com.mcparmory/elevenlabs
OCI · GHCR.IO/MCPARMORY/ELEVENLABS:1.0.3 · 2 COMPONENTS · SCANNED SEP 20
Convert text to speech, transcribe audio, and dub videos with AI voices
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security0
- Malware scan not yet available for this package.Unverified
- Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.Unverified
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 131 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability70
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 38535 tokens (~149/item across 258 items; 258 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
- Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety95
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 32 of 40 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "isolate_audio" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Partial
- An AI judge read all 258 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
How do I install the com.mcparmory/elevenlabs MCP server?
com.mcparmory/elevenlabs runs locally as a container image, launched with docker run --rm -i ghcr.io/mcparmory/elevenlabs:1.0.3. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.
oci · ghcr.io/mcparmory/elevenlabs:1.0.3
claude mcp add com-mcparmory-elevenlabs -- docker run --rm -i ghcr.io/mcparmory/elevenlabs:1.0.3
{
"mcpServers": {
"com-mcparmory-elevenlabs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} {
"servers": {
"com-mcparmory-elevenlabs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} codex mcp add com-mcparmory-elevenlabs -- docker run --rm -i ghcr.io/mcparmory/elevenlabs:1.0.3
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"com-mcparmory-elevenlabs": {
"type": "local",
"command": [
"docker",
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
],
"enabled": true
}
}
} mcp_servers:
com-mcparmory-elevenlabs:
command: "docker"
args: ["run", "--rm", "-i", "ghcr.io/mcparmory/elevenlabs:1.0.3"] {
"McpServers": {
"com-mcparmory-elevenlabs": {
"Transport": "stdio",
"Command": "docker",
"Arguments": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} {
"mcpServers": {
"com-mcparmory-elevenlabs": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/mcparmory/elevenlabs:1.0.3"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 −3
- Stability: pass → 0.80 functional
- 18 Sept 26 +1
- Stability: 0.97 → pass security
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 −3
- Stability: pass → 0.80 functional
- 11 Sept 26 +1
- Stability: 0.97 → pass security
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed oci/ghcr.io/mcparmory/elevenlabs:1.0.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | oci |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
get_batch_call Get Batch Call ~43
Retrieve detailed information about a specific batch call, including all recipients and their call status.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | The unique identifier of the batch call to retrieve. |
No output schema declared.
No examples provided.
get_chapter Get Chapter ~55
Retrieves detailed information about a specific chapter within a Studio project.
| Name | Type | Req | Description |
|---|---|---|---|
| chapter_id | string | yes | The unique identifier of the chapter to retrieve. |
| project_id | string | yes | The unique identifier of the Studio project containing the chapter. |
No output schema declared.
No examples provided.
get_chapter_snapshot Get Chapter Snapshot ~86
Retrieves a specific chapter snapshot from a Studio project. Use this to access saved states or versions of a chapter.
| Name | Type | Req | Description |
|---|---|---|---|
| chapter_id | string | yes | The unique identifier of the chapter within the project. |
| chapter_snapshot_id | string | yes | The unique identifier of the specific chapter snapshot to retrieve. |
| project_id | string | yes | The unique identifier of the Studio project containing the chapter. |
No output schema declared.
No examples provided.
get_chapter_snapshot_audio Get Chapter Snapshot Audio Stream ~115
Retrieve and stream audio from a chapter snapshot. Use the list snapshots endpoint to discover available snapshots for a chapter.
| Name | Type | Req | Description |
|---|---|---|---|
| chapter_id | string | yes | The unique identifier of the chapter within the project. |
| chapter_snapshot_id | string | yes | The unique identifier of the chapter snapshot to stream. |
| convert_to_mpeg | boolean | – | Whether to convert the streamed audio to MPEG format. Defaults to false, returning the original audio format. |
| project_id | string | yes | The unique identifier of the Studio project containing the chapter. |
No output schema declared.
