What is agent-bridge?

A configured MCP server, a program that gives an agent access to additional tools, called agent-bridge. The input only describes how it starts and the permissions and time limits assigned to it.

Use it when the agent needs to connect to the configured agent-bridge server; its concrete jobs cannot be determined from this description alone.

It provides a defined bridge for agent tools, but the input does not say what specific tasks or tools the server supports.

agent-bridge — MCP server by southlab-ai/Claude-Plugin-Marketplace

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add southlab-ai/Claude-Plugin-Marketplace

Claude Code

/plugin install agent-bridge

Installing this writes the configuration, not the program: `/bin/sh` has to be on your PATH already, or the server will not start.

Made for: Claude Code.

Or install agent-bridge, the plugin that ships this one along with the rest of its 1 skill, 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/southlab-ai/claude-plugin-marketplace/agent-bridge-agent-bridge/github.svg)](https://agentmods.dev/mcp/southlab-ai/claude-plugin-marketplace/agent-bridge-agent-bridge)

Your own site

<a href="https://agentmods.dev/mcp/southlab-ai/claude-plugin-marketplace/agent-bridge-agent-bridge"><img src="https://agentmods.dev/badge/mcp/southlab-ai/claude-plugin-marketplace/agent-bridge-agent-bridge/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/southlab-ai/claude-plugin-marketplace/agent-bridge-agent-bridge"><img src="https://agentmods.dev/badge/mcp/southlab-ai/claude-plugin-marketplace/agent-bridge-agent-bridge.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

agent-bridge 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 1mo 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.

plugins/agent-bridge/.mcp.json · 13 lines

What it actually says

{
  "agent-bridge": {
    "command": "/bin/sh",
    "args": [
      "-c",
      "ROOT=\"\"; for CANDIDATE in \"$PLUGIN_ROOT\" \"$CLAUDE_PLUGIN_ROOT\" \"$PWD\" \"$HOME\"/.codex/plugins/cache/*/agent-bridge/* \"$HOME\"/.claude/plugins/cache/*/agent-bridge/*; do if [ -n \"$CANDIDATE\" ] && [ -f \"$CANDIDATE/agent_bridge/server.py\" ] && [ -f \"$CANDIDATE/pyproject.toml\" ]; then ROOT=\"$CANDIDATE\"; break; fi; done; if [ -z \"$ROOT\" ]; then echo 'agent-bridge: plugin root not found' >&2; exit 1; fi; exec uv run --directory \"$ROOT\" python -m agent_bridge.server"
    ],
    "startup_timeout_sec": 30,
    "tool_timeout_sec": 7300,
    "required": true,
    "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.

1mo ago First seen · 13 lines scan A 6edf224b46b8

Subscribe to this mod's changes

agent-bridge is an MCP server published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (3 stars, last pushed 2mo 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 2026-08-31.

Building agents Claude Code Multi-Agent ai-agents computer-vision marketplace mcp

offload-mcp

MCP server that offloads routine AI coding tasks to free LLM APIs. Runs locally from the offload-mcp npm package.

DelinSirkov/offload-mcp · not measured

bus-mcp

Ergonomic MCP server fronting the self-hosted AlphaHive coordination-bus HTTP API (backend/coordinationbus.py) -- post/read/claim/release/heartbeat/status as MCP tools instead of hand-rolled curl. Fast-follow to the coordination-bus arc, github-mcp-shaped (MCP over an HTTP API). Runs locally from the bus-mcp Python…

jaimenbell/bus-mcp · not measured

agent-bridge

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

offload-mcp

bus-mcp

mcp-server

docs-langchain

component-explorer

reference-langchain