LLM CLI Gateway
A unified MCP gateway for running Claude Code, Codex, Gemini, Grok, and Mistral CLI tools from a single endpoint. Ships sync and async job tools with persistence, session continuity, and cache-aware prompting including Claude's cache_control blocks. Built for cross-LLM validation workflows where you want second opinions or consensus checks without reconfiguring clients. Includes git worktree isolation for multi-agent review loops, HTTP transport with bearer auth for remote clients, and a Go bootstrapper with setup, doctor, and upgrade commands. Targets single-user personal appliance deployments with Sigstore-signed releases and npm provenance. Reach for this when you're orchestrating multi-model code review or testing assistant outputs across providers from one MCP integration point.
- GitHub stars
- 8
- tools
- 12
- transport
- STDIO
- last updated
- May 30, 2026
Tools
12 toolsPublic tool metadata for what this MCP can expose to an agent.
validate_with_modelsask two or more providers to independently validate a question.
ask two or more providers to independently validate a question.
No parameter schema in public metadata yet.
review_changescapture one complete Git review artifact, fence repository content as untrusted data, and start read-only independent reviewers.
capture one complete Git review artifact, fence repository content as untrusted data, and start read-only independent reviewers.
No parameter schema in public metadata yet.
second_opinionask one provider to review an answer.
ask one provider to review an answer.
No parameter schema in public metadata yet.
red_team_reviewchallenge a plan, answer, or document for risks and failure modes.
challenge a plan, answer, or document for risks and failure modes.
No parameter schema in public metadata yet.
consensus_checkcheck whether providers agree with a claim.
check whether providers agree with a claim.
No parameter schema in public metadata yet.
ask_modelask one provider through the simplified surface.
ask one provider through the simplified surface.
No parameter schema in public metadata yet.
synthesize_validationrun an explicit judge model after provider results have been collected.
run an explicit judge model after provider results have been collected.
No parameter schema in public metadata yet.
list_available_modelslist the models each provider CLI exposes through the simplified surface.
list the models each provider CLI exposes through the simplified surface.
No parameter schema in public metadata yet.
job_statuspoll validation job outputs.
poll validation job outputs.
No parameter schema in public metadata yet.
job_resultcollect validation job outputs.
collect validation job outputs.
No parameter schema in public metadata yet.
validation_receiptretrieve the canonically hashed immutable receipt of a terminal cross-LLM validation run by validationId.
retrieve the canonically hashed immutable receipt of a terminal cross-LLM validation run by validationId.
No parameter schema in public metadata yet.
claude_requestExecute a Claude Code request with optional session management.
Execute a Claude Code request with optional session management.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
llm-cli-gateway
"Without consultation, plans are frustrated, but with many counselors they succeed." — Proverbs 15:22 (LSB)
Secure local control plane for AI coding agents.
Details
- Repository
- github.com/verivus-oss/llm-cli-gateway
- Category
- AI & LLM Tools
- Package
llm-cli-gateway- Transport
- STDIO
- Registry
- MCP registry, active
More from verivus-oss
Related AI & LLM Tools MCP servers
View all
Meta Prompt Mcpkapillamba4/meta-prompt-mcpMCP server providing official Google and Anthropic prompting guides for meta-prompt generation.2stars
Gemini Researchercapybearista/gemini-researcherStateless MCP server that proxies research queries to Gemini CLI, reducing agent context/model usage0stars
Gnosis Memorytekgnosis/gnosismemoryPersistent memory and vector search for AI agents. Hosted, OAuth-protected via Google sign-in.0stars
Llm Wiki Mcpflsteven87/llm-wiki-mcpMCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.0stars
Agent Output Guardagenson-tools/agent-output-guard-mcpValidate and verify data from other agents before acting on it. Zero LLM costs.0stars
Vector Search APIbr0ski777/vector-search-x402In-memory vector search with TF-IDF and cosine similarity. x402 micropayment.0stars