Scalar Agent SDK (Python)
Connect your AI agent to Scalar's OpenAPI MCP servers. Provides native integrations for the OpenAI Agents SDK and Anthropic Claude Agent SDK.
Installation
pip install scalar-agent
With provider extras:
# For Anthropic
pip install "scalar-agent[anthropic]"
# For OpenAI
pip install "scalar-agent[openai]"
# Both
pip install "scalar-agent[all]"
Setup
from scalar_agent import agent_scalar
scalar = agent_scalar(token="your-personal-token")
installation = scalar.installation("your-installation-id")
Providers
OpenAI Agents SDK
Returns params for MCPServerStreamableHttp from openai-agents. The agent runtime handles tool discovery and execution natively.
import asyncio
from scalar_agent import agent_scalar
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main() -> None:
scalar = agent_scalar(token="your-personal-token")
installation = scalar.installation("your-installation-id")
server = MCPServerStreamableHttp(**installation.create_openai_mcp())
await server.connect()
agent = Agent(name="api-agent", mcp_servers=[server])
result = await Runner.run(agent, "Which APIs are available that let me create a planet?")
print(result.final_output)
await server.cleanup()
asyncio.run(main())
Anthropic Claude Agent SDK
Returns an MCP server configuration for claude_agent_sdk.
import asyncio
from scalar_agent import agent_scalar
from claude_agent_sdk import query
from claude_agent_sdk.types import ClaudeAgentOptions, ResultMessage
scalar = agent_scalar(token="your-personal-token")
installation = scalar.installation("your-installation-id")
async def main() -> None:
async for message in query(
prompt="Which APIs are available that let me create a planet?",
options=ClaudeAgentOptions(
mcp_servers={"scalar": installation.create_anthropic_mcp()},
allowed_tools=["mcp__scalar__*"],
),
):
if isinstance(message, ResultMessage):
print(message.result)
asyncio.run(main())
Configuration
| Parameter | Type | Description |
|---|---|---|
token |
str |
Your Scalar Personal Token used to authenticate requests to your MCP |
base_url |
str |
Base URL of the Scalar MCP server. Defaults to the Scalar environment |
Metadata
Release files for scalar-agent 0.1.1
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 |
|---|---|---|---|---|
| scalar_agent-0.1.1.tar.gz | 3.8 kB | Without provenance | Details for scalar_agent-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| scalar_agent-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for scalar_agent-0.1.1-py3-none-any.whl |
Total release size: 8.0 kB
Release files / scalar_agent-0.1.1.tar.gz
| Download URL | scalar_agent-0.1.1.tar.gz |
|---|---|
| Size | 3.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cd273b526797bc1e7ee06682918440971e649eb7d1c25654cf2bacd10822487f
|
|
BLAKE2b-256 checksum How to use checksums |
922cf26fc60720a18f97ac14e243f3cd1913e2d605f3502a621b852fc46c81ae
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Release files / scalar_agent-0.1.1-py3-none-any.whl
| Download URL | scalar_agent-0.1.1-py3-none-any.whl |
|---|---|
| Size | 4.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4a5a2ce4d0cc9082a0e41a5a2a12e528bc0cb4c4e012b05eff0be847ba205d6d
|
|
BLAKE2b-256 checksum How to use checksums |
dcf8b4bcd34aa90e8fe19029b16d2ec83cc2f9b54c8e0978c26006733a1d673a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Security for scalar-agent 0.1.1
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.
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.