9Router MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NINEROUTER_KEY | No | Gateway bearer key when authentication is enabled. | |
| NINEROUTER_URL | No | Gateway base URL, optionally ending in /v1. A reverse-proxy prefix is preserved. | http://localhost:20128 |
| NINEROUTER_TOOLS | No | Comma-separated allowlist of full tool names. | all tools |
| NINEROUTER_MAX_BYTES | No | Maximum upstream request or response body size. MCP serialization and media base64 can increase the final message size. | 8388608 |
| NINEROUTER_TIMEOUT_MS | No | Request deadline, including response body reads. Set the host's tool timeout accordingly. | 120000 |
| NINEROUTER_MAX_CONCURRENT | No | In-flight requests per server process. | 4 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ninerouter_healthA | Check whether the configured 9Router instance is healthy. |
| ninerouter_list_modelsC | List chat models, fallback combos, or models for a specific capability. |
| ninerouter_model_infoC | Inspect the parameters and capabilities advertised for a model. |
| ninerouter_list_voicesB | List text-to-speech voices for a provider and optional language. |
| ninerouter_web_searchC | Search public web, news, or X using a configured 9Router search provider. |
| ninerouter_web_fetchB | Extract a public web page as Markdown, text, or HTML through 9Router. |
| ninerouter_chatB | Run a 9Router chat or vision model. Select the API dialect and supply its native request fields. |
| ninerouter_count_tokensC | Count tokens for an Anthropic Messages request using 9Router. |
| ninerouter_compact_responseC | Compact an OpenAI Responses conversation through 9Router. |
| ninerouter_generate_imageC | Generate or edit an image using the selected 9Router model. |
| ninerouter_text_to_speechC | Convert text to speech using a configured 9Router voice. |
| ninerouter_transcribe_audioC | Transcribe inline base64 audio through 9Router using a multipart upload. |
| ninerouter_generate_videoC | Submit a video generation job using a prompt or source image. |
| ninerouter_edit_videoC | Submit an edit job using a source video. |
| ninerouter_extend_videoC | Submit an extension job using a source video. |
| ninerouter_video_statusC | Poll a video job with the job reference returned at submission. |
| ninerouter_embedC | Create embeddings for text, text batches, or supported token inputs. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 17 tools
Most tools target clearly distinct operations across chat, embeddings, media, search, and utility tasks. The closest overlap is between list_models and model_info, and among the video job tools, but their descriptions provide enough separation to select correctly.
All tools share a consistent ninerouter_ prefix and snake_case naming. Most names use an action-oriented verb_noun pattern, with a few noun-based read/status names such as health, model_info, and video_status as minor deviations.
Seventeen tools is somewhat heavy but justified by the broad multi-modal gateway scope: chat, models, embeddings, images, video, speech, transcription, web access, and token utilities. Each tool maps to a meaningful capability rather than duplicating another.
The surface covers the main AI gateway workflows well, including model discovery, chat, embeddings, media generation, speech, transcription, web search/fetch, and health checks. Minor gaps exist around lifecycle operations such as canceling or listing video jobs and possible provider/model management, but agents can work around these.