No examples provided.
get_character_usage_metrics Get Character Usage Metrics ~218
Retrieve character usage metrics for the current user or entire workspace over a specified time period. Results can be aggregated by time interval and broken down by various dimensions such as voice, user, or API key.
| Name | Type | Req | Description |
|---|---|---|---|
| aggregation_bucket_size | integer | – | Custom aggregation interval in seconds. When specified, overrides the default daily aggregation. |
| breakdown_type | string | – | Dimension to break down usage metrics by. The 'user' breakdown requires include_workspace_metrics to be true. |
| end_unix | integer | yes | End of the usage window as a UTC Unix timestamp in milliseconds. Use 23:59:59 of the last day to include it in the results. |
| include_workspace_metrics | boolean | – | Include usage statistics for the entire workspace in addition to user-specific metrics. |
| metric | string | – | The usage metric to aggregate and return in the results. |
| start_unix | integer | yes | Start of the usage window as a UTC Unix timestamp in milliseconds. Use 00:00:00 of the first day to include it in the results. |
No output schema declared.
No examples provided.
get_conversation Get Conversation ~52
Retrieve the full details and history of a specific conversation by its ID. Use this to access conversation metadata, messages, and related information.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | string | yes | The unique identifier of the conversation to retrieve. |
No output schema declared.
No examples provided.
get_conversation_audio Get Conversation Audio ~50
Retrieve the audio recording of a specific conversation. Returns the audio file associated with the conversation ID.
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | string | yes | The unique identifier of the conversation whose audio recording you want to retrieve. |
No output schema declared.
No examples provided.
get_conversation_live_count Get Conversation Live Count ~59
Retrieve the current count of active ongoing conversations. Optionally filter results to a specific agent.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Filter the live count to conversations handled by a specific agent. Omit to get the total count across all agents. |
No output schema declared.
No examples provided.
get_criterion_analytics Get Criterion Analytics ~116
Retrieve analytics data for a specific evaluation criterion, with optional filtering by creation date range. Use this to analyze performance metrics and insights for a particular criterion.
| Name | Type | Req | Description |
|---|---|---|---|
| created_after | string | – | Filter analytics to include only records created on or after this date. Specify in ISO 8601 format. |
| created_before | string | – | Filter analytics to include only records created on or before this date. Specify in ISO 8601 format. |
| criterion_id | string | yes | The unique identifier of the evaluation criterion to retrieve analytics for. |
No output schema declared.
No examples provided.
get_default_voice_settings Get Default Voice Settings ~38
Retrieve the default voice settings for all voices, including similarity boost (Clarity + Similarity Enhancement) and stability parameters that control voice characteristics.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_dubbing Get Dubbing ~47
Retrieve metadata about a dubbing project, including its current processing status and completion state.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project to retrieve metadata for. |
No output schema declared.
No examples provided.
get_dubbing_resource Get Dubbing Resource ~69
Retrieves the dubbing resource for a given dubbing project ID that was created with studio enabled. Use this to access the generated dubbing output and associated metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project created from the dubbing endpoint with studio mode enabled. |
No output schema declared.
No examples provided.
get_environment_variable Get Environment Variable ~48
Retrieve a specific environment variable by its unique identifier. Use this to fetch configuration values stored in your environment.
| Name | Type | Req | Description |
|---|---|---|---|
| env_var_id | string | yes | The unique identifier of the environment variable to retrieve. |
No output schema declared.
No examples provided.
get_evaluation Get Evaluation ~40
Retrieve detailed information about a specific speech-to-text evaluation by its unique identifier.
| Name | Type | Req | Description |
|---|---|---|---|
| evaluation_id | string | yes | The unique identifier of the evaluation to retrieve. |
No output schema declared.
No examples provided.
get_evaluation_criterion Get Evaluation Criterion ~57
Retrieve a specific evaluation criterion by its ID for speech-to-text evaluation tasks. Use this to fetch detailed information about a criterion used in assessment workflows.
| Name | Type | Req | Description |
|---|---|---|---|
| criterion_id | string | yes | The unique identifier of the evaluation criterion to retrieve. |
No output schema declared.
No examples provided.
get_human_agent Get Human Agent ~53
Retrieve detailed information about a specific human agent in the speech-to-text evaluation system. Use this to access agent profiles and evaluation data.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the human agent to retrieve. |
No output schema declared.
