PyAI Voice AI MCP server
io.github.atomsai/pyaiatomsaistreamable-httpv0.5.26Scanned
Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.
59 tools: 10 can delete or cancel things, 12 change things and 37 only read.
- Reads private data · 0
- Reads text others write · 17
- Can send data out · 2
- 13 findings
Tools listed without sign-in. Remote posture
With Anlyon
10 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the PyAI Voice AI MCP server can do
The PyAI Voice AI MCP server is published by the GitHub account atomsai. It has 59 tools. It can delete or cancel things (10 tools: configure_amd, enable_recap, telephony_bind_number, telephony_create_call and 6 more) and create or change data (12 tools: synthesize_speech, create_transcription_job, create_recap, calls_list and 8 more). 37 tools only read.
17 tools bring in text other people can write (create_transcription_job, configure_amd, enable_recap and 14 more); 2 tools can send data out of your system (create_transcription_job and publish_website_widget).
The fixed checks matched 13 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 20, 2026, version 0.5.26.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
59 tools
Deletes or cancels 10Claude Code: deny
configure_amdSet the PyAI AMD (answering-machine detection) operating point + webhook (POST /v1/amd/config).Reads text others writeNo findings
Why it is in this group
- The description's first verb is "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Set the PyAI AMD (answering-machine detection) operating point + webhook (POST /v1/amd/config). `aggressiveness` is one dial 0-1: near 0 is human-safe (never hang up on a person), near 1 fires 'machine' fast. The realtime detection itself is a Twilio Media Streams WebSocket (wss /v1/amd/stream), a one-line-TwiML drop-in, not an MCP tool.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
configure_traceConfigure Trace compliance monitoring for the selected workspace.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Configure Trace compliance monitoring for the selected workspace.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
draft_website_widgetSave an unpublished website voice widget for a saved agent in the connected project.Reads text others write1 finding
Why it is in this group
- The description's first verb is "save": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.body.properties.origin.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.body.properties.origin.description: ".... No wildcard, path, query, fragment or credentials."
Description, as the server wrote it Save an unpublished website voice widget for a saved agent in the connected project. Specify the exact HTTPS origin and both daily session limits. The hosted widget sends visitor microphone audio to PyAI. Its session quotas cannot enforce a hard total spending cap. To replace a draft, first preview it and pass its expected_revision. A published widget cannot be edited here.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
enable_recapEnable Recap for the key's org (PUT /v1/recap/config).Reads text others writeNo findings
Why it is in this group
- The name "enable_recap" says "enable": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Enable Recap for the key's org (PUT /v1/recap/config). Sandbox keys already mint with Recap on; call this to set a webhook or pack, or to enable Recap on a signup/live key. Requires recap:configure.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
publish_website_widgetPublish the managed website voice widget only after the user explicitly approves the displayed project, origins, limits and embed for that exact preview revision.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "publish_website_widget" says "publish": a word for a change that another call does not undo.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "publish_website_widget" says "publish": it sends or publishes something to other people.
Description, as the server wrote it Publish the managed website voice widget only after the user explicitly approves the displayed project, origins, limits and embed for that exact preview revision. Set body.approved=true and pass body.revision. Return the snippet verbatim. The hosted widget sends visitor microphone audio to PyAI. Sessions may consume project credit and session quotas cannot enforce a hard total spending cap. After an uncertain result, preview the widget before any further action.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
set_agent_knowledgeReplace the knowledge bases bound to an Agent.No findings
Why it is in this group
- The name "set_agent_knowledge" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Replace the knowledge bases bound to an Agent. Read its existing bindings first.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
set_agent_toolsReplace the tools bound to an Agent.Reads text others write2 findings
Why it is in this group
- The name "set_agent_tools" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ately in the PyAI console. Never supply credentials."
- Info
The input schema at properties.body.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.body.description: "...gs are preserved for retained bindings. Credentials and connection settings are not accepte..."
Description, as the server wrote it Replace the tools bound to an Agent. Read the current Agent first; this replaces its bindings. Use saved tool IDs; configure connection settings privately in the PyAI console. Never supply credentials.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
telephony_bind_numberBind an owned number to an Agent using body.agent_id; null unassigns.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Bind an owned number to an Agent using body.agent_id; null unassigns. Read existing bindings first. Changes inbound routing.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
telephony_create_callPlace a real outbound call only to a user-authorized destination.Reads text others writeNo findings
Why it is in this group
- The name "telephony_create_call" says "create": a word for a change.
