[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
[project]
name = "mcp-eval-server"
version = "0.1.0"
description = "MCP server for comprehensive agent and prompt evaluation using LLM-as-a-judge techniques"
readme = "README.md"
license = { text = "Apache-2.0" }
authors = [
{ name = "Mihai Criveti", email = "redacted@ibm.com" }
]
classifiers = [
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
"Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.11",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Topic :: Software Development :: Libraries :: Python Modules",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
]
requires-python = ">=3.11"
dependencies = [
"aiofiles>=25.1.0",
"aiohttp>=3.13.3",
"cachetools>=7.0.1",
"diskcache>=5.6.3",
"httpx>=0.28.1",
"jinja2>=3.1.6",
"mcp>=1.26.0",
"numpy>=2.4.2",
"openai>=2.20.0",
"orjson>=3.11.7",
"psutil>=7.2.2",
"pydantic>=2.12.5",
"pydantic-settings>=2.12.0",
"python-dotenv>=1.2.1",
"PyYAML>=6.0.3",
"scikit-learn>=1.8.0",
"scipy>=1.17.0",
"tenacity>=9.1.4",
"textstat>=0.7.12",
]
[project.optional-dependencies]
dev = [
"black>=26.1.0",
"flake8>=7.3.0",
"isort>=7.0.0",
"mypy>=1.19.1",
"pre-commit>=4.5.1",
"pytest>=9.0.2",
"pytest-asyncio>=1.3.0",
"pytest-cov>=7.0.0",
"pytest-mock>=3.15.1",
]
docs = [
"mkdocs>=1.6.1",
"mkdocs-material>=9.7.1",
"mkdocstrings[python]>=1.0.3",
]
benchmark = [
"locust>=2.43.3",
"memory-profiler>=0.61.0",
]
anthropic = [
"anthropic>=0.79.0",
]
aws = [
"boto3>=1.42.47",
"botocore>=1.42.47",
]
ollama = []
gemini = [
"google-generativeai>=0.8.6",
]
watsonx = [
"ibm-watsonx-ai>=1.5.2",
]
rest = [
"fastapi>=0.128.8",
"python-multipart>=0.0.22",
"uvicorn[standard]>=0.40.0",
]
all = [
"anthropic>=0.79.0",
"boto3>=1.42.47",
"botocore>=1.42.47",
"fastapi>=0.128.8",
"google-generativeai>=0.8.6",
"ibm-watsonx-ai>=1.5.2",
"python-multipart>=0.0.22",
"uvicorn[standard]>=0.40.0",
]
[project.urls]
Homepage = "https://github.com/contextforge/mcp-context-forge"
Documentation = "https://contextforge.github.io/mcp-eval-server"
Repository = "https://github.com/contextforge/mcp-context-forge"
Issues = "https://github.com/contextforge/mcp-context-forge/issues"
[project.scripts]
mcp-eval-server = "mcp_eval_server.server:main"
mcp-eval-rest = "mcp_eval_server.rest_server:main"
[tool.hatch.build.targets.wheel]
packages = ["mcp_eval_server"]
[tool.black]
line-length = 100
target-version = ['py39']
include = '\.pyi?$'
extend-exclude = '''
/(
# directories
\.eggs
| \.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| build
| dist
)/
'''
[tool.isort]
profile = "black"
line_length = 100
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true
[tool.mypy]
python_version = "3.9"
warn_return_any = true
warn_unused_configs = true
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
disallow_untyped_decorators = true
no_implicit_optional = true
warn_redundant_casts = true
warn_unused_ignores = true
warn_no_return = true
warn_unreachable = true
strict_equality = true
[[tool.mypy.overrides]]
module = [
"textstat.*",
"cachetools.*",
"diskcache.*",
]
ignore_missing_imports = true
[tool.pytest.ini_options]
minversion = "7.0"
addopts = "-ra -q --cov=mcp_eval_server --cov-report=term-missing --cov-report=html"
testpaths = ["tests"]
asyncio_mode = "auto"
[tool.coverage.run]
source = ["mcp_eval_server"]
omit = [
"*/tests/*",
"*/test_*",
"*/__init__.py",
]
[tool.coverage.report]
exclude_lines = [
"pragma: no cover",
"def __repr__",
"if self.debug:",
"if settings.DEBUG",
"raise AssertionError",
"raise NotImplementedError",
"if 0:",
"if __name__ == .__main__.:",
"class .*\\bProtocol\\):",
"@(abc\\.)?abstractmethod",
]
