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 →
remix_voice Remix Voice ~228
Generate voice previews by remixing an existing voice based on a descriptive prompt. Returns multiple voice preview options with generated voice IDs that can be used to create new voices.
| Name | Type | Req | Description |
|---|---|---|---|
| loudness | number | – | Volume level of the generated voice, ranging from -1 (quietest) to 1 (loudest), with 0 corresponding to approximately -24 LUFS. |
| output_format | string | – | Audio output format specified as codec_sample_rate_bitrate. MP3 at 192kbps requires Creator tier or higher. PCM at 44.1kHz requires Pro tier or higher. μ-law format is compatible with Twilio. |
| stream_previews | boolean | – | When true, returns only generated voice IDs without audio previews in the response. Audio can then be streamed separately via the stream endpoint. |
| voice_description | string | yes | Detailed description of the voice modifications to apply. Be specific about desired characteristics such as pitch, tone, pace, or emotional qualities. |
| voice_id | string | yes | The ID of the voice to remix. Use the voices list endpoint to discover available voices. |
No output schema declared.
No examples provided.
remove_group_member Remove Group Member ~69
Remove a member from a user group. Requires `group_members_manage` permission to perform this action.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The email address of the workspace member to remove from the group. | |
| group_id | string | yes | The unique identifier of the group from which the member will be removed. |
No output schema declared.
No examples provided.
remove_voice_sample Remove Voice Sample ~75
Remove a sample from a PVC (Professional Voice Clone) voice. This permanently deletes the specified sample, which cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| sample_id | string | yes | The unique identifier of the sample to be deleted from the voice. |
| voice_id | string | yes | The unique identifier of the PVC voice from which to remove the sample. |
No output schema declared.
No examples provided.
rename_document Rename Document ~74
Rename a document in the knowledge base by updating its display name.
| Name | Type | Req | Description |
|---|---|---|---|
| documentation_id | string | yes | The unique identifier of the document to rename. This ID is provided when the document is initially added to the knowledge base. |
| name | string | yes | A human-readable name for the document. Must be at least one character long. |
No output schema declared.
No examples provided.
render_dubbing Render Dubbing ~129
Generate output media for a specific language in a dubbing project using the current Studio state. All segments must be dubbed before rendering to be included in the output; renders are processed asynchronously.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project to render. |
| language | string | yes | The target language code for rendering (e.g., 'es' for Spanish). Use 'original' to render the source track. |
| normalize_volume | boolean | – | Whether to apply volume normalization to the rendered audio. |
| render_type | string | yes | The output format for the rendered media. |
No output schema declared.
No examples provided.
replace_pronunciation_rules Replace Pronunciation Rules ~109
Replace all pronunciation rules in a dictionary with a new set of rules. Rules can define phonetic aliases or phoneme mappings using specified alphabets.
| Name | Type | Req | Description |
|---|---|---|---|
| pronunciation_dictionary_id | string | yes | The unique identifier of the pronunciation dictionary to update. |
| rules | array | yes | An ordered list of pronunciation rules to apply. Each rule maps a string to either an alias (another string) or a phoneme (with a specified alphabet such as IPA). All existing rules will be replaced… |
No output schema declared.
No examples provided.
resubmit_tests Resubmit Tests ~180
Resubmit specific test runs from a completed test invocation to re-evaluate agent performance with potentially updated configurations. Allows selective resubmission of individual test cases within a test batch.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_config_override | – | – | Agent configuration overrides for test resubmission |
| agent_id | string | yes | The unique identifier of the agent whose tests should be resubmitted. |
| branch_id | string | – | Branch ID for running tests against a specific agent variant or configuration. If omitted, tests run against the agent's default configuration. |
| test_invocation_id | string | yes | The unique identifier of the test invocation containing the test runs to resubmit. This ID is returned when tests are initially executed. |
| test_run_ids | array | yes | List of test run IDs to resubmit. Each ID identifies a specific test case within the invocation to be re-executed. |
No output schema declared.
No examples provided.
retrieve_knowledge_base_chunk Retrieve Knowledge Base Chunk ~135
Retrieve a specific chunk from a knowledge base document used by the RAG system. Returns the chunk content and metadata for the specified documentation and chunk identifiers.
| Name | Type | Req | Description |
|---|---|---|---|
| chunk_id | string | yes | The unique identifier of the specific chunk within the document. Chunks are sequential segments of a document created during RAG processing. |
| documentation_id | string | yes | The unique identifier of the document in the knowledge base. This ID is provided when the document is initially added to the knowledge base. |
| embedding_model | string | – | The embedding model used to generate and retrieve the chunk. Determines the vector representation used for semantic search and retrieval. |
No output schema declared.
No examples provided.
retrieve_knowledge_base_document Retrieve Knowledge Base Document ~83
Retrieve detailed information about a specific document from the agent's knowledge base. Use the documentation ID returned when the document was added to access its content and metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Optional agent identifier to scope the knowledge base query to a specific agent. |
| documentation_id | string | yes | The unique identifier of the document to retrieve from the knowledge base. |
No output schema declared.