No examples provided.
get_knowledge_base_size Get Knowledge Base Size ~65
Retrieves the total number of pages stored in an agent's knowledge base. Use this to understand the size and scope of the knowledge base associated with a specific agent.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent whose knowledge base size you want to retrieve. |
No output schema declared.
No examples provided.
get_knowledge_base_source_file_url Get Knowledge Base Source File URL ~77
Retrieve a signed URL to download the original source file of a document stored in the knowledge base. The URL is temporary and can be used to access the file directly.
| Name | Type | Req | Description |
|---|---|---|---|
| documentation_id | string | yes | The unique identifier of the knowledge base document. This ID is provided when the document is initially added to the knowledge base. |
No output schema declared.
No examples provided.
get_knowledge_base_summaries Get Knowledge Base Summaries ~67
Retrieve summaries for multiple knowledge base documents by their IDs. Useful for quickly accessing document metadata and content previews without loading full documents.
| Name | Type | Req | Description |
|---|---|---|---|
| document_ids | array | yes | List of knowledge base document IDs to retrieve summaries for. IDs must be valid document identifiers from your knowledge base. |
No output schema declared.
No examples provided.
get_mcp_server Get MCP Server ~53
Retrieve a specific MCP server configuration from your workspace. Use this to access detailed settings and metadata for a configured MCP server.
| Name | Type | Req | Description |
|---|---|---|---|
| mcp_server_id | string | yes | The unique identifier of the MCP server to retrieve. |
No output schema declared.
No examples provided.
get_phone_number Get Phone Number ~47
Retrieve details for a specific phone number by its ID. Returns the phone number configuration and associated metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| phone_number_id | string | yes | The unique identifier of the phone number to retrieve. |
No output schema declared.
No examples provided.
get_project Get Project ~68
Retrieve detailed information about a specific Studio project. Returns comprehensive project metadata including configuration, settings, and other project-specific details.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | The unique identifier of the Studio project to retrieve. |
| share_id | string | – | Optional share identifier to access a shared version of the project. |
No output schema declared.
No examples provided.
get_pronunciation_dictionary Get Pronunciation Dictionary ~52
Retrieve metadata for a specific pronunciation dictionary by its ID. Returns configuration details and properties of the pronunciation dictionary.
| Name | Type | Req | Description |
|---|---|---|---|
| pronunciation_dictionary_id | string | yes | The unique identifier of the pronunciation dictionary to retrieve metadata for. |
No output schema declared.
No examples provided.
get_rag_index_overview Get RAG Index Overview ~39
Retrieves metadata about RAG (Retrieval-Augmented Generation) indexes used by the knowledge base, including total size and other index statistics.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_resource Get Resource ~72
Retrieves metadata for a specific resource by its ID and type. Use this to fetch detailed information about any resource in your workspace.
| Name | Type | Req | Description |
|---|---|---|---|
| resource_id | string | yes | The unique identifier of the resource to retrieve. |
| resource_type | string | yes | The category of the resource. Determines which resource type's metadata will be returned. |
No output schema declared.
No examples provided.
get_snapshot Get Project Snapshot ~64
Retrieves a specific project snapshot by its ID. Use this to access saved project state and configuration data.
| Name | Type | Req | Description |
|---|---|---|---|
| project_id | string | yes | The unique identifier of the Studio project containing the snapshot. |
| project_snapshot_id | string | yes | The unique identifier of the project snapshot to retrieve. |
No output schema declared.
No examples provided.
get_speaker_audio Get Speaker Audio ~116
Retrieve the isolated audio track for a specific speaker from a voice sample. This operation extracts and returns only the audio corresponding to the designated speaker.
| Name | Type | Req | Description |
|---|---|---|---|
| sample_id | string | yes | The unique identifier of the sample within the specified voice. |
| speaker_id | string | yes | The unique identifier of the speaker whose audio should be extracted. Use the speakers list endpoint for the voice and sample to discover available speaker IDs. |
| voice_id | string | yes | The unique identifier of the voice. Use the voices list endpoint to discover available voice IDs. |
No output schema declared.
No examples provided.
get_speaker_separation_status Get Speaker Separation Status ~73
Retrieve the current status of speaker separation processing for a voice sample and list any detected speakers if the process is complete.
| Name | Type | Req | Description |
|---|---|---|---|
| sample_id | string | yes | The unique identifier of the voice sample undergoing speaker separation analysis. |
| voice_id | string | yes | The unique identifier of the voice whose sample is being analyzed. |
No output schema declared.
