Connect to HiveAgent — 586 MCP tools across 22 industry verticals. The Amazon for AI agents.
Project description
hiveagent-mcp
Connect to HiveAgent — 586 MCP tools across 22 industry verticals.
The Amazon for AI agents. One pip install gives your agent access to insurance claims, legal document processing, healthcare billing, fraud detection, real estate, supply chain, travel booking, and 15 more verticals — all via the Model Context Protocol.
pip install hiveagent-mcp
Quickstart
Plain Python
from hiveagent import HiveAgent
client = HiveAgent()
result = client.call_tool("insurance_claim_intake", {
"policy_number": "POL-12345",
"description": "Water damage to basement"
})
print(result)
LangChain (3 lines)
from hiveagent.langchain import HiveAgentToolkit
toolkit = HiveAgentToolkit()
agent = create_react_agent(llm, toolkit.get_tools())
Install with LangChain support: pip install "hiveagent-mcp[langchain]"
CrewAI (2 lines)
from hiveagent.crewai import HiveAgentTools
tools = HiveAgentTools().get_tools()
Install with CrewAI support: pip install "hiveagent-mcp[crewai]"
Vertical Filtering
Limit tools to specific industry verticals:
# LangChain — insurance and fraud detection only
from hiveagent.langchain import HiveAgentToolkit
toolkit = HiveAgentToolkit(verticals=["insurance", "fraud_detection"])
tools = toolkit.get_tools()
# CrewAI — legal vertical only
from hiveagent.crewai import HiveAgentTools
legal_tools = HiveAgentTools(verticals=["legal"]).get_tools()
# Split by vertical for specialist agents
from hiveagent.crewai import HiveAgentTools
tool_sets = HiveAgentTools().split_by_vertical()
claims_agent = Agent(tools=tool_sets["insurance"])
legal_agent = Agent(tools=tool_sets["legal"])
Discovery
Find the right tools for your use case using semantic search:
from hiveagent import discover
results = discover("I need to validate supplier invoices before payment")
for tool in results["tools"]:
print(tool["name"], "—", tool["description"])
Workflow Suggestions
Get a step-by-step workflow for complex multi-tool tasks:
from hiveagent import HiveAgent
client = HiveAgent()
workflow = client.suggest_workflow(
"Process an end-to-end insurance claim from intake to settlement"
)
print(f"Workflow: {workflow['workflow_name']}")
for step in workflow["steps"]:
print(f" {step['order']}. {step['tool']} — {step['description']}")
List Available Tools
from hiveagent import HiveAgent
from hiveagent.tools import get_tools, get_tool, list_verticals
# All 22 verticals
print(list_verticals())
# All tools in a vertical (no API call required)
insurance_tools = get_tools("insurance")
# Specific tool schema
tool = get_tool("fraud_screen_transaction")
print(tool["description"])
# Live tool list from the API
client = HiveAgent()
all_tools = client.list_tools()
print(f"{len(all_tools)} tools available")
Available Verticals
| Vertical | Example Tools |
|---|---|
insurance |
claim intake, damage assessment, policy comparison |
legal |
case intake, demand letters, deadline tracking |
healthcare |
prior auth, clinical notes, billing codes |
construction |
zoning lookup, permit status, material takeoff |
trades |
permit lookup, job estimates, invoice generation |
smb |
transaction categorisation, tax prep, contracts |
commerce |
product verification, merchant trust, order tracking |
fraud_detection |
transaction screening, anomaly detection, identity check |
real_estate |
property search, comps, mortgage calculation |
supply_chain |
demand forecasting, inventory optimisation, shipment tracking |
travel |
flight search, hotel booking, itinerary building |
sales_crm |
lead enrichment, outreach generation, pipeline forecast |
invoice_ap |
invoice extraction, three-way match, duplicate detection |
hr_recruiting |
resume screening, candidate matching, compensation benchmarking |
dynamic_pricing |
competitor monitoring, optimal pricing, promo generation |
procurement |
supplier discovery, RFQ, bid evaluation |
know_your_agent |
agent verification, delegation checks, spend limits |
trade_customs |
HS classification, sanctions screening, duty calculation |
defi |
token swaps, lending, yield farming |
agriculture |
yield forecasting, commodity alerts |
agent_recovery |
health checks, circuit breakers, hallucination detection |
advertising |
ad targeting, campaign analytics |
Full Documentation
Requirements
- Python 3.9+
httpx >= 0.24.0- LangChain integration:
langchain >= 0.2.0(optional) - CrewAI integration:
crewai >= 0.1.0(optional)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hiveagent_mcp-1.0.0.tar.gz.
File metadata
- Download URL: hiveagent_mcp-1.0.0.tar.gz
- Upload date:
- Size: 16.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5b265b39a7e36231d93cf7560f5f8406cdeb6c5b7097536ecb76623812269878
|
|
| MD5 |
c8cc1594f26af4f9a39900ec3a7dd60f
|
|
| BLAKE2b-256 |
6b149c1c9431e759edd02deb096e84f8d21b5dcee1ec30cedf16917a61bbb1da
|
File details
Details for the file hiveagent_mcp-1.0.0-py3-none-any.whl.
File metadata
- Download URL: hiveagent_mcp-1.0.0-py3-none-any.whl
- Upload date:
- Size: 16.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.8
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ce8fa1345100b03b939db3f7f7992c1033f0413afaa57d0328940cfff6db3ee1
|
|
| MD5 |
b96ae680297597af38c521bcb1fc1067
|
|
| BLAKE2b-256 |
2cd6c70a6dec095ef8ab2406ef40008f2acee870488726634835dd89b3189751
|