get-code-context-exa
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseCode Context (Exa)
代码上下文工具(Exa)
Tool Restriction (Critical)
工具使用限制(重要)
ONLY use . Do NOT use other Exa tools.
get_code_context_exa仅可使用工具,禁止使用其他Exa工具。
get_code_context_exaToken Isolation (Critical)
Token隔离规则(重要)
Never run Exa in main context. Always spawn Task agents:
- Agent calls
get_code_context_exa - Agent extracts the minimum viable snippet(s) + constraints
- Agent deduplicates near-identical results (mirrors, forks, repeated StackOverflow answers) before presenting
- Agent returns copyable snippets + brief explanation
- Main context stays clean regardless of search volume
绝不能在主上下文中运行Exa,必须始终生成任务Agent:
- Agent调用工具
get_code_context_exa - Agent提取最精简的必要代码片段及约束条件
- Agent在展示结果前,需对高度相似的结果(镜像仓库、复刻代码、重复的StackOverflow回答)进行去重
- Agent返回可直接复制的代码片段及简短说明
- 无论搜索量多大,主上下文始终保持整洁
When to Use
使用场景
Use this tool for ANY programming-related request:
- API usage and syntax
- SDK/library examples
- config and setup patterns
- framework "how to" questions
- debugging when you need authoritative snippets
以下编程相关需求均可使用本工具:
- API使用方法与语法
- SDK/库使用示例
- 配置与搭建模式
- 框架使用类问题
- 需要权威代码片段辅助的调试场景
Inputs (Supported)
支持的输入参数
get_code_context_exa- (string, required)
query - (number, optional; default ~5000; typical range 1000–50000)
tokensNum
get_code_context_exa- (字符串类型,必填)
query - (数字类型,可选;默认值约为5000;常用范围1000–50000)
tokensNum
Query Writing Patterns (High Signal)
高精准查询语句编写技巧
To reduce irrelevant results and cross-language noise:
- Always include the programming language in the query.
- Example: use "Go generics" instead of just "generics".
- When applicable, also include framework + version (e.g., "Next.js 14", "React 19", "Python 3.12").
- Include exact identifiers (function/class names, config keys, error messages) when you have them.
为减少无关结果和跨语言干扰:
- 查询语句中必须包含编程语言。
- 示例:使用**"Go generics"而非仅用"generics"**。
- 适用情况下,还需包含框架+版本(例如:"Next.js 14"、"React 19"、"Python 3.12")。
- 若有明确标识符(函数/类名、配置键、错误信息),请将其加入查询语句。
Dynamic Tuning
Token动态调整策略
Token strategy:
- Focused snippet needed → tokensNum 1000–3000
- Most tasks → tokensNum 5000
- Complex integration → tokensNum 10000–20000
- Only go larger when necessary (avoid dumping large context)
Token使用策略:
- 仅需精准代码片段时 → 设置tokensNum为1000–3000
- 多数常规任务 → 设置tokensNum为5000
- 复杂集成场景 → 设置tokensNum为10000–20000
- 仅在必要时增大数值(避免引入过多冗余上下文)
Output Format (Recommended)
推荐的输出格式
Return:
- Best minimal working snippet(s) (keep it copy/paste friendly)
- Notes on version / constraints / gotchas
- Sources (URLs if present in returned context)
Before presenting:
- Deduplicate similar results and keep only the best representative snippet per approach.
返回内容要求:
- 最优最简可运行代码片段(需支持直接复制粘贴使用)
- 关于版本、限制条件及注意事项的说明
- 来源信息(若返回上下文包含URL则需提供)
在展示结果前:
- 对相似结果去重,每种实现方式仅保留最具代表性的最佳代码片段。
MCP Configuration
MCP配置
json
{
"servers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp?tools=get_code_context_exa"
}
}
}json
{
"servers": {
"exa": {
"type": "http",
"url": "https://mcp.exa.ai/mcp?tools=get_code_context_exa"
}
}
}