No examples provided.
get_speech_history_audio Get Speech History Audio ~65
Retrieve the audio file associated with a specific speech synthesis history item. Use the history item ID obtained from the speech history list to download the generated audio.
| Name | Type | Req | Description |
|---|---|---|---|
| history_item_id | string | yes | The unique identifier of the speech history item from which to retrieve the audio file. |
No output schema declared.
No examples provided.
get_speech_history_item Get Speech History Item ~68
Retrieves a specific speech synthesis history item by its ID. Use this to access details about a previously generated speech synthesis request.
| Name | Type | Req | Description |
|---|---|---|---|
| history_item_id | string | yes | The unique identifier of the history item to retrieve. You can obtain available history item IDs by calling the list speech history operation. |
No output schema declared.
No examples provided.
get_subscription_info Get Subscription Info ~29
Retrieves detailed information about the user's current subscription, including plan details, billing status, and entitlements.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_test_invocation Get Test Invocation ~61
Retrieves a specific test invocation by its ID. Use this to fetch details about a test invocation that was previously executed.
| Name | Type | Req | Description |
|---|---|---|---|
| test_invocation_id | string | yes | The unique identifier of the test invocation to retrieve. This ID is provided when tests are executed. |
No output schema declared.
No examples provided.
get_tool Get Tool ~45
Retrieve a specific tool available in the workspace by its ID. Use this to fetch tool details and configuration.
| Name | Type | Req | Description |
|---|---|---|---|
| tool_id | string | yes | The unique identifier of the tool to retrieve. |
No output schema declared.
No examples provided.
get_tool_config_override Get Tool Config Override ~76
Retrieve configuration overrides for a specific MCP tool within an MCP server. Use this to fetch customized tool settings that differ from default configurations.
| Name | Type | Req | Description |
|---|---|---|---|
| mcp_server_id | string | yes | The unique identifier of the MCP server containing the tool. |
| tool_name | string | yes | The name of the MCP tool for which to retrieve configuration overrides. |
No output schema declared.
No examples provided.
get_transcript Get Transcript ~48
Retrieve a previously generated transcript by its unique identifier. Use this operation to access transcription results after they have been processed.
| Name | Type | Req | Description |
|---|---|---|---|
| transcription_id | string | yes | The unique identifier of the transcript to retrieve. |
No output schema declared.
No examples provided.
get_transcript_dubbing Get Dubbing Transcripts ~150
Retrieve the transcript for a specific language in a dubbing project. Supports multiple output formats including subtitle formats (SRT, WebVTT) and JSON transcripts.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project containing the transcript to retrieve. |
| format_type | string | yes | The output format for the transcript. Use 'srt' or 'webvtt' for subtitle formats, or 'json' for a full transcript (JSON format is not yet supported for Dubbing Studio). |
| language_code | string | yes | The language for which to retrieve the transcript. Use 'source' to fetch the original media transcript, or provide an ISO 639 language code. |
No output schema declared.
No examples provided.
get_user Get User Info ~18
Retrieves the authenticated user's profile information and account details.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_voice Get Voice ~67
Retrieve detailed metadata for a specific voice, including its properties and configuration. Use this to get information about a voice before using it for text-to-speech synthesis.
| Name | Type | Req | Description |
|---|---|---|---|
| voice_id | string | yes | The unique identifier of the voice to retrieve. You can list all available voices to discover valid IDs. |
No output schema declared.
No examples provided.
get_voice_sample_audio Get Voice Sample Audio ~102
Retrieve the first 30 seconds of audio from a voice sample, with optional background noise removal using audio isolation technology.
| Name | Type | Req | Description |
|---|---|---|---|
| remove_background_noise | boolean | – | Enable background noise removal using audio isolation. Note: applying this to samples without background noise may degrade audio quality. |
| sample_id | string | yes | The unique identifier of the specific voice sample to retrieve. |
| voice_id | string | yes | The unique identifier of the voice whose sample audio you want to retrieve. |
No output schema declared.
