A Model Context Protocol server starts the project's multi-model service with Python. Model Context Protocol is a standard way for an agent to call external tools and services.

It is for running the `multillm` service with its provider, workspace, timing, and execution settings.

It provides the configured connection through which the coding agent can use the multi-model service.

multi_llm — MCP server by beastlabai/multi-llm-plugin

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/beastlabai/multi-llm-plugin

Installing this writes the configuration, not the program: `python3` runs a file from the repository, so clone it first and make the path in the command match where you put it.

Made for: Claude Code.

Or install multi-llm, the plugin that ships this one along with the rest of its 1 skill, 3 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/beastlabai/multi-llm-plugin/multi-llm-multi_llm/github.svg)](https://agentmods.dev/mcp/beastlabai/multi-llm-plugin/multi-llm-multi_llm)

Your own site

<a href="https://agentmods.dev/mcp/beastlabai/multi-llm-plugin/multi-llm-multi_llm"><img src="https://agentmods.dev/badge/mcp/beastlabai/multi-llm-plugin/multi-llm-multi_llm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/beastlabai/multi-llm-plugin/multi-llm-multi_llm"><img src="https://agentmods.dev/badge/mcp/beastlabai/multi-llm-plugin/multi-llm-multi_llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

multi_llm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packaging/codex/multi-llm/.mcp.json · 31 lines

What it actually says

{
  "multi_llm": {
    "command": "python3",
    "args": [
      "./mcp/server.py"
    ],
    "cwd": ".",
    "env_vars": [
      "CODEX_HOME",
      "MULTI_LLM_PROVIDERS_CONFIG",
      "MULTI_LLM_PROVIDERS_CONFIG_PERMISSIVE",
      "MULTI_LLM_GIT_CREDENTIAL_HELPER",
      "MULTI_LLM_HOST",
      "MULTI_LLM_UV",
      "MULTI_LLM_UV_RUN_ARGS",
      "MULTI_LLM_SKILL_DIR",
      "MULTI_LLM_MAX_DETACHED",
      "MULTI_LLM_HEARTBEAT_INTERVAL_S",
      "MULTI_LLM_HANDSHAKE_TIMEOUT_S",
      "MULTI_LLM_REPLAY_FLAGS",
      "MULTI_LLM_LEGACY_INSTRUCTIONS",
      "MULTI_LLM_CODEX_UNSANDBOXED_WRITES",
      "UV_PROJECT_ENVIRONMENT",
      "UV_CACHE_DIR",
      "UV_OFFLINE",
      "PWD"
    ],
    "tool_timeout_sec": 900,
    "default_tools_approval_mode": "approve"
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

14d ago First seen · 31 lines scan A 8d81b3d7fc8a

Subscribe to this mod's changes

multi_llm is an MCP server published in the GitHub repository beastlabai/multi-llm-plugin (12 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-24.

Building agents

multi_llm next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
multi_llmbeastlabai/multi-llm-plugin	MCP server	12	5d ago	MIT	A	—	Claude Code
docs-langchainlangchain-ai/langchain	MCP server	149k	yesterday	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
component-explorermicrosoft/vscode	MCP server	195k	yesterday	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
codex_message_boardopenai/codex	MCP server	133k	yesterday	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
playwright-testmicrosoft/playwright	MCP server	99k	yesterday	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
reference-langchainlangchain-ai/langchain	MCP server	149k	yesterday	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
reamorluto/rea	MCP server	435k	yesterday	MIT	A	—	Claude Code