PingAura

See how AI answer engines mention your brand: visibility scores, competitors, prompts, site health audits and AI-optimised articles, in your PingAura workspace.

Ver em pingaura.ai

Servidor MCP hospedado

npx add-mcp 'https://www.pingaura.ai/api/mcp'

Instala no Claude Code, Codex, Cursor e outros

Documentação

Home Page

Sign In Sign Up

Documentation

Product guides

MCP Server

Connect PingAura to Claude, Cursor, Codex, VS Code, Perplexity, ChatGPT, Gemini CLI, and other AI clients via MCP. Access domains, visibility scores, audits, and articles from your AI assistant.

Updated Oct 24, 2026

ShareAsk AI

PingAura runs a remote MCP server. It lets AI assistants query your account data directly. This includes domains, visibility scores, site audits, and articles. You never have to leave your editor or chat interface.

Supported clients include Claude Code, Claude Desktop, Cursor, Codex, VS Code, Windsurf, Perplexity, ChatGPT, Gemini CLI, and Amazon Q.

Connect

Pick the path that matches where you'll use PingAura.

OAuth: for Claude.ai (recommended)

If you're using Claude on the web or desktop, this is the fastest setup. No keys to copy or paste.

  1. In Claude, go to Settings → Connectors → Add custom connector.
  2. Paste https://www.pingaura.ai/api/mcp.
  3. Claude opens a consent page on pingaura.ai. Sign in if you aren't already.
  4. Pick which workspace Claude should connect to (if you belong to more than one).
  5. Read your data is always on. Leave Modify your data ticked (recommended) so Claude can act on what it finds: create prompts, run audits, publish articles.
  6. Click Approve. Claude is connected, with all current tools ready.

You can disconnect any time from Claude's connector settings. See Connecting apps with OAuth for what happens to access when you do.

Full walk-through: Connecting apps with OAuth.

API key: for Claude Desktop, Cursor, Codex, VS Code, etc.

Anything that takes a header in a config file uses this path. Same access as OAuth, just configured once per machine.

  1. In your PingAura dashboard, go to Workspace settings → API & MCP.
  2. Click Create API Key, name it (e.g. "Cursor on my laptop"), and copy the key. You'll only see it once, so store it in a password manager.
  3. Drop it into your client's MCP config (see Client setup below) as either header:
    • Authorization: Key pa_xxx_yyy
    • Authorization: Bearer pa_xxx_yyy

Each API key is tied to a single workspace. Choose its scopes when you create it: Read, Write, or both. Ingest keys only send telemetry events and do not work with MCP. Only the workspace owner can create or revoke keys; other members can see existing ones.

Quick start

The fastest way to connect is with Claude Code:

claude mcp add pingaura --transport http https://www.pingaura.ai/api/mcp \
  --header "Authorization: Key YOUR_API_KEY"

Then ask Claude something like: "List my domains and their visibility scores"

Quick setup

Paste your API key to install PingAura directly into your editor.

PingAura API Key

Cursor iconInstall in CursorVS Code iconInstall in VS CodeClaude Code iconCopy Claude Code command

Enter your API key to enable install buttons.

About MCP clients

An MCP client is any application that speaks the Model Context Protocol: desktop apps, IDE extensions, CLI tools, and agent frameworks all qualify. PingAura uses the standard streamable HTTP transport, so you can use any client that supports streamable HTTP transport; just point it at https://www.pingaura.ai/api/mcp and supply your API key in the Authorization header.

Secret headers / API key in config

For clients that let you specify custom headers in a config file, the API key always goes in the Authorization header using one of these two forms:

Authorization: Key pa_xxx_yyy
Authorization: Bearer pa_xxx_yyy

Your API key is sensitive. Store it in an environment variable or a password manager. Do not commit it into version-controlled config files. Many clients support env-var interpolation (e.g. $PINGAURA_API_KEY) in their config; use that where available.

Client setup

OAuth or API key? Most modern MCP clients (Claude.ai, Claude Desktop, Claude Code, Cursor, recent versions of others) support OAuth: you point them at our URL and they handle the consent flow in your browser, no key needed. The configs below show both paths where the client supports OAuth: try OAuth first, fall back to API key only if your client requires headers in config or runs in an environment without a browser.