No examples provided.
get_voice_sample_waveform Get Voice Sample Waveform ~78
Retrieve the visual waveform representation of a specific voice sample. This waveform can be used to visualize the audio characteristics of the sample.
| Name | Type | Req | Description |
|---|---|---|---|
| sample_id | string | yes | The unique identifier of the voice sample whose waveform you want to retrieve. |
| voice_id | string | yes | The unique identifier of the voice whose sample waveform you want to retrieve. |
No output schema declared.
No examples provided.
get_voice_settings Get Voice Settings ~69
Retrieve the configuration settings for a specific voice, including similarity boost (Clarity + Similarity Enhancement) and stability parameters that control voice quality characteristics.
| Name | Type | Req | Description |
|---|---|---|---|
| voice_id | string | yes | The unique identifier of the voice whose settings you want to retrieve. Use the list voices endpoint to discover available voice IDs. |
No output schema declared.
No examples provided.
get_whatsapp_account Get WhatsApp Account ~53
Retrieve details for a specific WhatsApp account using its phone number ID. Returns account configuration and status information.
| Name | Type | Req | Description |
|---|---|---|---|
| phone_number_id | string | yes | The unique identifier for the WhatsApp phone number associated with the account. |
No output schema declared.
No examples provided.
grant_resource_access Grant Resource Access ~241
Grant or update a role on a workspace resource for a user, service account, group, or API key. This operation overrides any existing role the principal has on the resource. You must have admin access to the resource to perform this action.
| Name | Type | Req | Description |
|---|---|---|---|
| group_id | string | – | The unique identifier of the group to grant access to. Use the special value 'default' to target the default permissions principals have on this resource. |
| resource_id | string | yes | The unique identifier of the resource to share. |
| resource_type | string | yes | The category of resource being shared. Determines the type of object referenced by resource_id. |
| role | string | yes | The access level to grant to the principal. Determines what actions the principal can perform on the resource. |
| user_email | string | – | The email address of the user or service account to grant access to. The principal must already exist in your workspace. |
| workspace_api_key_id | string | – | The unique identifier of the workspace API key to grant access to. This is the key ID found in workspace settings, not the API key credential itself. Access will be granted to the service account ass… |
No output schema declared.
No examples provided.
import_phone_number Import Phone Number ~219
Import a phone number from your provider configuration (Twilio or SIP trunk) to enable inbound and outbound calling capabilities.
| Name | Type | Req | Description |
|---|---|---|---|
| inbound_trunk_config | object | – | SIP trunk configuration for inbound call routing, including server address, port, and authentication credentials. |
| label | string | yes | A descriptive label for this phone number to identify it in your system. |
| outbound_trunk_config | object | – | SIP trunk configuration for outbound call routing, including server address, port, and authentication credentials. |
| phone_number | string | yes | The phone number to import in E.164 format or provider-specific format. |
| provider | string | – | The telecommunications provider to import from. Defaults to Twilio if not specified. |
| region_config | object | – | Additional Twilio region configuration settings to optimize call routing and compliance for specific geographic regions. |
| sid | string | – | Your Twilio Account SID for authentication. Required when provider is set to Twilio. |
| token | string | – | Your Twilio Auth Token for authentication. Required when provider is set to Twilio. |
No output schema declared.
No examples provided.
index_knowledge_base_document Index Knowledge Base Document ~109
Trigger or retrieve the RAG indexing status for a knowledge base document. If the document hasn't been indexed yet, this operation initiates the indexing task; otherwise, it returns the current indexing status.
| Name | Type | Req | Description |
|---|---|---|---|
| documentation_id | string | yes | The unique identifier of the document in the knowledge base that you want to index or check the indexing status for. |
| model | string | yes | The embedding model to use for RAG indexing. This determines how the document content will be vectorized for semantic search. |
No output schema declared.