No examples provided.
retrieve_knowledge_base_document_content Retrieve Knowledge Base Document Content ~67
Retrieve the complete content of a document stored in the knowledge base. Use the documentation ID returned when the document was added to access its full text.
| Name | Type | Req | Description |
|---|---|---|---|
| documentation_id | string | yes | The unique identifier of the document in the knowledge base, provided when the document was initially added. |
No output schema declared.
No examples provided.
retrieve_voice_sample_audio Retrieve Voice Sample Audio ~96
Retrieves the audio file associated with a specific sample attached to a voice. Use this to download or access audio data for voice samples.
| Name | Type | Req | Description |
|---|---|---|---|
| sample_id | string | yes | The unique identifier of the sample within the specified voice. You can retrieve available sample IDs by fetching the voice details endpoint. |
| voice_id | string | yes | The unique identifier of the voice containing the sample. You can retrieve available voice IDs from the voices list endpoint. |
No output schema declared.
No examples provided.
retry_batch_call Retry Batch Call ~80
Retry a failed batch call by re-attempting to reach recipients who did not respond or experienced call failures. This operation allows you to reprocess a specific batch without creating a new batch call.
| Name | Type | Req | Description |
|---|---|---|---|
| batch_id | string | yes | The unique identifier of the batch call to retry. This specifies which batch's failed and no-response recipients should be called again. |
No output schema declared.
No examples provided.
revoke_mcp_server_tool_approval Revoke MCP Server Tool Approval ~88
Revoke approval for a specific MCP tool on a server when using per-tool approval mode. This removes the tool from the approved list, preventing its use until re-approved.
| Name | Type | Req | Description |
|---|---|---|---|
| mcp_server_id | string | yes | The unique identifier of the MCP Server from which to revoke tool approval. |
| tool_name | string | yes | The name of the MCP tool to revoke approval for. |
No output schema declared.
No examples provided.
revoke_resource_access Revoke Resource Access ~190
Removes all access permissions for a user, service account, group, or workspace API key to a workspace resource. The requester must have admin access to the resource.
| Name | Type | Req | Description |
|---|---|---|---|
| group_id | string | – | The identifier of the group to revoke access from. Use 'default' to target default permissions principals have on this resource. |
| resource_id | string | yes | The unique identifier of the workspace resource to revoke access from. |
| resource_type | string | yes | The category of the workspace resource being modified. |
| user_email | string | – | The email address of the user or service account to revoke access from. The user or service account must exist in your workspace. |
| workspace_api_key_id | string | – | The identifier of the workspace API key to revoke access from. This is the key ID found in workspace settings, not the authentication key itself. Access will be revoked from the service account assoc… |
No output schema declared.
No examples provided.
revoke_service_account_api_key Revoke Service Account API Key ~77
Revoke and permanently delete an API key associated with a service account. This action cannot be undone.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key_id | string | yes | The unique identifier of the API key to be revoked and deleted. |
| service_account_user_id | string | yes | The unique identifier of the service account that owns the API key to be deleted. |
No output schema declared.
No examples provided.
revoke_workspace_invitation Revoke Workspace Invitation ~77
Revoke an existing workspace invitation by email address. The invitation will remain visible in the recipient's inbox but will no longer be activatable to join the workspace. Only workspace members with WORKSPACE_MEMBERS_INVITE permission can perform this action.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The email address of the invitation recipient whose invitation should be revoked. |
No output schema declared.
No examples provided.
run_agent_tests Run Agent Tests ~113
Execute a suite of tests against a conversational AI agent with optional configuration overrides. Tests validate agent behavior, quality, and compliance against specified criteria.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_config_override | – | – | Agent configuration overrides for test execution |
| agent_id | string | yes | The unique identifier of the agent to test. |
| branch_id | string | – | Agent branch identifier to test against. If omitted, tests run on the default agent configuration. |
| tests | array | yes | Array of test configurations to execute. Each test validates specific agent behaviors or criteria. |
No output schema declared.
No examples provided.
search_conversation_messages Search Conversation Messages ~420
Search conversation transcripts using full-text and fuzzy matching with optional filtering by agent, user, call metrics, ratings, language, and other conversation attributes.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Filter results to conversations handled by a specific agent. |
| branch_id | string | – | Filter conversations by branch ID. |
| call_duration_max_secs | integer | – | Filter conversations with a maximum duration in seconds. |
| call_duration_min_secs | integer | – | Filter conversations with a minimum duration in seconds. |
| call_successful | string | – | Filter results by the outcome of the conversation (success, failure, or unknown). |
| conversation_initiation_source | string | – | Filter conversations by their initiation source (SDK, integration, or communication platform). |
| data_collection_params | array | – | Filter by data collection fields using comparison operators. Format: id:operator:value where operator is eq, neq, gt, gte, lt, lte, in, exists, or missing. Use pipe-delimited values for 'in' operator… |
| evaluation_params | array | – | Filter by evaluation criteria results. Specify as criteria_id:result pairs (repeatable parameter). |
| has_feedback_comment | boolean | – | Include only conversations that have user feedback comments. |
| main_languages | array | – | Filter conversations by detected primary language using language codes (repeatable parameter). |
| page_size | integer | – | Number of results to return per page. |
| rating_max | integer | – | Filter conversations with a maximum overall rating on a scale of 1-5. |
| rating_min | integer | – | Filter conversations with a minimum overall rating on a scale of 1-5. |
| summary_mode | string | – | Include or exclude transcript summaries in the response. |
| text_query | string | yes | The search query text to match against conversation messages using full-text and fuzzy search algorithms. |
| tool_names | array | – | Filter conversations by the names of tools used during the call (repeatable parameter). |
| user_id | string | – | Filter conversations by the user ID who initiated them. |
No output schema declared.
