This record as markdown: /tools/aiwerk-mcp-server-elevenlabs/get-speech-history.md
What get_speech_history does on Elevenlabs
AI agents call get_speech_history to retrieve information from Elevenlabs without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
search | string | null | — | search term used for filtering |
source | object | — | Source of the generated history item |
model_id | string | null | — | Model ID to filter history items by. |
voice_id | string | null | — | Voice ID to be filtered for, you can use GET https://api.elevenlabs.io/v1/voices to receive a list of voices and their IDs. |
page_size | number | — | How many history items to return at maximum. Can not exceed 1000, defaults to 100. |
sort_direction | object | — | Sort direction for the results. |
date_after_unix | number | null | — | Unix timestamp to filter history items after this date (inclusive). |
date_before_unix | number | null | — | Unix timestamp to filter history items before this date (exclusive). |
start_after_history_item_id | string | null | — | After which ID to start fetching, use this parameter to paginate across a large collection of history items. In case this parameter is not provided history item |
Parameters from the server's own tool schema.
Why get_speech_history is rated Low
Even though get_speech_history only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs get_speech_history safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Elevenlabs, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_speech_history, this is the rule to start with:
get_speech_history is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Elevenlabs, apply this rule, and every get_speech_history call is checked against it from then on.
Questions about get_speech_history
List Generated Items. It is categorised as a Read tool in the Elevenlabs MCP Server, which means it retrieves data without modifying state.
get_speech_history accepts 9 parameters: search, source, model_id, voice_id, page_size, sort_direction, date_after_unix, date_before_unix, start_after_history_item_id. The full parameter table on this page comes from the server's own tool schema.
Register the Elevenlabs MCP server in PolicyLayer and add a rule for get_speech_history: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Elevenlabs. Nothing to install.
get_speech_history is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_speech_history rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_speech_history. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_speech_history is provided by the Elevenlabs MCP server (@aiwerk/mcp-server-elevenlabs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Elevenlabs, and thousands of servers like it.
This server
Across the catalogue