Live data for LangChain agents.
Your LangChain agent reasons well but its knowledge is frozen at training time. Connect it to one keyless MCP URL and it gets 87 live tools - each datapoint stamped with its source, observed-at time, and an Ed25519 signature - so the agent can fetch and cite current facts at runtime.
The call
A keyless REST call any LangChain tool or chain can wrap directly - POST a batch of tools to v1/batch and get back signed, provenance-stamped results:
curl -s -X POST https://dynamicfeed.ai/v1/batch \
-H 'Content-Type: application/json' \
-d '{
"calls": [
{"tool": "reality_check", "args": {"claim": "the latest stable Python is 3.12"}},
{"tool": "weather_forecast", "args": {"city": "Sydney"}},
{"tool": "check_vulnerability", "args": {"package": "lodash", "version": "4.17.10", "ecosystem": "npm"}}
]
}'Sample response
# pip install langchain-mcp-adapters langgraph
from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({
"dynamic-feed": {
"url": "https://dynamicfeed.ai/mcp",
"transport": "streamable_http"
}
})
tools = await client.get_tools() # 87 keyless live-data tools
# pass `tools` to create_react_agent(model, tools)Why live data
LangChain agents call tools at runtime, which is exactly when you want fresh facts instead of training-cutoff guesses. Dynamic Feed exposes its 87 tools over a keyless Streamable HTTP MCP endpoint, so langchain-mcp-adapters can load the whole catalog as LangChain tools with one URL and no key - or you can wrap the keyless REST batch endpoint as a custom tool. Every result carries its provenance (source, observed-at, freshness) and an Ed25519 signature. Be precise about what that signature means: it is proof-of-existence and tamper-evidence - it proves Dynamic Feed reported value X at time T and that the bytes were not altered in transit. It is not a claim that X is true, accurate, or safe to act on. Your agent still owns the judgment; Dynamic Feed gives it citeable, verifiable inputs to reason over.
Use it for
- Load all 87 tools into a LangGraph ReAct agent with one keyless MCP URL
- Ground an agent's answer in a citeable fact instead of a training-cutoff guess
- Add a reality_check step that flags stale claims before the agent commits to them
- Give a DevOps agent live CVE and software-version lookups during a build
FAQ
Do I need an API key?
No. The MCP endpoint and the REST batch endpoint are both keyless and free for fair use. Point langchain-mcp-adapters at the URL and you are connected.
How do I load the tools into LangChain?
Use langchain-mcp-adapters MultiServerMCPClient with transport streamable_http pointed at https://dynamicfeed.ai/mcp, then call get_tools(). It returns all 87 tools as standard LangChain tools you can pass to any agent.
What does the Ed25519 signature actually prove?
It is proof-of-existence and tamper-evidence: it proves Dynamic Feed reported a given value at a given time and that the response was not altered. It does not assert the value is true, accurate, or safe - your agent still decides how to use it.