Llm Cli Gateway
未认领MCP server providing unified access to Claude Code, Codex, Gemini, Grok and Mistral CLIs with session management, retry logic, and async job orchestration.
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'llm-cli-gateway' -- 'npx' '-y' 'llm-cli-gateway'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
23 个工具中显示 23 个
文档中列出的工具 (23)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
ask_model
ask one provider through the simplified surface.
claude_request
Execute a Claude Code request with optional session management.
codex_fork_session
Fork an existing Codex session into a new branch (codex fork <SESSIONID--last> <prompt>), preserving the original session's history while the fork diverges. Unlike Codex new and resume requests, this command remains argv-bound and rejects oversized UTF-8 prompts as non-retryable inputtoolarge.
codex_request
Execute a Codex request with optional session tracking.
consensus_check
check whether providers agree with a claim.
gemini_request
Execute a Google Antigravity CLI (agy) request with session support.
grok_request
Execute a Grok CLI (xAI) request with session support.
job_status
and jobresult: poll and collect validation job outputs.
list_available_models
list the models each provider CLI exposes through the simplified surface.
list_models
List available models for each CLI.
red_team_review
challenge a plan, answer, or document for risks and failure modes.
review_changes
capture one complete Git review artifact, fence repository
second_opinion
ask one provider to review an answer.
session_clear_all
Clear all sessions, optionally for a specific CLI.
session_create
Create a new session for a specific CLI.
session_delete
Delete a specific session.
session_get
Retrieve details for a specific session.
session_list
List all sessions, optionally filtered by CLI.
session_set_active
Set the active session for a specific CLI.
synthesize_validation
run an explicit judge model after provider results have
timeoutMs
, optimizePrompt, optimizeResponse, forceRefresh, correlationId
validate_with_models
ask two or more providers to independently validate a question.
validation_receipt
retrieve the canonically hashed immutable receipt of a terminal cross-LLM validation run by validationId (returns minted pending verificationfailed expiredunminted notfound, own-or-not-found). verificationfailed means a stored receipt exists but disagrees with its durable run, which is a defect to i