A
licenseA
qualityD
maintenanceEnables AI agents to interact programmatically with Claude Code CLI, managing sessions, streaming outputs, and handling permission requests.
7
3 npm
1
MIT
Claude Code MCP Server
Related Servers
Alternatives to Claude Code MCP Server
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceWraps Anthropic Claude Code CLI as tools, allowing MCP clients to invoke headless Claude Code sessions.2393 npmMIT
- AlicenseBqualityCmaintenanceEnables AI agents to start, monitor, follow up on, stop, and collect results from headless Claude Code CLI sessions, with queuing, budgets, locks, and wake-up notifications.9MIT
- AlicenseNot gradedqualityDmaintenanceDelegates coding tasks to the local Claude Code CLI via MCP, offering run, review, and status tools for MCP-compatible agents.25 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables voice assistants to start, monitor, message, and approve local Claude Code sessions on your computer, including sessions already open in a terminal. It exposes session management, recaps, approvals, and history search as MCP tools.7GPL 3.0
- AlicenseNot gradedqualityBmaintenanceExposes interactive Claude Code CLI sessions running inside tmux across one or more machines as MCP tools, enabling agents to list, create, read, and drive those sessions over stdio.1MIT
TDQS
A4.4/5.0
Scored across 7 tools
Disambiguation4/5
Each tool has a largely distinct role: create cloud session, run local job, send follow-up, cancel, usage, auth. The main soft spot is claude_get_session, which serves two purposes (polling a background job and inspecting a session's branch/PR), but its description clearly separates the job-id versus session-id modes so an agent can still pick correctly.
Naming Consistency4/5
All names share a claude_ prefix and snake_case, with verb_noun forms like create_cloud_session, send_followup, get_session, cancel_session, run_local. The two noun-only names (claude_usage, claude_auth_status) are a minor deviation but are still readable as report-style tools.
Tool Count5/5
Seven tools is well-scoped for a Claude Code job runner: lifecycle (create/run/cancel/poll), interaction (followup), and environment checks (auth/usage). No tool feels redundant or missing from the count perspective.
Completeness4/5
The surface covers the full lifecycle of cloud and local jobs plus auth and usage preflight checks, which are the key dead-end preventers. The notable gap is the absence of a list/enumerate tool, so agents must retain session and job ids themselves, with no cleanup operation for stale sessions.
Maintenance
ActivityMaintained
ResponsivenessOutdated data