No examples provided.
initiate_outbound_call Initiate Outbound Call ~405
Initiate an outbound phone call through Twilio with AI agent capabilities, including voice synthesis, language support, and optional call recording.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Unique identifier of the AI agent that will handle the call. |
| agent_phone_number_id | string | yes | Identifier of the Twilio phone number resource to use as the caller. |
| call_recording_enabled | boolean | – | Whether Twilio should record the audio of this call for compliance, quality assurance, or archival purposes. |
| dynamic_variables | object | – | Key-value pairs of custom variables that can be referenced in the agent's prompt or system instructions to personalize the conversation. |
| first_message | string | – | Optional initial message the agent will speak when the call connects. If omitted, the agent waits for the caller to speak first. |
| language | string | – | Language code for the agent's automatic speech recognition and text-to-speech processing. |
| prompt | object | – | Configuration object specifying the LLM model and system prompt that defines the agent's behavior and knowledge. |
| similarity_boost | number | – | Controls how closely the generated speech matches the target voice characteristics. |
| soft_timeout_config | object | – | Configuration for soft timeout feedback, allowing the agent to provide immediate responses (e.g., acknowledgments) while processing longer LLM responses. |
| source | string | – | The platform or integration through which the call was initiated. |
| speed | number | – | Controls the playback speed of generated speech, where higher values increase speech rate. |
| stability | number | – | Controls the consistency of the generated speech, with higher values producing more stable output. |
| to_number | string | yes | The destination phone number to call in E.164 format or standard phone number format. |
| user_id | string | – | Identifier for the end user or customer participating in this call, used for tracking and attribution by the agent owner. |
| voice_id | string | – | Identifier for the text-to-speech voice to use for agent responses. |
No output schema declared.
No examples provided.
initiate_outbound_sip_call Initiate Outbound SIP Call ~436
Initiates an outbound call through a SIP trunk with an AI agent. The agent can be configured with custom voice settings, initial messaging, and LLM behavior to handle the conversation.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Unique identifier of the AI agent that will handle the outbound call. |
| agent_phone_number_id | string | yes | Unique identifier of the phone number resource associated with the agent for this call. |
| dynamic_variables | object | – | Custom variables that can be passed to the agent and used within the prompt or conversation context for dynamic behavior. |
| first_message | string | – | The initial message the agent will speak when the call connects. If empty, the agent waits for the caller to speak first. |
| language | string | – | The language code for the agent's automatic speech recognition (ASR) and text-to-speech (TTS) processing. |
| prompt | object | – | Configuration for the LLM behavior, including the model selection and system prompt that defines the agent's personality and capabilities. |
| similarity_boost | number | – | Controls how closely the generated speech matches the selected voice ID, balancing between voice similarity and speech quality. |
| soft_timeout_config | object | – | Configuration for soft timeout feedback, allowing the agent to provide immediate responses (e.g., acknowledgments) while processing longer LLM responses. |
| source | string | – | The source or channel through which the call was initiated, used for analytics and tracking purposes. |
| speed | number | – | Controls the speed of the generated speech, where lower values slow down speech and higher values speed it up. |
| stability | number | – | Controls the consistency of the generated speech, ranging from low variability to high variability in tone and delivery. |
| to_number | string | yes | The destination phone number to call in E.164 format or standard phone number format. |
| user_id | string | – | Identifier for the end user or customer participating in this call, used by the agent owner for tracking and user identification. |
| voice_id | string | – | The voice ID to use for text-to-speech synthesis. Determines the voice characteristics of the agent's spoken responses. |
No output schema declared.
No examples provided.
initiate_twilio_call Initiate Twilio Call ~427
Initiate a Twilio voice call with an AI agent and return TwiML configuration for call routing. Supports both inbound and outbound call directions with customizable agent behavior, voice settings, and conversation parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Unique identifier of the AI agent that will handle this call. |
| direction | string | – | Direction of the call flow. Inbound calls originate from external parties; outbound calls are initiated by the system. |
| dynamic_variables | object | – | Custom key-value variables that can be passed to the agent prompt for dynamic personalization or context injection during the conversation. |
| first_message | string | – | Opening message the agent will speak when the call connects. If empty, the agent waits for the caller to speak first. |
| from_number | string | yes | The phone number initiating the call (caller ID for outbound, destination for inbound). |
| language | string | – | Language code for automatic speech recognition (ASR) and text-to-speech (TTS) processing during the call. |
| prompt | object | – | Configuration object containing the LLM model identifier and system prompt that defines the agent's behavior and knowledge domain. |
| similarity_boost | number | – | Controls how closely the generated speech matches the target voice characteristics. |
| soft_timeout_config | object | – | Configuration for soft timeout feedback, allowing the agent to provide immediate acknowledgment messages while processing longer LLM responses. |
| source | string | – | Channel or platform through which this call was initiated, used for analytics and routing decisions. |
| speed | number | – | Controls the playback speed of generated speech, where higher values increase speech rate. |
| stability | number | – | Controls the consistency of generated speech output, affecting how natural and varied the voice sounds. |
| to_number | string | yes | The phone number receiving the call (destination for outbound, caller ID for inbound). |
| user_id | string | – | Identifier for the end user or customer participating in this call, used by the agent owner for tracking and analytics. |
| voice_id | string | – | Identifier for the text-to-speech voice model to use for agent responses. |
No output schema declared.