Claude Code (CLI)

With OAuth (no API key needed):

claude mcp add pingaura --transport http https://www.pingaura.ai/api/mcp

Claude Code detects our auth challenge, opens the consent screen on pingaura.ai in your browser, you sign in and approve, and the CLI receives the token. Tokens refresh automatically.

With an API key:

claude mcp add pingaura --transport http https://www.pingaura.ai/api/mcp \
  --header "Authorization: Key YOUR_API_KEY"

Verify either way with:

claude mcp list

No restart required.

Claude Desktop

With OAuth: in Claude Desktop, go to Settings → Connectors → Add custom connector and paste https://www.pingaura.ai/api/mcp. Approve in the browser when it opens. No config file edit needed.

With an API key, edit the config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "pingaura": {
      "url": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key YOUR_API_KEY"
      }
    }
  }
}

Restart Claude Desktop after saving.

Cursor

With OAuth (Cursor 0.45+): in Settings → Cursor Settings → MCP, click Add new MCP server, paste https://www.pingaura.ai/api/mcp, leave headers empty, and approve in the browser when prompted.

With an API key, add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

{
  "mcpServers": {
    "pingaura": {
      "url": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key YOUR_API_KEY"
      }
    }
  }
}

Or go to Settings > Cursor Settings > MCP and add the server there. No restart required.

Codex

Codex supports MCP servers in the CLI and IDE extension.

Use the PingAura MCP endpoint:

  • Server URL: https://www.pingaura.ai/api/mcp
  • Authorization header: Key YOUR_API_KEY

For a step-by-step guide, follow OpenAI's Codex MCP setup. Use the PingAura server URL and API key shown above.

VS Code (GitHub Copilot)

Add to .vscode/mcp.json in your project:

{
  "inputs": [
    {
      "type": "promptString",
      "id": "pingaura-api-key",
      "description": "PingAura API Key",
      "password": true
    }
  ],
  "servers": {
    "pingaura": {
      "type": "http",
      "url": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key ${input:pingaura-api-key}"
      }
    }
  }
}

VS Code will prompt you for the API key on first use.

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "pingaura": {
      "serverUrl": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key YOUR_API_KEY"
      }
    }
  }
}

Note: Windsurf uses serverUrl instead of url.

Amazon Q Developer

Add to ~/.aws/amazonq/mcp.json:

{
  "mcpServers": {
    "pingaura": {
      "type": "http",
      "url": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key YOUR_API_KEY"
      }
    }
  }
}

Perplexity

Perplexity supports custom remote MCP connectors on paid plans.

  1. Open the Perplexity app and go to Account Settings > Connectors.
  2. Click + Custom connector and select Remote.
  3. Fill in the details:
    • Display name: PingAura
    • MCP Server URL: https://www.pingaura.ai/api/mcp
    • Description: AI visibility scores, site audits, articles, and competitor data from PingAura
    • Authentication: Select API Key and enter your PingAura API key
    • Transport: Select Streamable HTTP
  4. Check the acknowledgement box and click Add.
  5. Click the PingAura connector card to enable it.

Once enabled, ask Perplexity questions like "What's my latest visibility score?" It will query PingAura directly.

ChatGPT

ChatGPT supports remote MCP servers through Developer Mode. This is available on Plus, Pro, and Team plans.

  1. Open ChatGPT on the web or desktop app.
  2. Open a new chat and enable Developer Mode from the model picker.
  3. Click the Tools icon (wrench) in the composer, then Add MCP connector.
  4. Enter the details:
    • Name: PingAura
    • URL: https://www.pingaura.ai/api/mcp
    • Authentication: Select API Key and enter your PingAura API key
  5. Click Add to save.

Once connected, ChatGPT can call PingAura tools in Developer Mode chats.

Gemini CLI

Edit ~/.gemini/settings.json (global) or .gemini/settings.json (project):

{
  "mcpServers": {
    "pingaura": {
      "httpUrl": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key YOUR_API_KEY"
      }
    }
  }
}

Note: Gemini CLI uses httpUrl instead of url.

Cline (VS Code extension)

Cline is a VS Code extension for AI-assisted coding. Its MCP settings live in a per-machine JSON file.

Edit ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json (macOS) or the Windows equivalent under %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\:

{
  "mcpServers": {
    "pingaura": {
      "url": "https://www.pingaura.ai/api/mcp",
      "headers": {
        "Authorization": "Key YOUR_API_KEY"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Reload VS Code after saving. Cline picks up the new server automatically.

