CLI Bridge MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 133 installs a week from pypi. Last commit 13 Sep 2026.
Other AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.
We read the source, 21 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
proc = subprocess.run(
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
path = os.path.join(config.OVERFLOW_DIR, f"{job_id}.txt")
proc = subprocess.run(
base_env = config.strip_nesting(dict(os.environ)) if config.strip_nesting_env() else os.environ
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cli-bridge-mcp -- uvx cli-bridge-mcp
{
"mcpServers": {
"cli-bridge-mcp": {
"args": [
"cli-bridge-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.cli-bridge-mcp]
command = "uvx"
args = ["cli-bridge-mcp"]
{
"mcpServers": {
"cli-bridge-mcp": {
"args": [
"cli-bridge-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"cli-bridge-mcp": {
"args": [
"cli-bridge-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
CLI_BRIDGE_PROFILE (Cost profile: saver (free-only fan-out, include_paid refused) | balanced (paid only with include_paid) | max (limited/paid join fan-out).), CLI_BRIDGE_TERSE (Response-style preamble level: off | lite (default) | full | ultra.), CLI_BRIDGE_CACHE_TTL_S (Response cache TTL in seconds. 0 = off (default).).
The author declared them in the registry entry; get the values from the project itself.
Token counting & multi-model LLM cost estimates: GPT-4o, Claude, Gemini, 25+. No API key.
Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs
Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local
Unified MCP server for Gemini, Codex, Claude, Grok, Ollama, and Antigravity
Search, resume and convert AI coding sessions (Claude Code, Codex, Gemini, OpenCode, Pi) over MCP.
Bridge Claude with Gemini CLI for AI-to-AI collaboration, code review, and second opinions
Second opinions in Claude Code and any MCP host from GPT, Gemini, Grok, and 400+ OpenRouter models.
No-key travel MCP for Claude Desktop, Codex-style agents, Hermes, and other clients.
Answers built from our own checks of this server.