AgentTools Python Client
Self-healing reference SDK for Tools for Agents — M2M / A2A.
Install
pip install agenttools-client
# or from repo:
pip install -e ./agenttools_client
Requires Python 3.10+ and httpx.
Features
| Feature | Description |
|---|---|
| Auto auth | AGENTTOOLS_API_KEY or POST /v1/register {} |
| 422 self-heal | Matches /v1/tools/{tool}/examples by missing fields[] |
| 5xx retry | Honors Retry-After / retry_after_sec |
| A2A-first | client.a2a.advisor(), run_chain(), run_mission() |
| Typed helpers | extract(), ingest(), dry_run(), advisor() |
Quick start
import asyncio
from agenttools_client import AsyncAgentToolsClient
async def main():
async with AsyncAgentToolsClient() as client:
plan = await client.advisor("Extract markdown from a blog URL")
page = await client.extract("https://example.com")
chain = await client.run_chain("article_read", {"url": "https://example.com"})
# A2A orchestrators:
skill = await client.a2a.advisor("Summarize a PDF for RAG")
asyncio.run(main())
A2A (preferred for multi-agent orchestrators)
async with AsyncAgentToolsClient() as client:
skills = await client.a2a.list_skills()
result = await client.a2a.run_chain("pdf_summary", {"url": "https://example.com/x.pdf"})
mission = await client.a2a.run_mission("Research solid-state batteries")
Agent Card: GET https://api.toolsforagents.tools/.well-known/agent-card.json
Self-healing 422
Wrong body → SDK fetches examples, picks best match for missing fields, retries once:
await client.json("POST", "/v1/conflict/detect", json={}) # auto-fixes to documents[]
Environment
| Variable | Default |
|---|---|
AGENTTOOLS_API_KEY |
— |
AGENTTOOLS_API_URL |
https://api.toolsforagents.tools |
Publish (maintainers)
See PUBLISH.md.
License
MIT
Metadata
Release files for agenttools-client 0.2.0
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 |
|---|---|---|---|---|
| agenttools_client-0.2.0.tar.gz | 7.4 kB | Without provenance | Details for agenttools_client-0.2.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agenttools_client-0.2.0-py3-none-any.whl | Python 3 | none | any | Details for agenttools_client-0.2.0-py3-none-any.whl |
Total release size: 16.9 kB
Release files / agenttools_client-0.2.0.tar.gz
| Download URL | agenttools_client-0.2.0.tar.gz |
|---|---|
| Size | 7.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e1c7c8083df2ff3217a8f454fb8557cc67ff70ac01b1f40b7f621d6d61e29ff1
|
|
BLAKE2b-256 checksum How to use checksums |
e9cca672f0b5c699d7257840fe1e5eed58b187127bbd2081c60b9c3581ee5f68
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Release files / agenttools_client-0.2.0-py3-none-any.whl
| Download URL | agenttools_client-0.2.0-py3-none-any.whl |
|---|---|
| Size | 9.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
31a97c3e7f162b6eba56a3fd19c4526e09c5676883ab05acc2856b7e557a8c33
|
|
BLAKE2b-256 checksum How to use checksums |
e7ef3a4445b86a0733c7d60845310d028b2da9892919ff70f18bfe4f2b2d3aad
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.11
|
Security for agenttools-client 0.2.0
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.