No examples provided.
search_conversation_messages_semantic Search Conversation Messages Semantically ~128
Search conversation transcripts using semantic similarity to find relevant messages based on meaning and intent rather than exact keyword matches. Returns the most contextually relevant messages from conversation history.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Filter results to messages from a specific agent. If omitted, searches across all agents in the conversation. |
| page_size | integer | – | Number of results to return per page. Controls pagination size for large result sets. |
| text_query | string | yes | The search query text to match against conversation messages using semantic similarity. Accepts natural language queries describing intent, topics, or specific requests. |
No output schema declared.
No examples provided.
send_whatsapp_message Send WhatsApp Message ~465
Send an outbound message to a WhatsApp user using a predefined template with optional AI agent configuration for interactive conversations.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The ID of the AI agent that will handle the conversation if this message initiates an interactive session. |
| dynamic_variables | object | – | Additional dynamic variables to be substituted into the template or used by the agent during the conversation. |
| first_message | string | – | The initial message the agent will send to start the conversation. If empty, the agent waits for the user to send the first message. |
| language | string | – | The language for the agent's automatic speech recognition (ASR) and text-to-speech (TTS) processing. |
| prompt | object | – | Configuration object containing the LLM model and system prompt that defines the agent's behavior and capabilities. |
| similarity_boost | number | – | Controls how closely the generated speech matches the selected voice characteristics. |
| soft_timeout_config | object | – | Configuration for soft timeout feedback, allowing the agent to send intermediate messages (e.g., acknowledgments) while processing longer responses. |
| source | string | – | The channel or platform through which this conversation was initiated. |
| speed | number | – | Controls the speed of generated speech playback. |
| stability | number | – | Controls the consistency of the generated speech, ranging from low variability to high variability. |
| template_language_code | string | yes | The language code for the template (e.g., 'en', 'es', 'fr'). Must match the template's supported languages. |
| template_name | string | yes | The name of the WhatsApp message template to use for this outbound message. |
| template_params | array | yes | An ordered array of parameter values to substitute into the template placeholders. Order and format must match the template definition. |
| user_id | string | – | Identifier for the end user participating in this conversation, used by the agent owner for tracking and analytics. |
| voice_id | string | – | The voice ID to use for text-to-speech synthesis when the agent responds with audio. |
| whatsapp_phone_number_id | string | yes | The WhatsApp phone number ID associated with your business account that will send the message. |
| whatsapp_user_id | string | yes | The WhatsApp user ID (recipient) who will receive the message. |
No output schema declared.
No examples provided.
send_workspace_invitations Send Workspace Invitations ~119
Send email invitations to multiple users to join your workspace. Invitees must have email addresses from verified domains, and accepted invitations will add them as workspace users consuming available seats.
| Name | Type | Req | Description |
|---|---|---|---|
| emails | array | yes | List of email addresses to invite. All emails must belong to verified domains associated with your workspace. |
| group_ids | array | – | List of group IDs to assign the invited users to upon acceptance. Groups organize users and manage permissions within the workspace. |
| seat_type | string | – | The permission level to assign to invited users within the workspace. |
No output schema declared.
No examples provided.
send_workspace_invite Send Workspace Invite ~121
Sends an email invitation to join the workspace. The recipient will be prompted to create an account if needed, and upon acceptance will be added as a workspace user consuming one available seat. Requires WORKSPACE_MEMBERS_INVITE permission.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The email address of the user to invite to the workspace. | |
| group_ids | array | – | List of group IDs to assign the invited user to. Groups determine access permissions and organizational structure within the workspace. |
| seat_type | string | – | The permission level to assign the invited user within the workspace. |
No output schema declared.
No examples provided.
separate_song_stems Separate Song Stems ~163
Separate an audio file into individual musical stems (vocals, drums, bass, etc.). This operation may have high latency depending on audio file length.
| Name | Type | Req | Description |
|---|---|---|---|
| file | string | yes | Base64-encoded file content for upload. The audio file to separate into individual stems. Provide the binary audio data. |
| output_format | string | – | Output format for the separated stems, specified as codec_sample_rate_bitrate. MP3 192kbps requires Creator tier or above; PCM 44.1kHz requires Pro tier or above. μ-law format is commonly used for Tw… |
| stem_variation_id | string | – | The stem separation model variation to use. Two-stem splits into vocals and instruments; six-stem provides more granular separation. |
No output schema declared.
No examples provided.
separate_speakers Separate Speakers ~72
Initiate speaker separation processing for an audio sample, which identifies and isolates individual speakers within the sample.
| Name | Type | Req | Description |
|---|---|---|---|
| sample_id | string | yes | The unique identifier of the audio sample to be processed for speaker separation. |
| voice_id | string | yes | The unique identifier of the voice to be used for the separation process. |
No output schema declared.