- The input addresses people (input.body.to): what it sends cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Place a real outbound call only to a user-authorized destination. Requires confirm=true and a stable idempotency_key. This is not a sandbox simulation. Preserve the returned ID; never redial after an uncertain timeout.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
update_agentUpdate a voice Agent profile.Reads text others write3 findings
Why it is in this group
- The name "update_agent" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ately in the PyAI console. Never supply credentials."
- Info
The input schema at properties.body.properties.platform_guidance.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.body.properties.platform_guidance.description: "...Requires an explicitly enrolled server credential; ordinary customer keys receive 403. Se..."
- Info
The input schema at properties.body.properties.tools.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.body.properties.tools.description: "...gs are preserved for retained bindings. Credentials and connection settings are not accepte..."
Description, as the server wrote it Update a voice Agent profile. Read it first and change only user-requested fields. Use saved tool IDs; configure connection settings privately in the PyAI console. Never supply credentials.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
Changes things 12Claude Code: ask
calls_getRead the current state of an outbound call by returned ID.1 finding
Why it is in this group
- The name "calls_get" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "calls_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "calls_get" says "call": a word for a change.
Description, as the server wrote it Read the current state of an outbound call by returned ID. dispatch_unknown needs inspection, not another call. Recap and Omni recordings are separate resources.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
calls_listList outbound calls and normalized network outcomes before retrying a dispatch.1 finding
Why it is in this group
- The name "calls_list" says "call": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "calls_list" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "calls_list" says "call": a word for a change.
Description, as the server wrote it List outbound calls and normalized network outcomes before retrying a dispatch.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
create_agentCreate a reusable voice Agent profile: persona, greeting, voice, language, tools and knowledge.Reads text others write3 findings
Why it is in this group
- The name "create_agent" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ately in the PyAI console. Never supply credentials."
- Info
The input schema at properties.body.properties.platform_guidance.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.body.properties.platform_guidance.description: "...Requires an explicitly enrolled server credential; ordinary customer keys receive 403. Se..."
- Info
The input schema at properties.body.properties.tools.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.body.properties.tools.description: "...gs are preserved for retained bindings. Credentials and connection settings are not accepte..."
Description, as the server wrote it Create a reusable voice Agent profile: persona, greeting, voice, language, tools and knowledge. Does not place a call. Use saved tool IDs; configure connection settings privately in the PyAI console. Never supply credentials.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_dubFetch audio from the user-authorized HTTPS source URL and start a translation and dubbing job.Reads text others writeNo findings
Why it is in this group
- The name "create_dub" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Fetch audio from the user-authorized HTTPS source URL and start a translation and dubbing job. Accesses an external source and consumes usage. Keep job_id and poll get_dub_job; do not submit again after a timeout.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_recapSubmit speaker-labelled utterances and get a recap.call (POST /v1/recap/calls/{call_id}).Reads text others writeNo findings
Why it is in this group
- The name "create_recap" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Submit speaker-labelled utterances and get a recap.call (POST /v1/recap/calls/{call_id}). Requires recap:create and Recap enabled. To poll with get_recap, also request recap:lookup.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
create_trace_rule_packCreate a workspace Trace compliance rule pack.No findings
Why it is in this group
- The name "create_trace_rule_pack" says "create": a word for a change.
Description, as the server wrote it Create a workspace Trace compliance rule pack. This creates persistent configuration.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_transcription_jobSubmit an async speech-to-text job for an audio URL (https).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "create_transcription_job" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.channel): what the tool writes goes there.
Description, as the server wrote it Submit an async speech-to-text job for an audio URL (https). Returns a job_id; poll with get_transcription_job. Supports diarization.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
direct_cast_scriptTurn a narration script into directed Cast lines before rendering.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Turn a narration script into directed Cast lines before rendering. Consumes usage.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
preview_cast_lineGenerate one directed Cast line.No findings
Why it is in this group
- The name "preview_cast_line" says "preview": a word for reading.