AnythingLLM (self-hosted)

AnythingLLM is a self-hosted AI platform for building RAG pipelines and running agents. Add PingAura under the MCP server settings.

  1. Open Settings → Tools → MCP Servers.
  2. Click Add MCP Server.
  3. Fill in:
    • Name: PingAura
    • Type: Streamable HTTP
    • URL: https://www.pingaura.ai/api/mcp
  4. Under Headers, add Authorization: Key YOUR_API_KEY.
  5. Click Save and enable the server.

PingAura tools are available to agents and custom AI workflows immediately.

Continue (open-source)

Continue is an open-source AI coding assistant that works inside VS Code and JetBrains. Add PingAura to ~/.continue/config.json:

{
  "mcpServers": [
    {
      "name": "pingaura",
      "transport": {
        "type": "streamable-http",
        "url": "https://www.pingaura.ai/api/mcp",
        "headers": {
          "Authorization": "Key YOUR_API_KEY"
        }
      }
    }
  ]
}

No restart required. Continue detects config changes and reconnects.

Zed (editor)

Zed supports MCP context servers via ~/.config/zed/settings.json. Add a context_servers entry:

{
  "context_servers": {
    "pingaura": {
      "settings": {
        "url": "https://www.pingaura.ai/api/mcp",
        "headers": {
          "Authorization": "Key YOUR_API_KEY"
        }
      }
    }
  }
}

Restart Zed after saving. The PingAura tools will appear in the Assistant panel.

Goose (by Block)

Goose is an open-source AI agent CLI from Block. Add PingAura as an extension in ~/.config/goose/config.yaml:

extensions:
  pingaura:
    type: streamable_http
    url: https://www.pingaura.ai/api/mcp
    headers:
      Authorization: "Key YOUR_API_KEY"
    enabled: true

No restart needed. Run goose and PingAura tools are available in the session.

JetBrains AI Assistant (IntelliJ / PyCharm / WebStorm)

JetBrains AI Assistant supports remote MCP servers through the IDE settings UI.

  1. Open Settings (⌘, on macOS, Ctrl+Alt+S on Windows/Linux).
  2. Navigate to Tools → AI Assistant → MCP Servers.
  3. Click + to add a new server and fill in:
    • Name: PingAura
    • URL: https://www.pingaura.ai/api/mcp
    • Headers: add Authorization → Key YOUR_API_KEY
  4. Click Apply and OK.

The PingAura tools will be available in AI Assistant chat immediately. No IDE restart required.

Cherry Studio (desktop)

Cherry Studio is a desktop AI client with a built-in MCP server manager.

  1. Open Settings → MCP Servers.
  2. Click Add Server.
  3. Fill in:
    • Name: PingAura
    • Type: Streamable HTTP
    • URL: https://www.pingaura.ai/api/mcp
  4. Under Headers, add Authorization: Key YOUR_API_KEY.
  5. Click Save and toggle the server on.

PingAura tools are ready in new conversations immediately.

5ire (desktop)

5ire is a desktop AI assistant with a tools panel for MCP integration.

  1. Open the Tools section from the left sidebar.
  2. Click New to add an MCP server.
  3. Fill in:
    • Name: PingAura
    • URL: https://www.pingaura.ai/api/mcp
  4. Add a custom header: Authorization: Key YOUR_API_KEY.
  5. Save and enable the server.

The PingAura tools appear in the tools list and are available in chat.

Open WebUI (self-hosted)

Open WebUI is a self-hosted ChatGPT-style interface that supports MCP tool servers. Add PingAura under the Tools settings.

  1. Open Settings → Tools → MCP Servers.
  2. Click Add Server and fill in:
    • Name: PingAura
    • URL: https://www.pingaura.ai/api/mcp
  3. Add a custom header: Authorization: Key YOUR_API_KEY.
  4. Save the server configuration.
  5. In your model settings, make sure Function Calling is enabled. Open WebUI only routes tool calls when the active model has function calling turned on.

PingAura tools will be available in new conversations once function calling is active.

Sourcegraph Cody (VS Code / JetBrains)

Cody is Sourcegraph's AI coding assistant. It supports remote MCP servers through the Cody settings panel.

