perplexity-enterprise-rbac

0
0
Source

Configure Perplexity enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for Perplexity. Trigger with phrases like "perplexity SSO", "perplexity RBAC", "perplexity enterprise", "perplexity roles", "perplexity permissions", "perplexity SAML".

Install

mkdir -p .claude/skills/perplexity-enterprise-rbac && curl -L -o skill.zip "https://mcp.directory/api/skills/download/9301" && unzip -o skill.zip -d .claude/skills/perplexity-enterprise-rbac && rm skill.zip

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

About this skill

Perplexity Enterprise RBAC

Overview

Control access to Perplexity Sonar API at the organizational level. Perplexity does not have built-in RBAC -- you implement access control through: separate API keys per team/environment, a gateway that enforces model and budget policies, and domain restrictions for compliance.

Access Control Strategy

LayerMechanismPerplexity Support
AuthenticationAPI key per teamYes (multiple keys)
Model restrictionGateway enforcementBuild yourself
Budget capPer-key monthly limitVia dashboard
Domain restrictionsearch_domain_filterYes (per-request)
Rate limitingGateway + key limitsYes (per-key RPM)

Prerequisites

  • Perplexity API account with admin access
  • Separate API keys per team/environment
  • Gateway or middleware for policy enforcement

Instructions

Step 1: Create Per-Team API Keys

Generate separate keys at perplexity.ai/settings/api:

Key: pplx-support-bot-prod     → Budget: $200/mo, sonar only
Key: pplx-research-team        → Budget: $1000/mo, sonar + sonar-pro
Key: pplx-data-team            → Budget: $500/mo, sonar only
Key: pplx-executive-reports    → Budget: $300/mo, sonar-pro

Step 2: Gateway with Policy Enforcement

// perplexity-gateway.ts
import OpenAI from "openai";

interface TeamPolicy {
  apiKey: string;
  allowedModels: string[];
  maxTokensPerRequest: number;
  maxRequestsPerMinute: number;
  requiredDomainFilter?: string[];  // Force search to specific domains
  blockedDomainFilter?: string[];   // Block specific domains
}

const TEAM_POLICIES: Record<string, TeamPolicy> = {
  support: {
    apiKey: process.env.PPLX_KEY_SUPPORT!,
    allowedModels: ["sonar"],
    maxTokensPerRequest: 512,
    maxRequestsPerMinute: 30,
  },
  research: {
    apiKey: process.env.PPLX_KEY_RESEARCH!,
    allowedModels: ["sonar", "sonar-pro", "sonar-reasoning-pro"],
    maxTokensPerRequest: 4096,
    maxRequestsPerMinute: 50,
  },
  compliance: {
    apiKey: process.env.PPLX_KEY_COMPLIANCE!,
    allowedModels: ["sonar", "sonar-pro"],
    maxTokensPerRequest: 2048,
    maxRequestsPerMinute: 20,
    requiredDomainFilter: ["sec.gov", "edgar.sec.gov", "law.cornell.edu"],
  },
  marketing: {
    apiKey: process.env.PPLX_KEY_MARKETING!,
    allowedModels: ["sonar"],
    maxTokensPerRequest: 1024,
    maxRequestsPerMinute: 20,
    blockedDomainFilter: ["-competitor1.com", "-competitor2.com"],
  },
};

function enforcePolicy(
  team: string,
  requestedModel: string,
  requestedTokens: number
): { client: OpenAI; model: string; maxTokens: number; domainFilter?: string[] } {
  const policy = TEAM_POLICIES[team];
  if (!policy) throw new Error(`Unknown team: ${team}`);

  if (!policy.allowedModels.includes(requestedModel)) {
    console.warn(`Team ${team} not allowed ${requestedModel}, using ${policy.allowedModels[0]}`);
  }

  const model = policy.allowedModels.includes(requestedModel)
    ? requestedModel
    : policy.allowedModels[0];

  const maxTokens = Math.min(requestedTokens, policy.maxTokensPerRequest);

  return {
    client: new OpenAI({ apiKey: policy.apiKey, baseURL: "https://api.perplexity.ai" }),
    model,
    maxTokens,
    domainFilter: policy.requiredDomainFilter || policy.blockedDomainFilter,
  };
}

Step 3: Enforced Search with Domain Restrictions

async function teamSearch(
  team: string,
  query: string,
  requestedModel: string = "sonar"
) {
  const { client, model, maxTokens, domainFilter } = enforcePolicy(
    team, requestedModel, 2048
  );

  const response = await client.chat.completions.create({
    model,
    messages: [{ role: "user", content: query }],
    max_tokens: maxTokens,
    ...(domainFilter && { search_domain_filter: domainFilter }),
  } as any);

  return {
    answer: response.choices[0].message.content,
    citations: (response as any).citations || [],
    model: response.model,
    team,
    tokens: response.usage?.total_tokens,
  };
}

