← Back to Skills Marketplace
agent mcp bridge
by
Ryne Schultz
· GitHub ↗
· v1.0.0
· MIT-0
86
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install agent-mcp-bridge
Description
Set up and use an MCP message broker for direct inter-agent communication between OpenClaw and other AI agents (e.g. hermes-agent, Claude Code, any MCP-capab...
README (SKILL.md)
Agent MCP Bridge
A lightweight FastMCP + SQLite message broker that lets two AI agents communicate directly via MCP tools. Both agents connect to the same server as MCP clients — symmetric, no platform-specific adapters.
Architecture
Agent A (OpenClaw) MCP Broker Agent B (hermes-agent / any)
send_message() ──────► FastAPI+SQLite ◄────────── poll_messages()
poll_messages() ◄────── localhost:8765 ──────────► send_message()
Quick Setup
1. Install and start the broker
cp -r \x3Cskill-dir>/scripts/server/ ~/.openclaw/agent-bridge-mcp/
cd ~/.openclaw/agent-bridge-mcp
./start.sh # creates venv, installs deps, starts on port 8765
2. Register as a launchd service (macOS auto-start)
cp \x3Cskill-dir>/references/launchd-plist.md ~/Library/LaunchAgents/ai.openclaw.agent-bridge.plist
# Edit the plist to set correct paths, then:
launchctl load ~/Library/LaunchAgents/ai.openclaw.agent-bridge.plist
3. Add to OpenClaw config
Add to ~/.openclaw/openclaw.json:
{
"mcp": {
"servers": {
"agent-bridge": {
"url": "http://127.0.0.1:8765/mcp",
"transport": "streamable-http"
}
}
}
}
4. Connect the other agent
Give the other agent the MCP URL: http://127.0.0.1:8765/mcp (streamable-http transport). They connect with their native MCP client support.
MCP Tools
| Tool | Parameters | Returns | Use when |
|---|---|---|---|
send_message |
from_agent, to, subject, body, reply_to? |
{message_id, timestamp} |
Sending a task or reply |
poll_messages |
agent_id, limit? |
list of message dicts | Checking your inbox |
mark_read |
message_id |
{status} |
After processing a message |
list_agents |
— | list of agent ids | Discovering who's active |
Message format
{
"id": "83223c09",
"from_agent": "hermes",
"to_agent": "isaac",
"subject": "Research request",
"body": "Please analyze...",
"timestamp": "2026-03-31T16:58:31Z",
"thread_id": "83223c09",
"reply_to": null,
"status": "pending"
}
Fallback: Filesystem bridge
If the MCP server is unavailable, use the filesystem bridge (zero infrastructure):
- See
references/filesystem-bridge.mdfor setup - Inbox/outbox dirs:
~/.openclaw/shared/{agent}-inbox/
Heartbeat integration (OpenClaw)
Add to HEARTBEAT.md to auto-process incoming messages:
Check ~/.openclaw/shared/isaac-inbox/ for new .json files.
If any exist: read, process, reply via hermes-inbox/, move to processed/.
Verification
Test the full loop:
# From Python
from agent_bridge import AgentBridge
bridge = AgentBridge("isaac")
bridge.send("hermes", "Handshake test", "Can you receive this?")
# Other agent polls and replies
msgs = bridge.receive()
Usage Guidance
This skill appears coherent with its purpose, but review and accept the security tradeoffs before installing: 1) There is no authentication or encryption — any local user/process with file or loopback access can read messages; keep the broker confined to a single trusted user or network namespace. 2) start.sh will pip-install packages from PyPI into a created venv — inspect requirements.txt and the code before running. 3) The filesystem bridge writes JSON files and the server creates messages.db in the server directory; ensure those directories have appropriate ownership and permissions. 4) If you enable auto-start (launchd), edit the plist paths carefully and avoid running as a privileged user. 5) Consider running the broker in an isolated environment (dedicated user, container, or VM) or adding authentication/transport restrictions if you plan to expose the service beyond localhost. 6) Note the small implementation detail: AgentBridge defaults to using the package directory as the shared directory — if you want inboxes under ~/.openclaw/shared, pass that path explicitly when instantiating AgentBridge.
Capability Analysis
Type: OpenClaw Skill
Name: agent-mcp-bridge
Version: 1.0.0
The bundle implements an inter-agent communication bridge using a local FastAPI/MCP server and a filesystem fallback. While the code appears functional and lacks clear malicious intent, it introduces high-risk capabilities including automated persistence via macOS launchd (`launchd-plist.md`) and instructions for the AI agent to autonomously poll, process, and respond to messages in the background (`SKILL.md`). These features, along with the setup of a local network service (`server.py`), fall under the category of risky capabilities that warrant a suspicious classification despite being aligned with the stated purpose.
Capability Assessment
Purpose & Capability
The name/description (MCP bridge for inter-agent messaging) aligns with the included server and filesystem-bridge code: a FastMCP + SQLite broker and a Python filesystem fallback. The only minor mismatch is that the AgentBridge default SHARED_DIR is Path(__file__).parent while the SKILL.md suggests using ~/.openclaw/shared; this is an implementation choice, not a functional contradiction.
Instruction Scope
SKILL.md instructs the user to copy the server files, run start.sh (which creates a venv and installs deps), optionally register a user launchd job, and add a local URL to OpenClaw config. The instructions do not ask the agent to read unrelated system files or external secrets. Note: message data is stored as plaintext (SQLite and JSON files) and the filesystem fallback writes to user-visible directories — there is no built-in authentication or encryption.
Install Mechanism
There is no formal install spec in the registry (instruction-only), but the included start.sh will create a virtualenv and pip-install requirements from PyPI (fastmcp, uvicorn, aiosqlite). This is a standard pattern but does entail network access to PyPI and execution of code you should audit before running.
Credentials
The skill declares no required environment variables, credentials, or config paths, and the code does not reference external secrets. The scope of access (local filesystem and a local TCP port) is appropriate for a local message broker.
Persistence & Privilege
always:false and default autonomous invocation are normal. The only persistence is user-level (virtualenv, SQLite DB, JSON files) and an optional per-user launchd plist. The skill does not attempt to modify other skills or system-wide privileged settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install agent-mcp-bridge - After installation, invoke the skill by name or use
/agent-mcp-bridge - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Inter-agent MCP message broker — lets two AI agents on the same machine communicate directly via MCP tools (FastMCP + SQLite). Includes filesystem fallback bridge and macOS launchd auto-start.
Metadata
Frequently Asked Questions
What is agent mcp bridge?
Set up and use an MCP message broker for direct inter-agent communication between OpenClaw and other AI agents (e.g. hermes-agent, Claude Code, any MCP-capab... It is an AI Agent Skill for Claude Code / OpenClaw, with 86 downloads so far.
How do I install agent mcp bridge?
Run "/install agent-mcp-bridge" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is agent mcp bridge free?
Yes, agent mcp bridge is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does agent mcp bridge support?
agent mcp bridge is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created agent mcp bridge?
It is built and maintained by Ryne Schultz (@ryno2390); the current version is v1.0.0.
More Skills