- The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generate one directed Cast line. Consumes usage. Check get_cast_capabilities for supported voice, emotion and intensity.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
render_castSubmit script text or directed lines using one top-level voice from get_cast_capabilities for the entire render.No findings
Why it is in this group
- The description's first verb is "submit": a word for a change.
Description, as the server wrote it Submit script text or directed lines using one top-level voice from get_cast_capabilities for the entire render. Per-line voices and a console project are not required or supported inputs. Returns a job; preserve its ID, poll get_cast_render and retrieve get_cast_audio when done. Consumes usage; do not resubmit on timeout.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
synthesize_speechGenerate speech from input.No findings
Why it is in this group
- The description's first verb is "generate": a word for a change.
Description, as the server wrote it Generate speech from input. Consumes usage in the connected project; live usage can be billed. Before generation, use whoami to verify project, environment, scopes, credit and limits. Returns inline MCP audio or an expiring resource_link, never a local file path. Host playback support varies. For integration code only, use get_started.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
transcribe_audioTranscribe a small audio attachment supplied as base64 (up to 8 MiB decoded).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Transcribe a small audio attachment supplied as base64 (up to 8 MiB decoded). Returns the synchronous transcript without diarization controls. For word timestamps and speaker labels, use create_transcription_job with diarize=true for mono or channel=true for stereo, then get_transcription_job. Consumes usage.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 37Show 37 read-only tools
discover_toolsFind the right PyAI tools and a short recipe for speech, STT, LiveKit or Pipecat integration, voice agents, compliance, summaries, dubbing or narration.1 finding
Why it is in this group
- The description's first verb is "find": a word for reading.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...ce, summaries, dubbing or narration. No credentials or usage."
Description, as the server wrote it Find the right PyAI tools and a short recipe for speech, STT, LiveKit or Pipecat integration, voice agents, compliance, summaries, dubbing or narration. No credentials or usage.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_agentRead a saved voice Agent profile and its current configuration.No findings
Why it is in this group
- The name "get_agent" says "get": a word for reading.
Description, as the server wrote it Read a saved voice Agent profile and its current configuration.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_amd_callGet one PyAI AMD decision by call id (GET /v1/amd/calls/{id}): who/what answered, with the reason.No findings
Why it is in this group
- The name "get_amd_call" says "get": a word for reading.
Description, as the server wrote it Get one PyAI AMD decision by call id (GET /v1/amd/calls/{id}): who/what answered, with the reason.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_cast_audioRetrieve completed Cast narration as playable audio or a download.No findings
Why it is in this group
- The name "get_cast_audio" says "get": a word for reading.
Description, as the server wrote it Retrieve completed Cast narration as playable audio or a download.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_cast_capabilitiesDiscover Cast voices, emotions, formats and supported rendering capabilities.No findings
Why it is in this group
- The name "get_cast_capabilities" says "get": a word for reading.
Description, as the server wrote it Discover Cast voices, emotions, formats and supported rendering capabilities.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_cast_renderCheck a durable Cast render job.No findings
Why it is in this group
- The name "get_cast_render" says "get": a word for reading.
Description, as the server wrote it Check a durable Cast render job. Preserve the original job ID.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_dub_audioRetrieve completed dubbed audio as a playable result or download.No findings
Why it is in this group
- The name "get_dub_audio" says "get": a word for reading.
Description, as the server wrote it Retrieve completed dubbed audio as a playable result or download. Call only when get_dub_job reports done.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_dub_capabilitiesRead currently supported Dub input and output languages before submitting a translation.No findings
Why it is in this group
- The name "get_dub_capabilities" says "get": a word for reading.
Description, as the server wrote it Read currently supported Dub input and output languages before submitting a translation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_dub_jobRetrieve the status and available results of an existing dubbing job by job_id.No findings
Why it is in this group
- The name "get_dub_job" says "get": a word for reading.
Description, as the server wrote it Retrieve the status and available results of an existing dubbing job by job_id. This read does not start or repeat a job. Poll pending/processing states without resubmitting.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_recapRead one Recap by call id (GET /v1/recap/calls/{call_id}).No findings
Why it is in this group
- The name "get_recap" says "get": a word for reading.