// Usage
const result = await teamSearch("compliance", "latest SEC filing for AAPL", "sonar-pro");
// -> Uses sonar-pro (allowed for compliance team)
// -> Searches only sec.gov, edgar.sec.gov, law.cornell.edu

const supportResult = await teamSearch("support", "How to reset password", "sonar-pro");
// -> Downgrades to sonar (support team only allowed sonar)

Step 4: Usage Tracking per Team

class TeamUsageTracker {
  private usage: Map<string, Array<{ timestamp: number; tokens: number; model: string; cost: number }>> = new Map();

  record(team: string, tokens: number, model: string) {
    const entries = this.usage.get(team) || [];
    const cost = model === "sonar-pro" ? tokens * 0.000009 : tokens * 0.000001;
    entries.push({ timestamp: Date.now(), tokens, model, cost });
    this.usage.set(team, entries);
  }

  getDailySummary(team: string) {
    const today = new Date().toDateString();
    const entries = (this.usage.get(team) || []).filter(
      (e) => new Date(e.timestamp).toDateString() === today
    );
    return {
      team,
      queries: entries.length,
      totalTokens: entries.reduce((s, e) => s + e.tokens, 0),
      estimatedCost: entries.reduce((s, e) => s + e.cost, 0).toFixed(4),
      modelBreakdown: {
        sonar: entries.filter((e) => e.model === "sonar").length,
        "sonar-pro": entries.filter((e) => e.model === "sonar-pro").length,
      },
    };
  }
}

Step 5: Key Rotation Schedule

Rotate API keys every 90 days. Name keys with quarter (pplx-research-2026Q1) for tracking.

set -euo pipefail
# 1. Generate new key at perplexity.ai/settings/api
# 2. Deploy new key alongside old key (24-hour overlap)
# 3. Verify new key works
curl -s -o /dev/null -w "%{http_code}" \
  -H "Authorization: Bearer $NEW_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sonar","messages":[{"role":"user","content":"test"}],"max_tokens":5}' \
  https://api.perplexity.ai/chat/completions
# 4. Remove old key from perplexity.ai/settings/api

Error Handling

IssueCauseSolution
401 for a teamKey expired or revokedRegenerate key for that team
Model downgrade unexpectedPolicy restricting accessCheck team's allowedModels
Compliance citations from wrong domainDomain filter not appliedVerify requiredDomainFilter in policy
Budget exceededTeam over monthly capAlert team lead, increase cap or throttle

Output

  • Per-team API key management
  • Gateway enforcing model and token policies
  • Domain-restricted search for compliance teams
  • Usage tracking and cost allocation per team

Resources

Next Steps

For migration planning, see perplexity-migration-deep-dive.

d2-diagram-creator

jeremylongshore

D2 Diagram Creator - Auto-activating skill for Visual Content. Triggers on: d2 diagram creator, d2 diagram creator Part of the Visual Content skill category.

6532

svg-icon-generator

jeremylongshore

Svg Icon Generator - Auto-activating skill for Visual Content. Triggers on: svg icon generator, svg icon generator Part of the Visual Content skill category.

9029

automating-mobile-app-testing

jeremylongshore

This skill enables automated testing of mobile applications on iOS and Android platforms using frameworks like Appium, Detox, XCUITest, and Espresso. It generates end-to-end tests, sets up page object models, and handles platform-specific elements. Use this skill when the user requests mobile app testing, test automation for iOS or Android, or needs assistance with setting up device farms and simulators. The skill is triggered by terms like "mobile testing", "appium", "detox", "xcuitest", "espresso", "android test", "ios test".

15922

performing-penetration-testing

jeremylongshore

This skill enables automated penetration testing of web applications. It uses the penetration-tester plugin to identify vulnerabilities, including OWASP Top 10 threats, and suggests exploitation techniques. Use this skill when the user requests a "penetration test", "pentest", "vulnerability assessment", or asks to "exploit" a web application. It provides comprehensive reporting on identified security flaws.

4915

designing-database-schemas

jeremylongshore

Design and visualize efficient database schemas, normalize data, map relationships, and generate ERD diagrams and SQL statements.

12014

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.

5110

You might also like

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

1,4071,302

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

1,2201,024

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

9001,013

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

958658

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

970608

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

1,033496

Stay ahead of the MCP ecosystem

Get weekly updates on new skills and servers.