Kobold MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| kobold_max_context_lengthB | Get current max context length setting |
| kobold_max_lengthB | Get current max length setting |
| kobold_generateC | Generate text with KoboldAI |
| kobold_model_infoB | Get current model information |
| kobold_versionB | Get KoboldAI version information |
| kobold_perf_infoC | Get performance information |
| kobold_token_countC | Count tokens in text |
| kobold_detokenizeC | Convert token IDs to text |
| kobold_transcribeC | Transcribe audio using Whisper |
| kobold_web_searchC | Search the web via DuckDuckGo |
| kobold_ttsC | Generate text-to-speech audio |
| kobold_abortB | Abort the currently ongoing generation |
| kobold_last_logprobsB | Get token logprobs from the last request |
| kobold_sd_modelsB | List available Stable Diffusion models |
| kobold_sd_samplersB | List available Stable Diffusion samplers |
| kobold_txt2imgC | Generate image from text prompt |
| kobold_img2imgC | Transform existing image using prompt |
| kobold_interrogateC | Generate caption for image |
| kobold_chatC | Chat completion (OpenAI-compatible) |
| kobold_completeC | Text completion (OpenAI-compatible) |
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 20 tools
Most tools have distinct purposes (e.g., text generation vs. image generation vs. utility functions), but there is some overlap between kobold_chat and kobold_complete (both for text generation) and kobold_token_count and kobold_detokenize (both token-related). Descriptions help clarify, but an agent might occasionally confuse similar tools.
All tool names follow a consistent snake_case pattern with a 'kobold_' prefix and descriptive suffixes (e.g., kobold_generate, kobold_model_info). This uniformity makes the set predictable and easy to navigate, with no deviations in style.
With 20 tools, the count is borderline high for a single server, as it covers diverse domains like text generation, image processing, audio, and utilities. While each tool serves a purpose, the scope feels broad, potentially overwhelming for agents focused on specific tasks.
The tool set covers core AI functionalities well, including text and image generation, audio processing, and model management. Minor gaps exist, such as no explicit tool for updating settings or managing generation parameters beyond aborting, but agents can work around these with the available tools.