Verifly Tool
Verifly is an agent-native email verification API. It tells you whether an email address is real and safe to send to — checking deliverability (syntax, domain, MX, SMTP) and risk flags (disposable, role, catch-all, free provider) — and returns a verdict with a send / do-not-send recommendation.
This tool lets a LlamaIndex agent verify an address before adding it to a list, confirming a signup, or firing off a message.
Installation
pip install llama-index-tools-verifly
Getting an API key
Create an account and grab a key at verifly.email. Verifly is built for autonomous workflows, so an agent can also self-onboard for a key (with free starter credits) and no human in the loop via the autonomous registration endpoint. Set it as an environment variable:
export VERIFLY_API_KEY="vf_..."
Usage
from llama_index.tools.verifly import VeriflyToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
verifly_tool = VeriflyToolSpec(api_key="vf_...") # or rely on VERIFLY_API_KEY
agent = FunctionAgent(
tools=verifly_tool.to_tool_list(),
llm=OpenAI(model="gpt-4o"),
)
await agent.run("Is lead@example.com a deliverable email address?")
Call it directly:
from llama_index.tools.verifly import VeriflyToolSpec
verifly_tool = VeriflyToolSpec() # reads VERIFLY_API_KEY from the environment
doc = verifly_tool.verify_email("lead@example.com")
print(doc.text) # e.g. "lead@example.com: deliverable - recommendation: send"
print(doc.metadata) # full structured result: is_valid, result, reason, details, ...
Available Functions
verify_email: Verify a single email address. Returns a Document whose text
is a short human-readable verdict and whose metadata holds the full
structured Verifly result (is_valid, result, reason, details,
recommendation, credits).
This loader is designed to be used as a Tool in an Agent.
Metadata
Release files for llama-index-tools-verifly 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 | Provenance | Actions |
|---|---|---|---|---|
| llama_index_tools_verifly-0.1.0.tar.gz | 4.1 kB | Without provenance | Details for llama_index_tools_verifly-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llama_index_tools_verifly-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for llama_index_tools_verifly-0.1.0-py3-none-any.whl |
Total release size: 8.8 kB
Release files / llama_index_tools_verifly-0.1.0.tar.gz
| Download URL | llama_index_tools_verifly-0.1.0.tar.gz |
|---|---|
| Size | 4.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
abfa9c83cffadc0b773fb7a3bff0170ff98b2062f14cae47772def1ff13adabd
|
|
BLAKE2b-256 checksum How to use checksums |
da1729ec38588a48970b16deaae2b0993d052a329d141a95298fc6ad389caaa2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Release files / llama_index_tools_verifly-0.1.0-py3-none-any.whl
| Download URL | llama_index_tools_verifly-0.1.0-py3-none-any.whl |
|---|---|
| Size | 4.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
63fcbb2c0ff473aa14f61ed12b708f5584cd0574ff1409c0d1456f433e0721b0
|
|
BLAKE2b-256 checksum How to use checksums |
57339dbc1a7af30aaa627493abf7dd3feb67b5673a6308723f235f39525c2337
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.12
|
Security for llama-index-tools-verifly 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.