No examples provided.
simulate_agent_conversation Simulate Agent Conversation ~743
Simulate a conversation between an AI agent and a simulated user to test agent behavior, responses, and conversation flow. Useful for validating agent configurations, prompts, and tool integrations before deployment.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent to simulate. This ID is provided when the agent is created. |
| backup_llm_config | – | – | Fallback LLM configuration for automatic cascading if the primary model fails or times out. Can be disabled, use system defaults, or specify a custom priority order. |
| built_in_tools | object | – | System tools available to the agent during the conversation, such as web search, calculator, or database lookup. |
| cascade_timeout_seconds | number | – | Time in seconds to wait before cascading to a backup LLM if the primary model does not respond. |
| custom_llm | object | – | Custom LLM configuration details when using a proprietary or self-hosted language model. Required if llm is set to 'custom-llm'. |
| disable_first_message_interruptions | boolean | – | Prevent the simulated user from interrupting the agent while the first message is being delivered. |
| dynamic_variables | object | – | Dynamic variables to inject into the prompt and conversation context, enabling parameterized testing scenarios. |
| extra_evaluation_criteria | array | – | Custom evaluation criteria to assess agent performance during the simulation, such as response quality, accuracy, or adherence to guidelines. |
| first_message | string | – | Optional opening message for the agent to deliver. If provided, the agent speaks first; if empty, the simulated user initiates the conversation. |
| hinglish_mode | boolean | – | Enable Hinglish (Hindi-English mix) responses when language is set to Hindi. |
| ignore_default_personality | boolean | – | Exclude the default personality and behavioral guidelines from the system prompt, allowing full control via the custom prompt parameter. |
| knowledge_base | array | – | Knowledge bases the agent can reference to retrieve relevant information and context during conversations. |
| language | string | – | Language code for the agent's speech recognition and text-to-speech capabilities. |
| llm | string | – | The language model to use for generating agent responses. Ensure the selected model is supported in your data residency environment if applicable. |
| max_tokens | integer | – | Maximum number of tokens the model can generate in its response. Use -1 for unlimited tokens (respects model defaults). |
| native_mcp_server_ids | array | – | List of Native MCP (Model Context Protocol) server IDs that provide additional capabilities and integrations to the agent. |
| new_turns_limit | integer | – | Maximum number of conversation turns to generate in the simulation. Prevents excessively long simulations. |
| partial_conversation_history | array | – | Pre-existing conversation history to resume from. Allows testing agent behavior in the context of an ongoing conversation rather than starting fresh. |
| prompt | string | – | System prompt that guides the agent's behavior, personality, and response style. |
| rag | object | – | Retrieval-Augmented Generation (RAG) settings to enable the agent to search and cite information from external sources. |
| reasoning_effort | string | – | Control the model's reasoning depth. Higher effort levels enable more complex reasoning but may increase latency. Only supported by certain models. |
| thinking_budget | integer | – | Maximum number of tokens allocated for the model's internal reasoning process. Set to 0 to disable thinking if the model supports it. |
| timezone | string | – | Timezone for displaying the current time in the system prompt. Use standard timezone identifiers to ensure accurate time context in agent responses. |
| tool_mock_config | object | – | Mock configurations for tools to simulate tool responses without making actual external calls. |
No output schema declared.
No examples provided.
simulate_conversation_stream Simulate Conversation Stream ~652
Simulate a conversation between an agent and a simulated user with streamed responses. The response streams partial message lists that should be concatenated, concluding with a final message containing conversation analysis.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent to simulate the conversation with. |
| backup_llm_config | – | – | Configuration for fallback LLM cascading behavior when the primary model is unavailable or times out. |
| built_in_tools | object | – | Built-in system tools available to the agent during the conversation (e.g., web search, calculator, file operations). |
| cascade_timeout_seconds | number | – | Time in seconds to wait before cascading to a backup LLM if the primary model does not respond. |
| custom_llm | object | – | Configuration object for a custom LLM provider. Required when llm parameter is set to 'custom-llm'. |
| disable_first_message_interruptions | boolean | – | Prevent the simulated user from interrupting the agent while the first message is being delivered. |
| dynamic_variables | object | – | Dynamic variables to inject into the agent's context and prompts during the conversation simulation. |
| extra_evaluation_criteria | array | – | List of custom evaluation criteria to assess the agent's performance during the conversation simulation. |
| first_message | string | – | Optional initial message for the agent to speak. If empty, the agent waits for the simulated user to initiate the conversation. |
| hinglish_mode | boolean | – | Enable Hinglish (Hindi-English mix) responses when language is set to Hindi. |
| ignore_default_personality | boolean | – | Exclude default personality traits and behavioral guidelines from the system prompt. |
| knowledge_base | array | – | List of knowledge bases the agent can reference to provide informed responses. |
| language | string | – | Language code for the agent's speech recognition and text-to-speech processing. |
| llm | string | – | The language model to use for generating agent responses. Must be supported in your data residency environment if applicable. |
| max_tokens | integer | – | Maximum number of tokens the model can generate in its response. Use -1 for no limit. |
| native_mcp_server_ids | array | – | List of Native MCP server identifiers to integrate with the agent for extended functionality. |
| new_turns_limit | integer | – | Maximum number of new conversation turns to generate before ending the simulation. |
| partial_conversation_history | array | – | Existing conversation history to resume from. If empty, the simulation starts fresh. Messages should be in chronological order. |
| prompt | string | – | System prompt that guides the agent's behavior and responses during the conversation. |
| rag | object | – | Configuration for Retrieval-Augmented Generation to enhance agent responses with external data sources. |
| reasoning_effort | string | – | Level of reasoning effort for the model. Only applicable to models that support extended reasoning. |
| thinking_budget | integer | – | Maximum number of tokens allocated for model thinking. Set to 0 to disable thinking if supported by the model. |
| timezone | string | – | Timezone identifier for displaying current time in the system prompt. Use standard timezone names to ensure accurate time context. |
| tool_mock_config | object | – | Configuration for mocking tool responses during simulation to test agent behavior without executing real tools. |
No output schema declared.
