langchain-agent-nexus
LangChain tools for the Agent Nexus registry — a machine-readable index of callable APIs, MCP servers and CLIs, with health signals and execution feedback.
Give a LangChain agent the ability to find a capability it does not have, read the exact call details, and report how the call went.
Install
pip install git+https://github.com/Strategiumfinancepartner/langchain-agent-nexus
Or install the built wheel directly:
pip install https://agentnexus.app/packages/langchain_agent_nexus-0.1.0-py3-none-any.whl
Use
from langchain_agent_nexus import AgentNexusToolkit
from langchain.chat_models import init_chat_model
from langgraph.prebuilt import create_react_agent
tools = AgentNexusToolkit().get_tools()
agent = create_react_agent(init_chat_model("gpt-4.1-mini"), tools)
agent.invoke({"messages": [("user", "Find a service that turns a photo into a printable 3D model, then explain how to call it.")]})
Individual tools:
from langchain_agent_nexus import AgentNexusDiscoverTool
tool = AgentNexusDiscoverTool()
print(tool.invoke({"need": "send transactional email", "limit": 3}))
Tools
| Tool | What it does |
|---|---|
agent_nexus_discover |
Ranks registry entries against a need described in plain words. Returns endpoint, auth mode, formats, pricing, reliability. |
agent_nexus_get_entry |
Full record for one entry by slug, including auth parameters and health history. |
agent_nexus_report |
Reports a real call outcome. Keeps reliability scores honest and raises the caller's daily quota. |
API key (optional)
Anonymous calls work out of the box at a lower daily quota. A free key raises it:
export AGENT_NEXUS_API_KEY="..." # https://agentnexus.app/keys
Or pass it directly: AgentNexusToolkit(api_key="...").
Links
- Registry: https://agentnexus.app
- Docs: https://agentnexus.app/docs
- MCP endpoint:
https://agentnexus.app/mcp - Agent card: https://agentnexus.app/.well-known/agent-card.json
MIT licensed.
Metadata
Release files for langchain-agent-nexus 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| langchain_agent_nexus-0.1.0.tar.gz | 6.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langchain_agent_nexus-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 13.0 kB
Release files / langchain_agent_nexus-0.1.0.tar.gz
| Download URL | langchain_agent_nexus-0.1.0.tar.gz |
|---|---|
| Size | 6.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2daec32ab528485f10538ea8bf6e945a1b97594a67278d0063098c0bf17293f8
|
|
BLAKE2b-256 checksum How to use checksums |
9a27d5e0d992bb92af188e284c5b77396aea0f1f321af441b1ec586a4ef9f1a2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.12
|
Release files / langchain_agent_nexus-0.1.0-py3-none-any.whl
| Download URL | langchain_agent_nexus-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
ed25184615ebf4ca3212ab2793e9d1f941f3abfee64e738979cad85a2064c2c9
|
|
BLAKE2b-256 checksum How to use checksums |
9ca4324b9672e5c3090f183e2152e55301e912f2713f053c41377aae7f78983d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.13.12
|