← Back to Skills Marketplace
XMTP Agents
by
Saul Carlin
· GitHub ↗
· v0.0.1
320
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install xmtp-agents
Description
Connect a running agent (OpenClaw, Claude Code, LangChain, custom Python, any agent runtime) to XMTP messaging so people can DM it and get responses that use...
Usage Guidance
This skill appears to do what it says: set up a persistent bridge between XMTP and an agent. Before installing or running it, consider the following: (1) xmtp init writes private wallet/encryption keys to ~/.xmtp/.env — keep that file secure, or run the bridge in an isolated container/VM; (2) the instructions call for npm install -g @xmtp/cli (verify the package and pin versions); (3) the example uses the OpenClaw CLI — adapt the bridge to your agent runtime if you use something else; (4) owner inbox messages are given full agent capabilities (tools, memory, file access) — only give owner status to wallets/IDs you trust; (5) run rate-limiting, logging, and prompt-sanitization to reduce DOS and prompt-injection risk; and (6) test in a non-production environment first.
Capability Analysis
Type: OpenClaw Skill
Name: xmtp-agents
Version: 0.0.1
The skill facilitates connecting the agent to the XMTP decentralized messaging network, creating a persistent bridge that routes remote messages directly to the agent's execution environment (e.g., OpenClaw or Claude Code). While the SKILL.md includes a basic authorization check (OWNER_INBOX_ID) and a restrictive prompt for public users, the architecture inherently exposes the agent to remote prompt injection and unauthorized tool usage. The instructions also require the agent to handle sensitive cryptographic keys stored in `~/.xmtp/.env` and encourage setting up a full persistent listener even for simple one-off messaging requests, significantly increasing the host's attack surface.
Capability Assessment
Purpose & Capability
The skill is about connecting an agent to XMTP and its instructions use the XMTP CLI and an agent CLI (openclaw agent) to implement a bridge — this fits the described purpose. Minor inconsistency: the description promises support for many backends (Claude Code, LangChain, custom Python), but the provided bridge example and commands are OpenClaw-specific; users will need to adapt the sample if they use a different runtime.
Instruction Scope
The SKILL.md instructs installing @xmtp/cli, running xmtp init which generates ~/.xmtp/.env containing a wallet/encryption key, and running a continuously streaming bridge that routes messages into your agent and back out. These steps are expected for an XMTP bridge but have important implications: private keys are written to local disk, the bridge is persistent (long-running), and owner messages are granted 'full agent capabilities' (tools, memory, file access). The skill does warn about DOS and prompt-injection, but the instructions nonetheless enable a process that could expose sensitive resources if misconfigured.
Install Mechanism
There is no platform install spec in the skill bundle, but the runtime instructions require running npm install -g @xmtp/cli (via the public npm registry), Node 22+, and jq. Installing the XMTP CLI from npm is a reasonable choice for this purpose but carries normal npm risks (trusting the package, supply-chain issues, global install).
Credentials
The registry metadata declares no required environment variables, which is consistent with the bundle, but the instructions rely on a generated local secrets file (~/.xmtp/.env) containing wallet and encryption keys and on an OWNER_INBOX_ID runtime variable for owner filtering. Granting the 'owner' inbox full agent privileges is functionally necessary for the described owner-vs-public behavior, but it is a high-privilege configuration — the skill does not request additional unrelated credentials, so scope is proportional but potentially sensitive.
Persistence & Privilege
The skill does not request always:true or any special platform privileges. It simply provides instructions to run a persistent bridge process; that is expected for the purpose and does not modify other skills or global agent settings.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install xmtp-agents - After installation, invoke the skill by name or use
/xmtp-agents - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.0.1
- Initial release: connect any agent runtime (OpenClaw, Claude Code, LangChain, custom Python, etc.) to XMTP for two-way messaging.
- Provides a full bridge pattern: CLI setup, identity registration, streaming incoming messages, and routing all conversations through your agent backend.
- Distinguishes between owner and public users, applying customizable prompts and restricting capabilities for public sessions.
- Includes ready-to-use Bash bridge script examples; supports swappable agent backends.
- Owner identity and inbox ID setup are required before running the bridge.
- Designed for continuous, session-based conversations — not individual message sends.
Metadata
Frequently Asked Questions
What is XMTP Agents?
Connect a running agent (OpenClaw, Claude Code, LangChain, custom Python, any agent runtime) to XMTP messaging so people can DM it and get responses that use... It is an AI Agent Skill for Claude Code / OpenClaw, with 320 downloads so far.
How do I install XMTP Agents?
Run "/install xmtp-agents" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is XMTP Agents free?
Yes, XMTP Agents is completely free (open-source). You can download, install and use it at no cost.
Which platforms does XMTP Agents support?
XMTP Agents is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created XMTP Agents?
It is built and maintained by Saul Carlin (@saulmc); the current version is v0.0.1.
More Skills