  1. Open the Cody sidebar in VS Code or your JetBrains IDE.
  2. Navigate to Cody Settings → MCP Servers.
  3. Click Add Server and fill in:
    • Name: PingAura
    • URL: https://www.pingaura.ai/api/mcp
  4. Add a custom header: Authorization: Key YOUR_API_KEY.
  5. Save. Cody picks up the new server without a restart.

PingAura tools are available in Cody chat and inline edit sessions.

Tome (by Runebook)

Tome is an MCP-first desktop AI client. Adding MCP servers is a first-class workflow.

  1. Open the Tome app and go to Settings → Integrations.
  2. Click Add MCP Server.
  3. Fill in:
    • Name: PingAura
    • URL: https://www.pingaura.ai/api/mcp
  4. Add a custom header: Authorization: Key YOUR_API_KEY.
  5. Save. Tome connects immediately. No restart required.

LibreChat (open-source)

LibreChat is a self-hosted ChatGPT alternative. Add PingAura to your librechat.yaml config file under the mcpServers key:

mcpServers:
  pingaura:
    type: streamable-http
    url: https://www.pingaura.ai/api/mcp
    headers:
      Authorization: "Key YOUR_API_KEY"

Restart your LibreChat instance after saving. PingAura tools will be available to all configured AI endpoints.

Other MCP clients

The following clients also support PingAura via the standard streamable HTTP transport. Use the same URL (https://www.pingaura.ai/api/mcp) and Authorization header pattern shown above. Refer to each client's documentation for where to configure remote MCP servers:

  • Roo Code: VS Code extension; supports MCP servers in its settings panel
  • Witsy: desktop AI assistant; MCP configured in its Integrations settings
  • Bolt.diy: open-source AI coding assistant; MCP configured in settings
  • Msty: desktop AI client; add PingAura under Settings → MCP Servers
  • Jan: offline-first desktop AI; add PingAura as a remote MCP tool in Extensions → MCP
  • Pinokio: AI app browser; configure PingAura as an MCP server in its tool settings

Available tools

Once connected, your AI assistant has access to these tools:

Read tools

ToolDescription
list-domainsList all domains in your account
get-domainGet details for a specific domain
list-competitorsList competitor domains tracked for a domain
list-visibility-runsList visibility analysis runs. With one_per_day, list one completed run per day (that day's Latest run, the one the Visibility page shows), each with its day, in time_zone (UTC by default). Each run lists the engines it asked and any that answered fewer prompts than expected
get-visibility-summaryGet scores, coverage, and competitor comparison for a run. Competitor lists hold the top 10 brands plus yours, with a count of the rest; detail: "full" returns every list, per engine too
get-visibility-scoreGet the AI AuraScore, Mention Rate and Share of Voice for one slice (prompt query type, topic, custom filters, engine) over a date range, the Latest run, a completed run's run_id, or a run_date (YYYY-MM-DD from 2020-01-01 to 2100-12-31, read in time_zone, UTC by default). The result names the scored run in scope.run_id; a chosen run also comes back with its completion time and a note when it predates a scoring change
compare-visibility-runsCompare 2-4 runs (run ids or days) across 1-20 slices in one table, at most 40 cells (runs × slices). Each cell gives AI AuraScore, Mention Rate, Share of Voice, Rank and Sentiment, scored as the Visibility page scores that run. Runs come back oldest first. Optionally adds competitor rows for the first slice: the top 30 by the newest run's Rank, with a count of the rest. A cell for a slice with no answers in that run is marked noAnswers
get-prompt-scoresGet visibility scores for tracked prompts/queries, highest first or, with order: "score_asc", lowest first
list-prompt-filtersList the custom filters a domain declares, with their values
list-prompt-topicsList a domain's prompt topics with their ids
list-site-auditsList site health audits, newest first, each with its page, scores, issue count and performance
get-audit-issuesGet issues from an audit (filter by severity or category)
list-articlesList AI-generated articles
get-articleGet full article content
list-site-pagesList discovered pages for a domain
get-account-infoGet account details and subscription status
get-quota-usageGet used, limit and remaining for prompts (active prompts), articles (this billing period), site audits and chat
get-site-health-summaryGet site health summary with scores, issue counts, and priority fixes
get-openai-ads-accountGet your ChatGPT Ads account. The ChatGPT Ads tools need ChatGPT Ads connected for the domain
list-openai-ads-campaignsList ChatGPT Ads campaigns
get-openai-ads-campaignGet one campaign
list-openai-ads-ad-groupsList ad groups
get-openai-ads-ad-groupGet one ad group
list-openai-ads-adsList ads
get-openai-ads-adGet one ad, including its creative
get-openai-ads-account-insightsSpend and performance for the whole account over a date range
get-openai-ads-campaign-insightsSpend and performance for one campaign over a date range
get-openai-ads-ad-group-insightsSpend and performance for one ad group over a date range
get-openai-ads-ad-insightsSpend and performance for one ad over a date range

