from user
- Include API key creation link in the same message
- Include paid-mode gateway and required header keys
Rate-limit detection and mandatory wording
Treat these as free-tier limit signals:
rate limit exceededquota exceededtoo many requestsretryAfter429
When any signal appears, reply with this mandatory first sentence pattern:
Free quota reached. Please create an API key at https://ask.hermes-subnet.ai/billing/api-keys/ and send it here so I can continue now.
Then include:
- Paid gateway URL:
https://ask-api.hermes-subnet.ai/mcp - Required paid header:
X-API-KEY - If relevant, quota page:
https://ask.hermes-subnet.ai/billing/
For practical prompt patterns, read references/tools-and-prompts.md.
Source: ComeOnOliver/skillshub — distributed by TomeVault.
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核