mcp-test-harness-openai
OpenAI function calling testing helpers for MCP Test Harness.
Author: Vaquar Khan -- https://github.com/vaquarkhan
Install
pip install mcp-test-harness-openai
This automatically installs mcp-test-harness as a dependency.
Usage
from mcp_test_harness_openai import assert_openai_tool, mcp_tools_to_openai_functions, create_openai_test_config
async def test_tool(mcp_server):
await assert_openai_tool(mcp_server, "my_tool", {}, expected_text="ok")
def test_schema_bridge(mcp_tools):
# mcp_tools from list_tools — convert for OpenAI SDKs
return mcp_tools_to_openai_functions(mcp_tools)
cfg = create_openai_test_config("python server.py", timeout=45)
Helpers
- Tool call assertion with optional text check
- MCP tool → OpenAI schema converter
mcp-test.yaml-shaped config builder
License
MIT. See LICENSE.
1 maintainer
Metadata
1 maintainer
Release files for mcp-test-harness-openai 5.3.1
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 |
|---|---|---|---|---|
| mcp_test_harness_openai-5.3.1.tar.gz | 3.5 kB | With provenance | Details for mcp_test_harness_openai-5.3.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| mcp_test_harness_openai-5.3.1-py3-none-any.whl | Python 3 | none | any | Details for mcp_test_harness_openai-5.3.1-py3-none-any.whl |
Total release size: 8.2 kB
Release files / mcp_test_harness_openai-5.3.1.tar.gz
| Download URL | mcp_test_harness_openai-5.3.1.tar.gz |
|---|---|
| Size | 3.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a24fc6996ca292cbc3d7cdf18172dea71a60182e257a2b53e232f9a558fc0ec7
|
|
BLAKE2b-256 checksum How to use checksums |
25025eb73d0f89400299a9edd5c31a1cd004dd98fa0b960ef7f37a2951d64389
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logRelease files / mcp_test_harness_openai-5.3.1-py3-none-any.whl
| Download URL | mcp_test_harness_openai-5.3.1-py3-none-any.whl |
|---|---|
| Size | 4.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
83e08fb778dafca476231c46af09213a69968097a315925e0d171a58c0bbd2aa
|
|
BLAKE2b-256 checksum How to use checksums |
205db31ed4853b94912c9c90d1f0dcd69bcb969408e8126b23cdeb1c531f0a5e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logSecurity for mcp-test-harness-openai 5.3.1
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for mcp_test_harness_openai-5.3.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 24, 2026.
Transparency logA 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.
