Installs into .claude/skills of the current project.
Are you the author of Mcp?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/xberg-io-mcp)
---
name: "mcp"
description: "Use liter-llm mcp reference documentation."
---
<!-- This file is auto-generated by alef — DO NOT EDIT. -->
<!-- alef:hash:b284de2d4d7b58d2c9fabcd28373994279620f54d91dce8009d4c2c18921ff8c -->
<!-- To regenerate: alef docs -->
<!-- To verify freshness: alef verify -->
# liter-llm MCP Reference
Use this skill when integrating liter-llm through Model Context Protocol tools, prompts, or resources.
- `cancel_batch`: Cancel an in-progress batch processing job
- `cancel_response`: Cancel an in-progress response (Responses API)
- `chat`: Send a chat completion request to an LLM
- `create_batch`: Create a new batch processing job
- `create_file`: Upload a file to the LLM provider
- `create_response`: Create a new response (Responses API)
- `delete_file`: Delete an uploaded file
- `embed`: Generate text embeddings for the given input
- `file_content`: Retrieve the raw content of an uploaded file
- `generate_image`: Generate images from a text prompt
- `list_batches`: List batch processing jobs
- `list_files`: List uploaded files
- `list_models`: List available models from configured providers
- `moderate`: Check content against moderation policies
- `ocr`: Extract text from an image or document via OCR
- `rerank`: Rerank documents by relevance to a query
- `retrieve_batch`: Retrieve a batch processing job by ID
- `retrieve_file`: Retrieve metadata for an uploaded file
- `retrieve_response`: Retrieve a response by ID (Responses API)
- `search`: Perform a web or document search
- `speech`: Generate speech audio from text (text-to-speech)
- `transcribe`: Transcribe audio to text (speech-to-text)
