Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MIN_PNoMin-p parameter for the model (e.g., 0.05)
LLM_TOP_KNoTop-k parameter for the model (e.g., 40)
LLM_TOP_PNoTop-p parameter for the model (e.g., 0.85)
LLM_NUM_CTXNoContext window size (e.g., 16384)
LLM_BASE_URLNoBase URL for the model provider (e.g., https://ollama.internal, http://my-openai-compatible-server.com:3000/v1)
LLM_TIMEOUT_SNoTimeout in seconds for LLM requests (e.g., 240 for 4 minutes)240
LLM_MODEL_NAMEYesThe name of the model to use (e.g., qwen2-32b:q6_k, anthropic.claude-3-7-sonnet-20250219-v1:0)
OPENAI_API_KEYNoAPI key for OpenAI (required when using OpenAI provider)
LLM_TEMPERATURENoTemperature parameter for the model (e.g., 0.2)
LLM_MODEL_PROVIDERYesThe model provider (e.g., bedrock, ollama, openai, openai-compatible)
LLM_ALLOW_FILE_WRITENoSet to true to allow the generate_code_to_file tool to write to filesfalse
LLM_REPETITION_PENALTYNoRepetition penalty parameter for the model (e.g., 1.05)
LLM_SYSTEM_PROMPT_ASK_QUESTIONNoSystem prompt for the ask_question tool
LLM_SYSTEM_PROMPT_GENERATE_CODENoSystem prompt for the generate_code tool
LLM_SYSTEM_PROMPT_GENERATE_DOCUMENTATIONNoSystem 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

CapabilityDetails
tools
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3/5.0

Scored across 4 tools

Disambiguation3/5

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.

Naming Consistency4/5

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.

Tool Count4/5

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.

Completeness3/5

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.

Maintenance

ActivityInactive
ResponsivenessNo issues