AgentWatch for LangChain
dev.workers.agentwatch.agentwatch/agentwatch
Read-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.
client:LangChain
transport:streamable-http
tools:21
Install AgentWatch in LangChain
pip install langchain-mcp-adapters
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"agentwatch": {
"transport": "streamable_http",
"url": "https://agentwatch.agentwatch.workers.dev/mcp",
}
})
tools = await client.get_tools()
get_tools() returns the server's tools as LangChain tools, ready for an agent. LangChain docs
What LangChain can do once it is connected
- list_watched
- get_feed
- run_audit
- get_capabilities
- get_alerts
- get_pending_proposals
- get_fidelity
- get_leaderboard
- get_benchmark
- get_tca
- register_intent
- add_watch
- watch_demo_set
- refresh_watches
- get_agent_passport
- set_agent_passport
- list_recovery_owners
- set_recovery_owner
- remove_recovery_owner
- get_safe_defaults
- get_dashboard