No examples provided.
stream_project_snapshot_audio Stream Project Snapshot Audio ~97
Stream audio from a Studio project snapshot. Optionally convert the audio to MPEG format during streaming.
| Name | Type | Req | Description |
|---|---|---|---|
| convert_to_mpeg | boolean | – | Whether to convert the streamed audio to MPEG format. Defaults to false, streaming in the original format. |
| 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 whose audio should be streamed. |
No output schema declared.
No examples provided.
stream_voice_preview Stream Voice Preview ~56
Stream audio data for a voice preview that was previously generated using the voice design endpoint. This operation returns the audio content as a continuous stream.
| Name | Type | Req | Description |
|---|---|---|---|
| generated_voice_id | string | yes | The unique identifier of the generated voice preview to stream. |
No output schema declared.
No examples provided.
submit_batch_calls Submit Batch Calls ~289
Submit a batch call request to schedule multiple outbound calls to recipients. Supports scheduling, concurrency limits, and WhatsApp permission request templates.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | Unique identifier of the conversational AI agent to use for the calls. |
| agent_phone_number_id | string | – | Phone number identifier associated with the agent making the calls. Required for certain call routing configurations. |
| call_name | string | yes | Display name or identifier for this batch call campaign. |
| recipients | array | yes | List of recipient phone numbers or contact identifiers to call. Order is preserved for sequential processing. |
| scheduled_time_unix | integer | – | Unix timestamp (seconds since epoch) for when to start executing the batch calls. If omitted, calls begin immediately. |
| target_concurrency_limit | integer | – | Maximum number of simultaneous calls allowed in this batch. When set, this limit takes precedence over workspace or agent-level capacity settings. |
| timezone | string | – | Timezone identifier (e.g., America/New_York, Europe/London) for interpreting scheduled_time_unix in local context. |
| whatsapp_call_permission_request_template_language_code | string | yes | Language code for the WhatsApp permission request template (e.g., en, es, fr). Must match a supported language for the specified template. |
| whatsapp_call_permission_request_template_name | string | yes | Name of the WhatsApp message template to use for requesting call permissions from recipients. |
No output schema declared.
No examples provided.
submit_conversation_feedback Submit Conversation Feedback ~69
Submit feedback for a conversation to indicate user satisfaction. Feedback can be positive ('like') or negative ('dislike').
| Name | Type | Req | Description |
|---|---|---|---|
| conversation_id | string | yes | The unique identifier of the conversation to provide feedback for. |
| feedback | string | – | The feedback sentiment for the conversation, either positive or negative. |
No output schema declared.
No examples provided.
submit_voice_verification Submit Voice Verification ~137
Submit verification documents for manual review of a PVC (Premium Voice Clone) voice. This process validates the voice identity before it can be used in production.
| Name | Type | Req | Description |
|---|---|---|---|
| extra_text | string | – | Optional additional context or information to support the verification request, such as clarification about the voice or usage intent. |
| files | array | yes | Base64-encoded file content for upload. Array of verification document files to submit for manual review. Documents should be in a supported format and clearly demonstrate voice ownership or authoriz… |
| voice_id | string | yes | The unique identifier of the voice to be verified. Use the voices list endpoint to retrieve available voice IDs. |
No output schema declared.
No examples provided.
train_voice Train Voice ~93
Start a PVC (Personal Voice Cloning) training process for a specified voice. This initiates the model training that enables voice customization and optimization.
| Name | Type | Req | Description |
|---|---|---|---|
| model_id | string | – | The AI model version to use for training. Specifies which voice conversion model architecture to apply during the training process. |
| voice_id | string | yes | The unique identifier of the voice to train. You can retrieve available voices from the voices list endpoint. |
No output schema declared.