Write tools

ToolDescription
create-promptCreate a new visibility prompt for a domain
archive-promptArchive a prompt (sets status to archived)
restore-promptRestore an archived prompt to active (subject to quota)
move-prompt-to-topicMove a prompt to a different topic
create-prompt-topicCreate a new prompt topic for a domain
update-prompt-topicRename a prompt topic
delete-prompt-topicDelete a prompt topic. It must hold no prompts, archived ones included
update-articleUpdate article metadata (title, slug, status, keywords, meta description)
publish-articlePublish an article
archive-articleArchive an article (sets status to archived)
run-site-auditQueue a site health audit for tracked pages
update-issue-statusMark a site health issue as resolved or reopen it
add-competitorAdd competitor domains to tracking. One that is already tracked keeps its name and aliases
update-competitorUpdate a competitor's display name or aliases (these decide which answers count as a mention)
delete-competitorRemove a competitor from tracking
sync-sitemapScan a domain's sitemap to find and track pages. Needed before the first site audit
update-prompt-filtersSet custom filter values on a prompt. The valid keys and values are the ones list-prompt-filters returns
set-prompt-filter-definitionsReplace the custom filters a domain declares (up to 5 filters, 50 values each). Send the full list: anything left out is removed

Hosted page tools

These work on the pages PingAura writes and hosts for a domain. They need Lead Pages on your plan; without it, each one replies that Lead Pages is not on the current plan. Anything that takes a live page down (rejecting it, sending it for a rewrite, or retiring it) needs a workspace owner.

ToolDescription
list-hosted-pagesList a domain's hosted pages and the review status of each
get-hosted-pageGet one hosted page: its text, the evidence behind it, and any claims the fact check flagged
dispose-hosted-claimMark a flagged claim as accepted or rejected. Every flagged claim needs a decision before the page can be approved
acknowledge-hosted-self-checkRecord that a person has read a page the automatic fact check could not
request-hosted-page-regenerationSend a page back to be rewritten, with a note on what to change
reject-hosted-pageReject a page and close its topic, so it is not proposed again. A live page starts retiring
retire-hosted-pageTake a live page off your domain, optionally redirecting it to another live page

Example prompts

Once PingAura is connected, try asking your AI assistant:

  • "Show me all my domains and their current status"
  • "What's the latest visibility score for example.com?"
  • "List the critical audit issues for my homepage"
  • "Show me all published articles and their word counts"
  • "Compare my visibility scores against competitors"
  • "Which of my pages have critical audit issues?"
  • "How are my ChatGPT Ads campaigns doing this month?"
  • "Get the AEO issues from the latest audit"
  • "Archive the prompt about delivery services"
  • "Add hubspot.com as a competitor for my domain"
  • "Mark that broken-links issue as resolved"
  • "Publish my latest article"
  • "How much of my prompt quota have I used?"

Access control

  • API keys are tied to one workspace. They only return that workspace's data.
  • Only the workspace owner can create, update or revoke API keys.
  • Other members can see existing keys but cannot manage them.
  • Keys support optional expiration dates.
  • Revoked keys are immediately rejected.

Troubleshooting

"Unauthorized" error

  • Check that your API key is correct and not revoked.
  • Ensure the header format is Authorization: Key pa_xxx_yyy or Authorization: Bearer pa_xxx_yyy.

Tools not showing up

  • Run claude mcp list (Claude Code) or check MCP status in your client.
  • Verify the URL is exactly https://www.pingaura.ai/api/mcp.

Connection timeout

  • If you're behind a firewall, ensure outbound HTTPS to www.pingaura.ai is allowed.

Chat with us

Home Page

Sign In Sign Up

{"@context":"https://schema.org","@type":"WebSite","name":"PingAura","url":"https://www.pingaura.ai","potentialAction":{"@type":"SearchAction","target":"https://www.pingaura.ai/search?q={search_term_string}","query-input":"required name=search_term_string"}}