No examples provided.
initiate_whatsapp_call Initiate WhatsApp Call ~467
Initiate an outbound voice call to a WhatsApp user through a configured WhatsApp Business Account. The call uses a pre-approved permission request template and connects to an AI agent for conversation.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The ID of the AI agent that will handle the conversation during the call. |
| dynamic_variables | object | – | Dynamic variables that can be passed to customize the agent's behavior and responses during the call. |
| first_message | string | – | The initial message the agent will speak when the call connects. If empty, the agent will wait for the user to speak first. |
| language | string | – | The language code for the agent's automatic speech recognition and text-to-speech (e.g., 'en-US', 'es-ES'). |
| prompt | object | – | The system prompt that defines the agent's behavior, personality, and instructions for handling the conversation. |
| similarity_boost | number | – | The similarity boost parameter for speech synthesis, controlling how closely the voice matches the selected voice ID. |
| soft_timeout_config | object | – | Configuration for soft timeout feedback, allowing the agent to send intermediate messages while processing longer LLM responses to keep the conversation feeling responsive. |
| source | string | – | The source or channel through which the call was initiated. |
| speed | number | – | The speed parameter for speech synthesis, controlling how fast the agent speaks. |
| stability | number | – | The stability parameter for speech synthesis, controlling consistency of the generated voice. |
| user_id | string | – | The ID of the end user initiating this call, used by the agent owner for tracking and identifying conversation participants. |
| voice_id | string | – | The voice ID to use for text-to-speech synthesis during the call. |
| whatsapp_call_permission_request_template_language_code | string | yes | The language code of the call permission request template (e.g., 'en_US', 'es_ES'). |
| whatsapp_call_permission_request_template_name | string | yes | The name of the WhatsApp-approved call permission request template to use for initiating the call. |
| whatsapp_phone_number_id | string | yes | The WhatsApp Business Account phone number ID that will be used to make the outbound call. |
| whatsapp_user_id | string | yes | The WhatsApp user ID of the recipient who will receive the outbound call. |
No output schema declared.
No examples provided.
isolate_audio Isolate Audio ~68
Removes background noise and isolates vocals or speech from an audio file. Returns the cleaned audio with background noise suppressed.
| Name | Type | Req | Description |
|---|---|---|---|
| audio | string | yes | Base64-encoded file content for upload. The audio file to process for noise removal and vocal/speech isolation. Accepts binary audio data in common formats. |
No output schema declared.
No examples provided.
What is the com.mcparmory/elevenlabs MCP server?
com.mcparmory/elevenlabs is an MCP server listed in the public MCP registry as com.mcparmory/elevenlabs. Convert text to speech, transcribe audio, and dub videos with AI voices. This page covers its container image (ghcr.io/mcparmory/elevenlabs:1.0.3).
Is the com.mcparmory/elevenlabs MCP server safe to use?
com.mcparmory/elevenlabs scores 48 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the com.mcparmory/elevenlabs MCP server expose?
com.mcparmory/elevenlabs exposes 258 tools: list_speech_history, get_speech_history_item, delete_history_item, get_speech_history_audio, download_speech_items, and 253 more. Their descriptions and schemas cost roughly 38,535 tokens of context every time the server is loaded.
Is the com.mcparmory/elevenlabs MCP server still maintained?
com.mcparmory/elevenlabs is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.