No examples provided.
transcribe_audio Transcribe Audio ~929
Transcribe audio or video files to text with support for speaker diarization, multi-channel processing, and entity detection. Supports synchronous responses or asynchronous webhook delivery with optional custom metadata for request tracking.
| Name | Type | Req | Description |
|---|---|---|---|
| additional_formats | array | – | List of additional output formats to generate alongside the default transcript. Each format can optionally include speaker labels and timestamps. Maximum of 10 formats per request. |
| cloud_storage_url | string | – | HTTPS URL of the audio or video file to transcribe. The file must be publicly accessible and under 2GB. Supports cloud storage URLs (S3, Google Cloud Storage, Cloudflare R2) and pre-signed URLs with… |
| diarization_threshold | number | – | Sensitivity threshold for speaker diarization (only applies when diarize is true and num_speakers is not specified). Higher values reduce speaker fragmentation but increase the risk of merging distin… |
| diarize | boolean | – | Whether to perform speaker diarization to identify and label which speaker is talking at each point in the transcript. |
| entity_detection | – | – | Entity detection configuration to identify and extract entities from the transcript. Accepts 'all' for all entity types, specific entity type names, or a list of types/categories (pii, phi, pci, othe… |
| entity_redaction | – | – | Entity types or categories to redact from the transcript text. Accepts the same format as entity_detection ('all', specific categories like 'pii' or 'phi', or a list of entity types). Must be a subse… |
| file | string | – | Base64-encoded file content for upload. The file to transcribe. All major audio and video formats are supported. Exactly one of the file or cloud_storage_url parameters must be provided. The file siz… |
| keyterms | array | – | List of domain-specific words or phrases to bias the model toward recognizing with higher accuracy. Each keyterm must be under 50 characters and contain at most 5 words. Maximum 1000 keyterms per req… |
| language_code | string | – | ISO-639-1 or ISO-639-3 language code of the audio content. Providing the language can improve transcription accuracy; if omitted, language is automatically detected. |
| model_id | string | yes | The transcription model to use. Choose between scribe_v1 (standard) or scribe_v2 (enhanced with additional features like verbatim control). |
| no_verbatim | boolean | – | Whether to remove filler words, false starts, and non-speech sounds from the transcript for a cleaner output. Only supported with the scribe_v2 model. |
| num_speakers | integer | – | Maximum number of speakers expected in the audio. Helps the model predict speaker transitions more accurately. If not specified, the model uses its maximum supported speaker count (up to 32). |
| tag_audio_events | boolean | – | Whether to identify and tag audio events such as laughter, footsteps, and other non-speech sounds in the transcript. |
| timestamps_granularity | string | – | Timestamp precision level in the transcript. 'word' provides timestamps for each word, 'character' provides character-level timestamps within words, and 'none' omits timestamps. |
| use_multi_channel | boolean | – | Whether to transcribe multi-channel audio independently, treating each channel as a separate speaker. Supports up to 5 channels; each word in the response includes a channel_index field indicating it… |
| webhook | boolean | – | Whether to process the request asynchronously and deliver results via configured webhooks. When enabled, the request returns immediately without the transcription result. |
| webhook_id | string | – | ID of a specific webhook endpoint to receive the transcription result. Only valid when webhook is true. If omitted, results are sent to all configured speech-to-text webhooks. |
| webhook_metadata | – | – | Custom metadata to include in webhook responses for request correlation and tracking. Must be a JSON object with maximum depth of 2 levels and total size under 16KB. Useful for associating results wi… |
No output schema declared.
No examples provided.
translate_dubbing_segments Translate Dubbing Segments ~108
Regenerate translations for specified segments and languages in a dubbing project. Automatically transcribes any missing transcriptions but does not regenerate dubs.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project to translate. |
| languages | array | yes | List of target language codes to translate for each specified segment. Only these languages will be generated. |
| segments | array | yes | List of segment identifiers to translate. Only these segments will be processed; order is preserved as provided. |
No output schema declared.
No examples provided.
update_agent_settings Update Agent Settings ~262
Updates agent settings including conversation configuration, platform settings, workflow structure, metadata, and versioning. Changes are applied to the specified agent or branch.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent to update. |
| branch_id | string | – | The branch identifier to target for updates. If not specified, updates apply to the main agent configuration. |
| conversation_config | object | – | Configuration settings that control conversation behavior, orchestration, and interaction patterns. |
| edges | object | – | Workflow edges defining connections and transitions between nodes in the agent's conversation flow. |
| enable_versioning_if_not_enabled | boolean | – | Automatically enable versioning for this agent if not already enabled, allowing you to track and manage configuration changes. |
| name | string | – | A human-readable name for the agent to improve discoverability and organization. |
| nodes | object | – | Workflow nodes representing conversation states, actions, or processing steps in the agent's logic. |
| platform_settings | object | – | Platform-level settings for deployment, integrations, and non-conversation features. |
| tags | array | – | Classification tags for organizing and filtering agents by category or function. |
| version_description | string | – | A description of the changes in this version, used when publishing updates to versioned agents. |
No output schema declared.
No examples provided.
update_agent_test Update Agent Test ~374
Updates an agent response test configuration by ID. Allows modification of test criteria, success/failure examples, dynamic variables, and simulation settings.
