claude-code-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
| logging | {} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| claude_codeA | Start a background Claude Code run and return sessionId immediately. No final result is returned here. Main loop: call claude_code_check(action='poll'), store nextCursor, and keep polling until status becomes idle, error, or cancelled. If actions[] contains permission requests, answer them with claude_code_check(action='respond_permission'). respond_user_input is not supported. Adjust polling cadence to progress: poll faster while new events/actions are arriving, and slower when the session is quietly thinking. Long-running work is normal: Claude Code can keep working for 10+ minutes, especially with high/max effort, so wait for polling to settle before assuming it is stuck. If you want to continue after a run pauses or finishes, use claude_code_reply with the same sessionId instead of starting a new claude_code session. For runtime-authoritative tool names, call claude_code_check with pollOptions.includeTools=true. Internal tools (runtime list when includeTools=true): [agent]
[execute]
[file_read]
[file_write]
[interaction]
[mcp]
[network]
Permission control: allowedTools pre-approves tools but is not a strict allowlist unless strictAllowedTools=true; disallowedTools always denies; other tools may require approval. |
| claude_code_replyA | Send a follow-up to an existing session. Reuse the same sessionId instead of starting a new claude_code session when you want to continue. Returns immediately; poll with claude_code_check. Use diskResumeConfig only when the in-memory session is missing and disk resume is enabled. |
| claude_code_sessionB | List, inspect, cancel, or interrupt sessions. |
| claude_code_checkA | Poll session state or answer a pending permission request. POLLING FREQUENCY: Do NOT poll every turn. Claude Code tasks take minutes, not seconds.
Main loop: call action='poll', persist nextCursor, and use action='respond_permission' for approvals. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| server_info | Server metadata (version/platform/runtime). |
| internal_tools | Claude Code internal tool catalog (runtime-aware). |
| gotchas | High-signal failure modes, symptoms, and remedies for this MCP workflow. |
| quickstart | Canonical async start, poll, permission, and continue flow for MCP callers. |
| errors | Structured error codes and remediation hints. |
| compat_report | Compatibility diagnostics for MCP clients and local runtime assumptions. |
TDQS
Scored across 4 tools
Each tool has a distinct purpose: starting a session, polling/responding, sending follow-ups, and managing sessions. No overlap.
All tools follow the claude_code_<action> pattern except the base start command (claude_code). This minor deviation is consistent enough for easy recognition.
Four tools cover the essential operations for managing Claude Code sessions without unnecessary complexity.
The tool surface covers the full lifecycle: start, poll/respond to permissions, send follow-ups, and manage sessions. No obvious gaps.