Description, as the server wrote it Read one Recap by call id (GET /v1/recap/calls/{call_id}). When complete, `record` is recap.record.v1 (tldr, summary, action_items, disposition, next_steps, talk_ratio, signals, fields). Requires recap:lookup and Recap enabled.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_recap_configRead Recap summarization configuration before changing it.No findings
Why it is in this group
- The name "get_recap_config" says "get": a word for reading.
Description, as the server wrote it Read Recap summarization configuration before changing it.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_startedReturn a concise, correct quickstart for building with PyAI (auth, SDK install, TTS/STT/realtime snippets, error handling).No findings
Why it is in this group
- The name "get_started" says "get": a word for reading.
Description, as the server wrote it Return a concise, correct quickstart for building with PyAI (auth, SDK install, TTS/STT/realtime snippets, error handling). No key or network needed, read this before writing PyAI code so you use the right endpoints and the official SDK.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_trace_configInspect Trace call-compliance configuration.No findings
Why it is in this group
- The name "get_trace_config" says "get": a word for reading.
Description, as the server wrote it Inspect Trace call-compliance configuration.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_trace_exposureRead aggregate compliance exposure for the workspace.No findings
Why it is in this group
- The name "get_trace_exposure" says "get": a word for reading.
Description, as the server wrote it Read aggregate compliance exposure for the workspace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_trace_interactionRead one monitored interaction and its compliance evidence.No findings
Why it is in this group
- The name "get_trace_interaction" says "get": a word for reading.
Description, as the server wrote it Read one monitored interaction and its compliance evidence.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_transcription_jobGet the status + result of a transcription job by id.No findings
Why it is in this group
- The name "get_transcription_job" says "get": a word for reading.
Description, as the server wrote it Get the status + result of a transcription job by id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_agentsList saved voice Agent profiles before creating or changing one.No findings
Why it is in this group
- The name "list_agents" says "list": a word for reading.
Description, as the server wrote it List saved voice Agent profiles before creating or changing one.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_amd_callsList recent PyAI AMD decisions (GET /v1/amd/calls).No findings
Why it is in this group
- The name "list_amd_calls" says "list": a word for reading.
Description, as the server wrote it List recent PyAI AMD decisions (GET /v1/amd/calls). Each carries answered_by (human/voicemail/ivr/screening/sit_invalid/…), answered_by_twilio (Twilio's enum, for routing parity), confidence, decision_ms, and the word-level reason.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_modelsList the available PyAI models (catalog).No findings
Why it is in this group
- The name "list_models" says "list": a word for reading.
Description, as the server wrote it List the available PyAI models (catalog). No arguments.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_published_website_widgetsLook up published managed website voice widgets in the connected project without an agent ID.Reads text others writeNo findings
Why it is in this group
- The name "list_published_website_widgets" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "list_published_website_widgets" says "list" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "website": it reads web pages, which anyone can write.
Description, as the server wrote it Look up published managed website voice widgets in the connected project without an agent ID. Read their public embed snippets, exact origins and effective daily session limits. Follow next_cursor while has_more before concluding no match. Ask which widget if multiple match. This read does not create a widget or start a session.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_recap_callsList existing Recap records for the organization (GET /v1/recap/calls).No findings
Why it is in this group
- The name "list_recap_calls" says "list": a word for reading.
Description, as the server wrote it List existing Recap records for the organization (GET /v1/recap/calls). Requires recap:lookup and Recap enabled.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_trace_findingsFind compliance findings with source evidence.No findings
Why it is in this group
- The name "list_trace_findings" says "list": a word for reading.
Description, as the server wrote it Find compliance findings with source evidence. Findings are signals for review, not legal conclusions.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_trace_interactionsFind monitored calls and interactions for compliance review.Reads text others writeNo findings
Why it is in this group
- The name "list_trace_interactions" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "find" and "review": it reads comments, which other people can write.
Description, as the server wrote it Find monitored calls and interactions for compliance review.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_trace_rule_packsDiscover available Trace compliance rule packs before enabling monitoring.No findings
Why it is in this group
- The name "list_trace_rule_packs" says "list": a word for reading.
Description, as the server wrote it Discover available Trace compliance rule packs before enabling monitoring.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_trace_violationsList Trace rule violations for compliance review.Reads text others writeNo findings
Why it is in this group
- The name "list_trace_violations" says "list": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "list" and "review": it reads comments, which other people can write.
