EX

exa-enterprise-rbac

Implements RBAC through multi-key architectures and application-level permission logic for Exa.

Install

mkdir -p .claude/skills/exa-enterprise-rbac && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6864" && unzip -o skill.zip -d .claude/skills/exa-enterprise-rbac && rm skill.zip

Installs to .claude/skills/exa-enterprise-rbac

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Manage Exa API key scoping, team access controls, and domain restrictions.
74 charsno explicit “when” trigger
Advanced

Key capabilities

  • Implement multi-key architecture for use-case isolation
  • Enforce application-level search permissions
  • Restrict search results to specific domains per team
  • Track API key usage for budget enforcement
  • Perform secure API key rotation

How it works

It implements access control by using multiple API keys and application-layer logic to enforce usage limits and domain restrictions.

Inputs & outputs

You give it
Search request parameters and user role
You get back
Validated search result or access denial

When to use exa-enterprise-rbac

  • Implement multi-key architecture
  • Set up per-team search limits
  • Apply domain-level restrictions
  • Configure role-based access for search

About this skill

Exa Enterprise RBAC

Overview

Manage access to Exa search API through API key scoping and application-level controls. Exa is API-key-based (no built-in RBAC), so access control is implemented through multiple API keys per use case, application-layer permission enforcement, domain restrictions per team, and per-key usage monitoring.

Prerequisites

  • Exa API account with team/enterprise plan
  • Dashboard access at dashboard.exa.ai
  • Multiple API keys for key isolation

Instructions

Step 1: Key-Per-Use-Case Architecture

// config/exa-keys.ts
import Exa from "exa-js";

// Create separate clients for each use case
const exaClients = {
  // High-volume RAG pipeline — production key with higher limits
  ragPipeline: new Exa(process.env.EXA_KEY_RAG!),

  // Internal research tool — lower volume key
  researchTool: new Exa(process.env.EXA_KEY_RESEARCH!),

  // Customer-facing search — separate key for isolation
  customerSearch: new Exa(process.env.EXA_KEY_CUSTOMER!),
};

export function getExaForUseCase(
  useCase: keyof typeof exaClients
): Exa {
  const client = exaClients[useCase];
  if (!client) throw new Error(`No Exa client for use case: ${useCase}`);
  return client;
}

Step 2: Application-Level Permission Enforcement

// middleware/exa-permissions.ts
interface ExaPermissions {
  maxResults: number;
  allowedTypes: ("auto" | "neural" | "keyword" | "fast" | "deep")[];
  allowedCategories: string[];
  includeDomains?: string[];     // restrict to these domains
  dailySearchLimit: number;
}

const ROLE_PERMISSIONS: Record<string, ExaPermissions> = {
  "rag-pipeline": {
    maxResults: 10,
    allowedTypes: ["neural", "auto"],
    allowedCategories: [],
    dailySearchLimit: 10000,
  },
  "research-analyst": {
    maxResults: 25,
    allowedTypes: ["neural", "keyword", "auto", "deep"],
    allowedCategories: ["research paper", "news"],
    dailySearchLimit: 500,
  },
  "marketing-team": {
    maxResults: 5,
    allowedTypes: ["keyword", "auto"],
    allowedCategories: ["company", "news"],
    dailySearchLimit: 100,
  },
  "compliance-team": {
    maxResults: 10,
    allowedTypes: ["keyword", "auto"],
    allowedCategories: [],
    includeDomains: ["nist.gov", "owasp.org", "sans.org", "sec.gov"],
    dailySearchLimit: 200,
  },
};

function validateSearchRequest(
  role: string,
  searchType: string,
  numResults: number,
  category?: string
): { allowed: boolean; reason?: string } {
  const perms = ROLE_PERMISSIONS[role];
  if (!perms) return { allowed: false, reason: "Unknown role" };
  if (!perms.allowedTypes.includes(searchType as any)) {
    return { allowed: false, reason: `Search type ${searchType} not allowed for ${role}` };
  }
  if (numResults > perms.maxResults) {
    return { allowed: false, reason: `Max ${perms.maxResults} results for ${role}` };
  }
  if (category && perms.allowedCategories.length > 0 && !perms.allowedCategories.includes(category)) {
    return { allowed: false, reason: `Category ${category} not allowed for ${role}` };
  }
  return { allowed: true };
}