| Name | Type | Req | Description |
|---|---|---|---|
| chat_history | array | – | Conversation history to use as context for the test. Ordered list of messages exchanged before the agent response being tested. |
| check_any_tool_matches | boolean | – | When True, the test passes if any tool call matches the criteria. When False, the test fails if the agent returns multiple tool calls. |
| dynamic_variables | object | – | Key-value pairs of dynamic variables to substitute into the agent configuration during test execution. |
| failure_examples | array | – | List of example responses that should be considered failures. Used to validate test behavior. |
| from_conversation_metadata | – | – | Metadata from the conversation this test was originally created from, if applicable. |
| name | string | yes | A descriptive name for the test. |
| simulation_environment | string | – | The environment context for running the simulation test. Defaults to production if not specified. |
| simulation_max_turns | integer | – | Maximum number of conversation turns allowed in simulation tests. Controls test duration and complexity. |
| simulation_scenario | string | – | Description of the simulation scenario and user persona for simulation-based tests. |
| success_condition | string | – | A prompt that evaluates whether the agent's response meets success criteria. Should return a boolean value (True for success, False for failure). |
| success_examples | array | – | List of example responses that should be considered successful outcomes. Used to validate test behavior. |
| test_id | string | yes | The unique identifier of the agent response test to update. |
| tool_call_parameters | – | – | Criteria for evaluating tool calls made by the agent. If not provided, tool call validation is skipped. |
| type | string | – | The type of test to run. Determines how the agent response is evaluated. |
No output schema declared.
No examples provided.
update_audio_native_content Update Audio Native Content ~202
Updates content for an Audio-Native project with optional automatic conversion and publishing. Use this to modify project content and trigger downstream processing workflows.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_convert | boolean | – | Automatically convert the project to audio format after content update. |
| auto_publish | boolean | – | Automatically publish a new project snapshot after conversion completes. Only applies when auto_convert is enabled. |
| file | string | – | Base64-encoded file content for upload. Either txt or HTML input file containing the article content. HTML should be formatted as follows '<html><body><div><p>Your content<… |
| project_id | string | yes | The unique identifier of the Studio project to update. |
No output schema declared.
No examples provided.
update_audio_native_content_from_url Update Audio Native Content from URL ~92
Extracts content from a provided URL, updates the matching AudioNative project, and queues it for conversion and auto-publishing.
| Name | Type | Req | Description |
|---|---|---|---|
| author | string | – | Optional author name to display in the player and insert at the start of the article. Uses the default author from Player settings if not provided. |
| url | string | yes | The web page URL from which to extract content for the AudioNative project. |
No output schema declared.
No examples provided.
update_branch Update Branch ~128
Update agent branch properties including name, archival status, and access control permissions. Allows modification of branch configuration and protection levels.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | The unique identifier of the agent that owns the branch. |
| branch_id | string | yes | The unique identifier of the branch to update. |
| is_archived | boolean | – | Whether to archive the branch. Archived branches are hidden from normal operations but retain their data. |
| name | string | – | New name for the branch. Must be unique within the agent. |
| protection_status | string | – | The access control level required to modify the branch. |
No output schema declared.
No examples provided.
update_chapter Update Chapter ~103
Updates an existing chapter in a Studio project, including its name and content blocks.
| Name | Type | Req | Description |
|---|---|---|---|
| blocks | array | yes | An ordered array of content blocks that comprise the chapter. Each block defines a section of content within the chapter. |
| chapter_id | string | yes | The unique identifier of the chapter to update. |
| name | string | – | The display name of the chapter for identification purposes. |
| project_id | string | yes | The unique identifier of the Studio project containing the chapter. |
No output schema declared.
No examples provided.
update_environment_variable Update Environment Variable ~91
Update an environment variable's values across different environments. Set values to null to remove a specific environment (production environment cannot be removed).
| Name | Type | Req | Description |
|---|---|---|---|
| env_var_id | string | yes | The unique identifier of the environment variable to update. |
| values | object | yes | A mapping of environment names to their values. Set an environment's value to null to remove it from the variable (production environment is required and cannot be removed). |
No output schema declared.
No examples provided.
update_eval_criterion Update Evaluation Criterion ~122
Update an existing evaluation criterion for speech-to-text assessment. Modify the criterion name, evaluation criteria details, and associated fields.
| Name | Type | Req | Description |
|---|---|---|---|
| criteria | array | – | An array of evaluation criteria details. Order and structure should match the evaluation framework requirements. |
| criterion_id | string | yes | The unique identifier of the evaluation criterion to update. |
| fields | array | yes | An array of field identifiers or definitions associated with this evaluation criterion. Specifies which fields are evaluated. |
| name | string | – | The name of the evaluation criterion. Must be between 1 and 200 characters. |
No output schema declared.
No examples provided.
update_phone_number Update Phone Number ~337
Update the routing configuration and credentials for a phone number, including assigned agent, SIP trunk settings, and security policies.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Hostname or IP address where SIP INVITE requests are routed. |
| agent_id | string | – | The ID of the agent to assign to this phone number for handling incoming calls. |
| allowed_addresses | array | – | List of IP addresses or CIDR blocks permitted to use this trunk. Each entry can be a single IP address or a CIDR notation block. |
| allowed_numbers | array | – | List of phone numbers authorized to use this trunk. |
| headers | object | – | Custom SIP X-* headers to include in INVITE requests. Useful for identifying calls or passing metadata to the SIP provider. |
| inbound_trunk_configCredentialsUsername | string | yes | Username credential for inbound SIP trunk authentication. |
| label | string | – | A human-readable label or name for this phone number. |
| livekit_stack | string | – | LiveKit media server stack configuration for call handling. |
| media_encryption | string | – | Media encryption policy for outbound calls. Controls whether RTP traffic is encrypted. |
| outbound_trunk_configCredentialsUsername | string | yes | Username credential for outbound SIP trunk authentication. |
| password | string | – | Password credential for outbound SIP trunk authentication. If omitted, the existing password remains unchanged. |
| phone_number_id | string | yes | The unique identifier of the phone number to update. |
| remote_domains | array | – | List of remote SIP server domains used for validating TLS certificates during secure connections. |
| transport | string | – | SIP transport protocol for signaling. Auto-detection attempts to select the optimal protocol. |
No output schema declared.