Description, as the server wrote it List Trace rule violations for compliance review.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_transcription_jobsFind existing audio processing and transcription jobs before submitting duplicates.No findings
Why it is in this group
- The name "list_transcription_jobs" says "list": a word for reading.
Description, as the server wrote it Find existing audio processing and transcription jobs before submitting duplicates.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_voicesList PyAI stock + cloned voices.No findings
Why it is in this group
- The name "list_voices" says "list": a word for reading.
Description, as the server wrote it List PyAI stock + cloned voices. Optionally filter by gender or region. Use a returned voice id as the `voice` for synthesize_speech.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
omni_get_callRead an Omni session's transcript, recording availability and summary.No findings
Why it is in this group
- The name "omni_get_call" says "get": a word for reading.
Description, as the server wrote it Read an Omni session's transcript, recording availability and summary. For outbound calls use artifacts.omni_call_id from calls_get.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
omni_get_recordingGet the canonical authenticated recording resource URL.Reads text others writeNo findings
Why it is in this group
- The name "omni_get_recording" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Get the canonical authenticated recording resource URL. Requires response=url. This URL is not public playable audio; recording must have been enabled.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
omni_get_summaryRead the structured summary for an Omni call when generated; a missing summary is not an empty result.No findings
Why it is in this group
- The name "omni_get_summary" says "get": a word for reading.
Description, as the server wrote it Read the structured summary for an Omni call when generated; a missing summary is not an empty result.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
omni_get_transcriptRead the complete Omni call transcript through the authenticated API.No findings
Why it is in this group
- The name "omni_get_transcript" says "get": a word for reading.
Description, as the server wrote it Read the complete Omni call transcript through the authenticated API.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
omni_list_callsList Omni sessions, including inbound calls.No findings
Why it is in this group
- The name "omni_list_calls" says "list": a word for reading.
Description, as the server wrote it List Omni sessions, including inbound calls. Filter by session_label and preserve each returned call_id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
openapi_getFetch live API operation discovery with a SHA-256 digest.No findings
Why it is in this group
- The name "openapi_get" says "get": a word for reading.
Description, as the server wrote it Fetch live API operation discovery with a SHA-256 digest. Supply path and method for one operation and its referenced schemas, or include_document=true for the entire contract. Pin sha256 to detect contract drift. No API key required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
preview_website_widgetRead the saved managed website voice widget for this agent.Reads text others writeNo findings
Why it is in this group
- The name "preview_website_widget" says "preview": a word for reading.
What it can reach
- untrusted-inputThe name "preview_website_widget" says "preview" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "read" and "website": it reads web pages, which anyone can write.
Description, as the server wrote it Read the saved managed website voice widget for this agent. Show its project, exact origins, session limits, status, embed snippet, readiness and revision before asking to publish. Does not publish or start a session.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
telephony_list_numbersList owned numbers and current Agent bindings before changing inbound routing.No findings
Why it is in this group
- The name "telephony_list_numbers" says "list": a word for reading.
Description, as the server wrote it List owned numbers and current Agent bindings before changing inbound routing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
telephony_search_numbersSearch available managed numbers and inspect provisioning requirements before purchase.No findings
Why it is in this group
- The name "telephony_search_numbers" says "search": a word for reading.
Description, as the server wrote it Search available managed numbers and inspect provisioning requirements before purchase.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
whoamiIntrospect the active key (GET /v1/me): org, environment (test/live), granted scopes, and rate-limit/credit posture.1 finding
Why it is in this group
- The name "whoami" says "whoami": a word for reading.
Findings
- Info
The input schema at properties.verbose.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.verbose.description: "...de authorized identity details in text. Credentials are always omitted."
Description, as the server wrote it Introspect the active key (GET /v1/me): org, environment (test/live), granted scopes, and rate-limit/credit posture. Organization and project names and IDs, billing guidance, and any managed payer/budget appear in text and structuredContent. Names are display labels; verify IDs and environment too. Use verbose=true for key identity details. Use it before usage and to diagnose a 401/403/402.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write17
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:02 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 22
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.pyai.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.pyai.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 22 tools that change things (10 destructive, 12 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.pyai.com/mcp: tools/list returned 58 tools to an anonymous client, including configure_amd (destructive), enable_recap (destructive), telephony_bind_number (destructive), telephony_create_call (destructive), update_agent (destructive) and 17 more
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 401 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 22
- Protocol version: none to 2025-06-18
- WWW-Authenticate on 401: yes to not observed
- resource_metadata in WWW-Authenticate: https://api.pyai.com/.well-known/oauth-protected-resource/mcp to none
Findings
Matches of fixed checks, with the text they matched.
