Claude Code MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLAUDE_BIN | No | Path or name of the Claude Code CLI binary. | claude |
| CLAUDE_MCP_CWD | No | Directory the CLI runs in. claude --cloud packages this tree, and workspace trust is resolved from it. A relative path is resolved at startup. The path must exist and be a directory. | process working directory |
| CLAUDE_MCP_PYTHON | No | Python 3 interpreter used to allocate the pseudo-terminal for create. | python3 |
| CLAUDE_MCP_TRUST_CWD | No | 1, true, or yes lets create accept Claude Code's workspace-trust dialog for CLAUDE_MCP_CWD only (the process working directory when that is unset). 0, false, no, or unset leaves the dialog unanswered and the call fails with WORKSPACE_NOT_TRUSTED. | |
| CLAUDE_MCP_TIMEOUT_MS | No | Hard timeout for each spawned CLI process, in milliseconds (positive integer). On timeout the process gets SIGTERM, then SIGKILL 5 s later. | 300000 |
| CLAUDE_CLOUD_ENVIRONMENT_ID | No | Default cloud environment id (for example ccpool_...), passed as --environment when a call does not pass environment_id. |
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_create_cloud_sessionA | Create a new Claude Code cloud session via |
| claude_send_followupA | Queue a follow-up message into an existing Claude Code cloud session via |
| claude_auth_statusA | Report whether the local Claude Code CLI is signed in, via |
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 3 tools
Each tool targets a distinct action: creating a cloud session, sending a follow-up message, and checking CLI auth. There is no plausible overlap or way an agent could confuse them.
All three tools use the same claude_ prefix followed by a clear snake_case verb_noun form (create_cloud_session, send_followup, auth_status). The pattern is entirely predictable.
Three tools is a lean but coherent set for driving Claude Code cloud sessions. It is slightly under-scoped, but no tool feels redundant or bloated.
The surface covers session creation, follow-ups, and auth, but has notable gaps: no way to list existing sessions, read a session's output/status, or terminate a session. Agents can partially work around this via the returned session_url, but the lifecycle is incomplete.