Athena MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATHENA_MODEL | No | Model to use for reasoning | opus |
| ATHENA_EFFORT | No | Reasoning effort level: 'low', 'medium', or 'high' | high |
| ATHENA_APP_URL | No | OpenRouter analytics header for app URL | |
| ATHENA_BACKEND | No | Backend to use: 'claude-code' if 'claude' CLI found, else 'openrouter' | auto |
| ATHENA_APP_NAME | No | OpenRouter analytics header for app name | |
| ATHENA_CLAUDE_CLI | No | Absolute path to 'claude' binary (for claude-code backend) | |
| ATHENA_TIMEOUT_MS | No | Subprocess timeout in milliseconds (for claude-code backend) | 180000 |
| OPENROUTER_API_KEY | No | API key for OpenRouter backend (required if using openrouter) |
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 |
|---|---|
| thinkA | Ask Athena to think. Delegates deep reasoning to a stronger model when you hit a hard problem — architecture decisions, subtle bugs, plan critique, tricky logic. Athena has NO tools; she only reasons and returns a concise response. You must gather relevant context yourself and pass it in via the |
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 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'think' has a clearly defined and distinct purpose focused solely on deep reasoning without any competing alternatives.
A single tool inherently exhibits perfect naming consistency, as there are no other tools to compare against. The tool name 'think' is straightforward and follows a simple verb pattern without any conflicting conventions.
A single tool is generally too few for most server purposes, as it severely limits functionality and scope. While the tool is well-defined for reasoning tasks, the server lacks breadth, making it feel thin and potentially incomplete for broader applications.
The server is severely incomplete for any domain beyond basic reasoning, as it only offers a single tool for deep thinking without supporting actions like file modification, command execution, or network access. This creates significant gaps that will likely cause agent failures in practical workflows.