- Warncalls_list
The server marks "calls_list" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "calls_list" says "call": a word for a change.
- Warncalls_get
The server marks "calls_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "calls_get" says "call": a word for a change.
- Infowhoami
The input schema at properties.verbose.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.verbose.description: "...de authorized identity details in text. Credentials are always omitted."
- Infocreate_agent
The description mentions "credentials".
What this check looks forMatched text
description: "...ately in the PyAI console. Never supply credentials."
- Infocreate_agent
The input schema at properties.body.properties.platform_guidance.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.body.properties.platform_guidance.description: "...Requires an explicitly enrolled server credential; ordinary customer keys receive 403. Se..."
- Infocreate_agent
The input schema at properties.body.properties.tools.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.body.properties.tools.description: "...gs are preserved for retained bindings. Credentials and connection settings are not accepte..."
Show 7 more findingsShow fewer
- Infoupdate_agent
The description mentions "credentials".
What this check looks forMatched text
description: "...ately in the PyAI console. Never supply credentials."
- Infoupdate_agent
The input schema at properties.body.properties.platform_guidance.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.body.properties.platform_guidance.description: "...Requires an explicitly enrolled server credential; ordinary customer keys receive 403. Se..."
- Infoupdate_agent
The input schema at properties.body.properties.tools.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.body.properties.tools.description: "...gs are preserved for retained bindings. Credentials and connection settings are not accepte..."
- Infoset_agent_tools
The description mentions "credentials".
What this check looks forMatched text
description: "...ately in the PyAI console. Never supply credentials."
- Infoset_agent_tools
The input schema at properties.body.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.body.description: "...gs are preserved for retained bindings. Credentials and connection settings are not accepte..."
The input schema at properties.body.properties.origin.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.body.properties.origin.description: ".... No wildcard, path, query, fragment or credentials."
- Infodiscover_tools
The description mentions "credentials".
What this check looks forMatched text
description: "...ce, summaries, dubbing or narration. No credentials or usage."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools4 added.+4 addedView diff
- Added:draft_website_widgetDeletes or cancels
- Added:list_published_website_widgetsOnly reads
- Added:preview_website_widgetOnly reads
- Added:publish_website_widgetDeletes or cancels
PostureRemote posture changed. HTTP status of an anonymous initialize: 401 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 22 (and 3 more).View diff
- HTTP status of an anonymous initialize: 401 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 22
- Protocol version: none to 2025-06-18
- WWW-Authenticate on 401: yes to not observed
- resource_metadata in WWW-Authenticate: https://api.pyai.com/.well-known/oauth-protected-resource/mcp to none
Tools4 changed.~4 changedView diff
- Changed:create_recapChanges thingsdescription
- Changed:create_transcription_jobChanges thingsinputSchema
- Changed:get_recapOnly readsdescription
- Changed:list_recap_callsOnly readsdescription
Install
Pinned to version 0.5.26. Values in angle brackets are yours to fill in.
