Pengu.inc MCP server

• Addresshttps://audn.ai/api/mcpnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on audn.ai when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-27
• Tools43
• Server calls itselfaudn-ai
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 132 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer468 ms
• Space in an agent's context≈ 2,740 tokensthe definitions of all its tools (43), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 43 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• audn_assess_agent

  Use this when the user wants a quick risk scorecard for a voice agent based on phone number, inbound/outbound setup, guardrails, and failure modes. Returns top risks and recommended adversarial tests.

• audn_api.executeCampaign

  Execute a security testing campaign. Supports both voice and text campaigns: - Voice campaigns: Initiates phone calls using the configured voice platform - Text campaigns: Sends API requests to the configured text agent endpoint The…

• audn_api.getCampaignStatus

  Retrieve current execution status details for a campaign

• audn_api.getCampaign

  Retrieve the current status and results of a campaign

• audn_api.deleteCampaign

  Delete a campaign by ID

• audn_api.listCampaigns

  Retrieve a list of campaigns

• audn_api.createCampaign

  Create a new testing campaign

• audn_api.listAgents

  Retrieve a list of voice agents

• audn_api.createAgent

  Create a new voice agent

• audn_api.getAgent

  Retrieve a specific agent by ID

• audn_api.updateAgent

  Update an existing agent

• audn_api.deleteAgent

  Delete an agent by ID

• audn_api.verifyAgentPhone

  Send or verify phone verification codes for agents

• audn_api.verifyTextAgent

  Verify a text agent by sending a test "hello" message to the configured API endpoint. Returns verification status, response preview, and latency information.

• audn_api.listScenarios

  Retrieve available attack scenarios

• audn_api.listUserScenarios

  Retrieve reusable scenarios available to the user

• audn_api.createScenario

  Create a new attack scenario tied to a campaign

• audn_api.getScenario

  Retrieve details for a scenario

• audn_api.updateScenario

  Update an existing scenario

• audn_api.deleteScenario

  Delete a scenario by ID

• audn_api.listCustomScenarios

  Retrieve custom scenarios created by the user

• audn_api.createCustomScenario

  Create a custom scenario

• audn_api.updateCustomScenario

  Update an existing custom scenario

• audn_api.executeCustomScenario

  Execute a custom scenario test run

• audn_api.listResults

  Retrieve test results with pagination and filters

• audn_api.getResultById

  Retrieve detailed information for a specific test result

• audn_api.getResults

  Retrieve test results for campaigns

• audn_api.listReports

  Retrieve a list of reports with optional pagination and filters

• audn_api.generateReport

  Generate compliance or vulnerability report

• audn_api.getReport

  Retrieve report details by ID

• audn_api.regenerateReport

  Regenerate report artifacts for a report

• audn_api.listApiKeys

  Retrieve a list of API keys

• audn_api.createApiKey

  Create a new API key

• audn_api.revokeApiKey

  Revoke an existing API key

• audn_api.revokeApiKeyLegacy

  Revoke an API key using key_id identifier

• audn_api.rotateApiKeyLegacy

  Rotate an API key secret by key_id

• audn_api.listAuditLogs

  Retrieve a list of audit logs

• audn_api.getCurrentUserProfile

  Retrieve the authenticated user's profile information

• audn_api.updateCurrentUserProfile

  Update the authenticated user's profile

• audn_api.getHumeAudio

  Retrieve a signed URL to stream reconstructed audio from Hume for a given chat

• audn_api.listVulnerabilities

  Retrieve a list of detected vulnerabilities

• audn_api.getCampaignRecoveryHealthGlobal

  Retrieve global status of campaign recovery workers and stuck campaigns

• audn_api.recoverCampaigns

  Kick off recovery process for all eligible stuck campaigns