skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
exa-labs/exa-mcp-server49 installs

get-code-context-exa

Code context using Exa. Finds real snippets and docs from GitHub, StackOverflow, and technical docs. Use when searching for code examples, API syntax, library documentation, or debugging help.

How do I install this agent skill?

npx skills add https://github.com/exa-labs/exa-mcp-server --skill get-code-context-exa
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    This skill configures a code-search tool using the Exa.ai API via the Model Context Protocol (MCP). It includes best-practice instructions for token management and query optimization. The primary risk is the inherent susceptibility to indirect prompt injection from the external technical content (e.g., StackOverflow or GitHub) that the skill is designed to ingest.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · No issues

  • Runlayerwarn

    1/1 file flagged

What does this agent skill do?

Code Context (Exa)

Tool Restriction (Critical)

ONLY use get_code_context_exa. Do NOT use other Exa tools.

Token Isolation (Critical)

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

When to Use

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

Inputs (Supported)

get_code_context_exa supports:

  • query (string, required)
  • tokensNum (number, optional; default ~5000; typical range 1000–50000)

Query Writing Patterns (High Signal)

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.

Dynamic Tuning

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)

Output Format (Recommended)

Return:

  1. Best minimal working snippet(s) (keep it copy/paste friendly)
  2. Notes on version / constraints / gotchas
  3. Sources (URLs if present in returned context)

Before presenting:

  • Deduplicate similar results and keep only the best representative snippet per approach.

MCP Configuration

{
  "servers": {
    "exa": {
      "type": "http",
      "url": "https://mcp.exa.ai/mcp?tools=get_code_context_exa"
    }
  }
}

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/exa-labs/exa-mcp-server/get-code-context-exa">View get-code-context-exa on skillZs</a>