claude mcp add --transport http pyai https://api.pyai.com/mcpclaude mcp add --transport http pyai https://api.pyai.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__pyai__openapi_get",
"mcp__pyai__get_started",
"mcp__pyai__whoami",
"mcp__pyai__list_models",
"mcp__pyai__list_voices",
"mcp__pyai__get_transcription_job",
"mcp__pyai__list_amd_calls",
"mcp__pyai__get_amd_call",
"mcp__pyai__get_recap",
"mcp__pyai__list_recap_calls",
"mcp__pyai__omni_list_calls",
"mcp__pyai__omni_get_call",
"mcp__pyai__omni_get_summary",
"mcp__pyai__omni_get_transcript",
"mcp__pyai__omni_get_recording",
"mcp__pyai__telephony_search_numbers",
"mcp__pyai__telephony_list_numbers",
"mcp__pyai__list_agents",
"mcp__pyai__get_agent",
"mcp__pyai__list_published_website_widgets",
"mcp__pyai__preview_website_widget",
"mcp__pyai__get_trace_config",
"mcp__pyai__list_trace_rule_packs",
"mcp__pyai__list_trace_interactions",
"mcp__pyai__get_trace_interaction",
"mcp__pyai__list_trace_findings",
"mcp__pyai__list_trace_violations",
"mcp__pyai__get_trace_exposure",
"mcp__pyai__get_recap_config",
"mcp__pyai__get_cast_capabilities",
"mcp__pyai__list_transcription_jobs",
"mcp__pyai__discover_tools",
"mcp__pyai__get_dub_capabilities",
"mcp__pyai__get_dub_job",
"mcp__pyai__get_dub_audio",
"mcp__pyai__get_cast_render",
"mcp__pyai__get_cast_audio"
],
"ask": [
"mcp__pyai__synthesize_speech",
"mcp__pyai__create_transcription_job",
"mcp__pyai__create_recap",
"mcp__pyai__calls_list",
"mcp__pyai__calls_get",
"mcp__pyai__create_agent",
"mcp__pyai__create_trace_rule_pack",
"mcp__pyai__direct_cast_script",
"mcp__pyai__render_cast",
"mcp__pyai__create_dub",
"mcp__pyai__preview_cast_line",
"mcp__pyai__transcribe_audio"
],
"deny": [
"mcp__pyai__configure_amd",
"mcp__pyai__enable_recap",
"mcp__pyai__telephony_bind_number",
"mcp__pyai__telephony_create_call",
"mcp__pyai__update_agent",
"mcp__pyai__set_agent_tools",
"mcp__pyai__set_agent_knowledge",
"mcp__pyai__draft_website_widget",
"mcp__pyai__publish_website_widget",
"mcp__pyai__configure_trace"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as pyai. Review it before you use it.
Capability tags behind 17 rules
- mcp__pyai__create_transcription_job untrusted-input, outbound
- mcp__pyai__configure_amd untrusted-input
- mcp__pyai__enable_recap untrusted-input
- mcp__pyai__create_recap untrusted-input
- mcp__pyai__omni_get_recording untrusted-input
- mcp__pyai__telephony_bind_number untrusted-input
- mcp__pyai__telephony_create_call untrusted-input
- mcp__pyai__create_agent untrusted-input
- mcp__pyai__update_agent untrusted-input
- mcp__pyai__set_agent_tools untrusted-input
- mcp__pyai__list_published_website_widgets untrusted-input
- mcp__pyai__draft_website_widget untrusted-input
- mcp__pyai__preview_website_widget untrusted-input
- mcp__pyai__publish_website_widget untrusted-input, outbound
- mcp__pyai__list_trace_interactions untrusted-input
- mcp__pyai__list_trace_violations untrusted-input
- mcp__pyai__create_dub untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.atomsai/pyai/verify?hash=f87603673cdc74a7a23c287f05fbe6f0e68661c4e5a0edd142c5c77897cfa526" | jq -e '.changed == false'Pinned hash f87603673cdc, from Nov 20, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.atomsai/pyai/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.atomsai/pyai)Source: MCP Registry · repository. Synced Nov 20, 2026, 20:18 UTC.
PyAI Voice AI MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PyAI Voice AI MCP server safe?
- No scan can promise that. What its definitions show: 59 tools, 22 of which can change, send or delete something, and 13 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the PyAI Voice AI MCP server delete data?
- Yes. 10 tools can delete, cancel or revoke something: configure_amd, enable_recap, telephony_bind_number, telephony_create_call, update_agent, set_agent_tools and 4 more.
Can the PyAI Voice AI MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the PyAI Voice AI MCP server have?
- 59 tools: 10 destructive, 12 write, 37 read. configure_amd, enable_recap, telephony_bind_number, telephony_create_call, update_agent, set_agent_tools, set_agent_knowledge, draft_website_widget and 51 more.
Does the PyAI Voice AI MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PyAI Voice AI MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_transcription_job and publish_website_widget.
Has the PyAI Voice AI MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 20, 2026. Every change is on this page and in its Atom feed.