No examples provided.
update_project_content Update Project Content ~272
Updates the content of a Studio project. Optionally converts the project to audio format during the update.
| Name | Type | Req | Description |
|---|---|---|---|
| auto_convert | boolean | – | Whether to automatically convert the Studio project to audio format. Defaults to false if not specified. |
| content_blocks | array | – | List of block objects, each with 'sub_type' (e.g., 'p', 'h1', 'h2') and 'nodes' (list of node objects) |
| content_chapters | array | – | List of chapter objects, each with 'name' (string) and 'blocks' (list of block objects) |
| content_nodes | array | – | List of TTS node objects, each with 'type' ('tts_node'), 'text' (string), and 'voice_id' (string) |
| from_document | string | – | Base64-encoded file content for upload. An optional .epub, .pdf, .txt or similar file can be provided. If provided, we will initialize the Studio project with its content. If this is set, 'from_url'… |
| project_id | string | yes | The unique identifier of the Studio project to update. |
No output schema declared.
No examples provided.
update_pronunciation_dictionary Update Pronunciation Dictionary ~99
Partially update a pronunciation dictionary by modifying its name or archive status without affecting the version. Only specified fields will be updated.
| Name | Type | Req | Description |
|---|---|---|---|
| archived | boolean | – | Set whether the pronunciation dictionary should be archived. Archived dictionaries are retained but no longer active. |
| name | string | – | A human-readable name for the pronunciation dictionary used for identification and organization purposes. |
| pronunciation_dictionary_id | string | yes | The unique identifier of the pronunciation dictionary to update. |
No output schema declared.
No examples provided.
update_secret Update Secret ~107
Update an existing secret in the Convai workspace. Modify the secret's type, name, or value by providing the secret ID and updated details.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | yes | The display name or label for the secret. |
| secret_id | string | yes | The unique identifier of the secret to update. |
| type | string | yes | The type or category of the secret (e.g., API key, password, token). |
| value | string | yes | The secret value or credential data to store. |
No output schema declared.
No examples provided.
update_segment_language Update Segment Language ~159
Modify the text and/or timing of a specific segment in a particular language within a dubbing project. Changes are applied only to the specified language and do not automatically trigger dub regeneration.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project containing the segment to modify. |
| end_time | number | – | The end time of the segment in seconds. Defines when the segment ends in the audio timeline. |
| language | string | yes | The language identifier for which the segment content should be modified. |
| segment_id | string | yes | The unique identifier of the segment within the dubbing project to be updated. |
| start_time | number | – | The start time of the segment in seconds. Defines when the segment begins in the audio timeline. |
No output schema declared.
No examples provided.
update_speaker Update Speaker ~186
Update speaker metadata in a dubbing project, including voice selection and styling. Supports both ElevenLabs library voices and voice cloning options.
| Name | Type | Req | Description |
|---|---|---|---|
| dubbing_id | string | yes | The unique identifier of the dubbing project containing the speaker. |
| languages | array | – | List of language codes to apply these speaker changes to. If empty or omitted, changes apply to all languages in the project. |
| speaker_id | string | yes | The unique identifier of the speaker to update. |
| speaker_name | string | – | The display name to assign to this speaker. |
| voice_id | string | – | The voice identifier, either from the ElevenLabs voice library or a cloning option ('track-clone' or 'clip-clone'). |
| voice_style | number | – | The voice style intensity for supported models. Valid range is 0.0 to 1.0, defaults to 1.0. |
No output schema declared.
No examples provided.
update_studio_project Update Studio Project ~211
Updates a Studio project with new metadata, voice settings, and audio processing preferences. Changes apply to the project configuration and affect how new content is generated and exported.
| Name | Type | Req | Description |
|---|---|---|---|
| author | string | – | Optional author name that will be embedded as metadata in exported MP3 files when the project or chapters are downloaded. |
| default_paragraph_voice_id | string | yes | The voice ID to use as the default voice for newly created paragraph sections. |
| default_title_voice_id | string | yes | The voice ID to use as the default voice for newly created title sections. |
| isbn_number | string | – | Optional ISBN number that will be embedded as metadata in exported MP3 files when the project or chapters are downloaded. |
| name | string | yes | The display name of the Studio project used for identification and organization. |
| project_id | string | yes | The unique identifier of the Studio project to update. |
| volume_normalization | boolean | – | When enabled, applies audio postprocessing to downloaded files to ensure compliance with audiobook volume normalization standards. |
No output schema declared.
No examples provided.
update_tool Update Tool ~66
Update the configuration of an existing tool in the workspace. Modify tool settings and behavior by providing updated configuration parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| tool_config | – | yes | The configuration object containing the tool's settings and parameters to be updated. |
| tool_id | string | yes | The unique identifier of the tool to be updated. |
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.