io.github.mcp-dir/elevenlabs-mcp
ElevenLabs
ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m
alive probed 2026-10-14 · HTTP 200
155tools
62ktokens in Claude Opus 5.5
65ktokens in Claude Code
31.1 %of a 200k context window
32ko200k_base estimate
255 msto initialize
193 msto list tools
- Endpoint
- https://api.mcp.ai/p_elevenlabs (streamable-http)
- Host
- api.mcp.ai
- Protocol
- 2025-11-25
- Reports itself as
- mcp-ai 0.9.372
- Capabilities
- tools
- Instructions
- 507 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/mcp-dir/elevenlabs-mcp
- Registry
- active, updated 2026-08-21 · registry entry
- Reachable
- 11 of the last 12 probes
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| elevenlabs_update_speech_engine | 1 899 | 6 % |
| elevenlabs_create_speech_engine | 1 740 | 5 % |
| elevenlabs_generate | 1 295 | 4 % |
| elevenlabs_create_auth_connection | 788 | 2 % |
| marketplace | 702 | 2 % |
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-10-14 09:27 | alive | 255 ms | 155 | 62k | 32k |
| 2026-10-13 11:22 | server error | ||||
| 2026-10-11 10:27 | alive | 118 ms | 155 | 62k | 32k |
| 2026-10-09 11:24 | alive | 215 ms | 155 | 62k | 32k |
| 2026-10-07 11:16 | alive | 440 ms | 155 | 62k | 32k |
| 2026-10-06 11:03 | alive | 1.3 s | 155 | 62k | 32k |
| 2026-10-05 15:04 | alive | 2.8 s | 155 | 62k | 32k |
| 2026-10-05 00:39 | alive | 78 ms | 155 | 32k | |
| 2026-10-04 10:07 | alive | 141 ms | 155 | 32k | |
| 2026-10-04 08:02 | alive | 114 ms | 155 | 32k | |
| 2026-10-03 20:41 | alive | 151 ms | 155 | 32k | |
| 2026-10-03 17:58 | alive | 261 ms | 155 | 32k |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.mcp-dir/elevenlabs-mcp)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.