mcp-llm
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MIN_P | No | Min-p parameter for the model (e.g., 0.05) | |
| LLM_TOP_K | No | Top-k parameter for the model (e.g., 40) | |
| LLM_TOP_P | No | Top-p parameter for the model (e.g., 0.85) | |
| LLM_NUM_CTX | No | Context window size (e.g., 16384) | |
| LLM_BASE_URL | No | Base URL for the model provider (e.g., https://ollama.internal, http://my-openai-compatible-server.com:3000/v1) | |
| LLM_TIMEOUT_S | No | Timeout in seconds for LLM requests (e.g., 240 for 4 minutes) | 240 |
| LLM_MODEL_NAME | Yes | The name of the model to use (e.g., qwen2-32b:q6_k, anthropic.claude-3-7-sonnet-20250219-v1:0) | |
| OPENAI_API_KEY | No | API key for OpenAI (required when using OpenAI provider) | |
| LLM_TEMPERATURE | No | Temperature parameter for the model (e.g., 0.2) | |
| LLM_MODEL_PROVIDER | Yes | The model provider (e.g., bedrock, ollama, openai, openai-compatible) | |
| LLM_ALLOW_FILE_WRITE | No | Set to true to allow the generate_code_to_file tool to write to files | false |
| LLM_REPETITION_PENALTY | No | Repetition penalty parameter for the model (e.g., 1.05) | |
| LLM_SYSTEM_PROMPT_ASK_QUESTION | No | System prompt for the ask_question tool | |
| LLM_SYSTEM_PROMPT_GENERATE_CODE | No | System prompt for the generate_code tool | |
| LLM_SYSTEM_PROMPT_GENERATE_DOCUMENTATION | No | System prompt for the generate_documentation tool |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_codeC | Generate code based on a description |
| generate_code_to_fileB | Generate code and write it directly to a file at a specific line number |
| generate_documentationC | Generate documentation for code |
| ask_questionC | Ask a question to the LLM |
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 4 tools
The tools have overlapping purposes that could cause confusion. 'generate_code' and 'generate_code_to_file' both generate code, with the latter adding file writing functionality, which might lead to misselection when file output isn't needed. However, 'ask_question' and 'generate_documentation' are more distinct in their purposes, helping to mitigate some ambiguity.
The naming follows a consistent verb_noun pattern throughout, such as 'ask_question' and 'generate_documentation'. There is a minor deviation with 'generate_code_to_file', which includes a prepositional phrase, but overall the pattern is clear and readable, maintaining good consistency.
With 4 tools, the count is slightly low but reasonable for an LLM-focused server. It covers core functionalities like questioning, code generation, and documentation, though it might feel thin if more advanced features are expected. The scope is well-defined, so the number is appropriate for basic operations.
There are notable gaps in the tool surface for an LLM domain. While it covers code generation and documentation, it lacks tools for editing, refactoring, or analyzing existing code, and there's no way to manage conversations or context. This could lead to agent failures in more complex workflows, but core tasks are addressed.