Step 3: Domain Restrictions per Team

// Enforce domain restrictions so compliance-sensitive teams
// only see results from vetted sources
async function enforcedSearch(
  exa: Exa,
  role: string,
  query: string,
  opts: any = {}
) {
  const perms = ROLE_PERMISSIONS[role];
  if (!perms) throw new Error(`Unknown role: ${role}`);

  const validation = validateSearchRequest(
    role,
    opts.type || "auto",
    opts.numResults || 10,
    opts.category
  );
  if (!validation.allowed) throw new Error(validation.reason);

  return exa.searchAndContents(query, {
    ...opts,
    numResults: Math.min(opts.numResults || 10, perms.maxResults),
    type: opts.type || "auto",
    // Merge domain restrictions from role permissions
    includeDomains: perms.includeDomains || opts.includeDomains,
  });
}

Step 4: Per-Key Usage Tracking

// Track usage per API key / role for budget enforcement
class KeyUsageTracker {
  private usage = new Map<string, { count: number; resetAt: number }>();

  checkAndIncrement(role: string): void {
    const perms = ROLE_PERMISSIONS[role];
    if (!perms) throw new Error(`Unknown role: ${role}`);

    const now = Date.now();
    const dayStart = new Date().setHours(0, 0, 0, 0);
    let entry = this.usage.get(role);

    if (!entry || entry.resetAt < now) {
      entry = { count: 0, resetAt: dayStart + 24 * 60 * 60 * 1000 };
    }

    if (entry.count >= perms.dailySearchLimit) {
      throw new Error(
        `Daily search limit (${perms.dailySearchLimit}) exceeded for ${role}`
      );
    }

    entry.count++;
    this.usage.set(role, entry);
  }

  getUsage(role: string) {
    const entry = this.usage.get(role);
    const limit = ROLE_PERMISSIONS[role]?.dailySearchLimit || 0;
    return {
      used: entry?.count || 0,
      limit,
      remaining: limit - (entry?.count || 0),
    };
  }
}

Step 5: Key Rotation Procedure

set -euo pipefail
# 1. Create new key in Exa dashboard (dashboard.exa.ai)
# 2. Deploy new key alongside old key
# 3. Verify new key works
curl -s -o /dev/null -w "%{http_code}" \
  -X POST https://api.exa.ai/search \
  -H "x-api-key: $NEW_EXA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"key rotation test","numResults":1}'

# 4. Switch traffic to new key
# 5. Monitor for errors
# 6. Revoke old key in dashboard after 24h

Error Handling

IssueCauseSolution
401 on searchInvalid or revoked API keyRegenerate in dashboard
429 rate limitedKey-level rate limit exceededDistribute across keys
Daily limit hitSearch budget exhaustedAdjust limits or wait for reset
Wrong domain resultsMissing domain filterApply includeDomains per role

Resources

Next Steps

For policy enforcement, see exa-policy-guardrails. For multi-env setup, see exa-multi-env-setup.

When not to use it

  • When a single API key is sufficient for all operations
  • When organization-level governance is not required

Prerequisites

Exa enterprise planDashboard access at dashboard.exa.ai

Limitations

  • Access control is enforced at the application layer, not the API layer
  • Requires manual management of multiple API keys

How it compares

It builds custom RBAC logic on top of Exa's key-based system since Exa does not have built-in role-based access control.

Compared to similar skills

exa-enterprise-rbac side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
exa-enterprise-rbac (this skill)127dCautionAdvanced
github-code-review132moReviewAdvanced
windows-ui-automation178moReviewAdvanced
qa-tester299moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

Search skills

Search the agent skills registry