claude-octopus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAUDE_CWD | No | Working directory | process.cwd() |
| CLAUDE_BETAS | No | Beta features (comma-separated) | |
| CLAUDE_MODEL | No | Model (`sonnet`, `opus`, `haiku`, or full ID) | |
| CLAUDE_EFFORT | No | Thinking effort (`low`, `medium`, `high`, `max`) | |
| CLAUDE_PLUGINS | No | Local plugin paths (comma-separated) | |
| CLAUDE_SETTINGS | No | Path to settings JSON or inline JSON | |
| CLAUDE_MAX_TURNS | No | Max conversation turns | |
| CLAUDE_TOOL_NAME | No | Tool name prefix (`<name>` and `<name>_reply`) | claude_code |
| ANTHROPIC_API_KEY | No | Anthropic API key for this agent | inherited from parent |
| CLAUDE_DESCRIPTION | No | Tool description shown to the host AI | |
| CLAUDE_MCP_SERVERS | No | MCP servers for the inner agent (JSON) | |
| CLAUDE_SERVER_NAME | No | MCP server name in protocol handshake | claude-octopus |
| CLAUDE_FACTORY_ONLY | No | Only expose the factory wizard tool | false |
| CLAUDE_ALLOWED_TOOLS | No | Comma-separated tool restriction (available tools) | all |
| CLAUDE_APPEND_PROMPT | No | Appended to the default prompt | |
| CLAUDE_SYSTEM_PROMPT | No | Replaces the default Claude Code system prompt | |
| CLAUDE_MAX_BUDGET_USD | No | Max spend per invocation | |
| CLAUDE_ADDITIONAL_DIRS | No | Extra directories to grant access (comma-separated) | |
| CLAUDE_PERMISSION_MODE | No | Permission mode (`default`, `acceptEdits`, `bypassPermissions`, `plan`) | default |
| CLAUDE_PERSIST_SESSION | No | Enable session resume (`true`/`false`) | true |
| CLAUDE_SETTING_SOURCES | No | Settings to load: `user`, `project`, `local` | |
| CLAUDE_CODE_OAUTH_TOKEN | No | Claude Code OAuth token for this agent | inherited from parent |
| CLAUDE_DISALLOWED_TOOLS | No | Comma-separated tool blacklist |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| claude_codeA | Send a task to an autonomous Claude Code agent. It reads/writes files, runs shell commands, searches codebases, and handles complex software engineering tasks end-to-end. Returns the result text plus a session_id for follow-ups via claude_code_reply. |
| claude_code_replyA | Continue a previous claude_code conversation by session ID. Use this for follow-up questions, iterative refinement, or multi-step workflows that build on prior context. |
| claude_code_timelineA | Query the cross-agent workflow timeline. No args: list all runs. run_id: show one run's agent sequence. session_id: retrieve timeline entry and session metadata. Use claude_code_transcript for full transcripts. |
| claude_code_transcriptA | Retrieve the full conversation transcript for a session from Claude Code's storage. Returns chronological user/assistant messages. Use session_id from a prior query or timeline lookup. |
| claude_code_reportA | Generate a self-contained HTML report of a workflow run. No args: list all runs. run_id: detailed report for that run with agent sequence, cost breakdown, and collapsible transcripts. Save the returned HTML to a file and open in a browser. |
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 5 tools
Each tool targets a distinct aspect of Claude Code interaction: initiation, continuation, report generation, timeline querying, and transcript retrieval. No two tools have overlapping purposes or ambiguous boundaries.
All tools follow a consistent claude_code_<noun> pattern (except claude_code itself, which is the base action). The naming is predictable and descriptive, aiding quick identification of each tool's role.
With 5 tools, the set is tightly scoped to the domain of managing Claude Code sessions. Each tool contributes a necessary function without redundancy, and the count is appropriate for the server's focused purpose.
The tools cover the core workflow: initiating, continuing, reporting, and reviewing sessions. A minor gap is the lack of a cancel/stop tool, but for most use cases the set is complete.