claude-max-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAUDE_MAX_MCP_BIN | No | Path to the Claude Code CLI. | claude |
| CLAUDE_MAX_MCP_CWD | No | Working dir for the claude subprocess. | $HOME |
| CLAUDE_MAX_MCP_MODEL | No | Model passed to claude --model. Aliases work (opus, sonnet, haiku). | claude-opus-4-7 |
| CLAUDE_MAX_MCP_TOOL_NAME | No | Override the exposed tool name. | ask_claude |
| CLAUDE_MAX_MCP_EXTRA_ARGS | No | Extra space-separated args to pass to claude -p. | |
| CLAUDE_MAX_MCP_TIMEOUT_MS | No | How long a single delegated call can run (in milliseconds). | 600000 |
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 |
|---|---|
| ask_claudeA | Delegate a substantive task to Claude Code, billed against the user's Claude Max / Pro subscription (model: claude-opus-4-7). Use this for: code generation, deep reasoning, multi-step engineering, refactoring, or anything that needs more capability than the routing model can reliably deliver. The receiver has NO memory of the calling agent's conversation — include everything Claude needs in the prompt argument: the user's verbatim request, project / file context, relevant prior messages, and what kind of output you want back. Returns Claude's full text response. |
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. The tool's purpose is distinct and unambiguous.
The single tool name 'ask_claude' follows a clear verb_noun pattern. Consistency is perfect due to the lack of other tools.
The server contains only one tool, which is appropriate for its narrow scope of delegating tasks to Claude Code. While a slightly larger set might be expected for a full SDK, the single tool is well-justified and not trivial.
The tool fully covers the stated domain of delegating substantive tasks to Claude Code. No additional tools are necessary for the server's purpose.