microsoft-agents-copilotstudio-client
A client library for Microsoft Agents
Decision gist · record as of 2026-08-14
Yes. The package is actively maintained, has no known vulnerabilities, uses a permissive MIT license, and provides a straightforward way to integrate Copilot Studio agents into Python applications. Install it if you need direct programmatic access to Copilot Studio agents outside traditional chat channels. The single runtime dependency and low install friction make adoption low-risk.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; authentication token and valid Copilot Studio environment/agent identifiers must be obtained separately (typically via MSAL or Entra ID).
- Active maintenance with recent release (15 days old), supports Python 3.10–3.14, and depends on a single runtime package (microsoft-agents-hosting-core) with low install friction.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use, modification, and distribution with minimal restrictions—suitable for most enterprise and open-source projects.
last release 2026-07-30 (15 days) · last repo commit 2026-08-13 · 1,036 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 465,035 downloads/mo, #6,511 on PyPI
Alternatives
Verify before relying
pip install microsoft-agents-copilotstudio-client
from microsoft_agents_copilotstudio_client import CopilotClient, ConnectionSettings
settings = ConnectionSettings(
environment_id="your-env-id",
agent_identifier="your-agent-id"
)
client = CopilotClient(settings, token)- Whether the package requires Azure/Microsoft 365 credentials or service subscriptions beyond what the documentation shows
- Performance characteristics and latency expectations for agent communication at scale
- Backward compatibility guarantees across minor versions
What it is and what it does
This package is a Python client for connecting to and interacting with AI agents built in Microsoft Copilot Studio. It bypasses traditional chat channels and provides a direct connection to agents, making it suitable for integrating conversational AI into custom applications, building specialized UIs, or enabling agent-to-agent communication flows. The library is part of the broader Microsoft 365 Agents SDK and handles authentication, connection configuration, and message exchange with Copilot Studio agents.
The client supports multiple connection modes: environment-based configuration using credentials and agent identifiers, or simplified DirectConnect URL mode for streamlined setup. It includes optional diagnostic logging for HTTP communication inspection and experimental endpoint support for pre-release features. The package requires Python 3.10 or later and depends on microsoft-agents-hosting-core for core hosting functionality.
Use it for
- Embed Copilot Studio agents into custom Python web applications or desktop tools without using Teams or web chat interfaces
- Build agent-to-agent communication flows where one Python service orchestrates interactions with multiple Copilot Studio agents
- Create specialized user interfaces that interact with Copilot Studio agents while maintaining full control over conversation state and presentation
- Integrate enterprise AI agents into backend services or data processing pipelines for automated decision-making or content generation
- Enable diagnostic inspection of agent communication for debugging, monitoring, or compliance logging
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is actively maintained, has no known vulnerabilities, uses a permissive MIT license, and provides a straightforward way to integrate Copilot Studio agents into Python applications. Install it if you need direct programmatic access to Copilot Studio agents outside traditional chat channels. The single runtime dependency and low install friction make adoption low-risk.
Install
microsoft-agents-copilotstudio-client on PyPI
Before you install
Active maintenance with recent release (15 days old), supports Python 3.10–3.14, and depends on a single runtime package (microsoft-agents-hosting-core) with low install friction.
Requires Python 3.10 or later; authentication token and valid Copilot Studio environment/agent identifiers must be obtained separately (typically via MSAL or Entra ID).
License in practice
MIT license permits commercial and private use, modification, and distribution with minimal restrictions—suitable for most enterprise and open-source projects.
Quickstart
pip install microsoft-agents-copilotstudio-client
from microsoft_agents_copilotstudio_client import CopilotClient, ConnectionSettings
settings = ConnectionSettings(
environment_id="your-env-id",
agent_identifier="your-agent-id"
)
client = CopilotClient(settings, token)Verify before relying
- Whether the package requires Azure/Microsoft 365 credentials or service subscriptions beyond what the documentation shows
- Performance characteristics and latency expectations for agent communication at scale
- Backward compatibility guarantees across minor versions
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 1 packagemicrosoft-agents-hosting-core |
| Maintenance | Actively maintained 15 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 465,035 / month, #6,511 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Operating System :: OS IndependentProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14 |
Evidence: microsoft_agents_copilotstudio_client-1.3.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “direct agent connection”
- microsoft-agents-copilotstudio-clientConnects Python applications to AI agents created in Microsoft…
- google-antigravityBuilds and runs AI agents powered by Google's Gemini, handling the…
- agent-framework-anthropicConnects Agent Framework applications to Anthropic's API, providing…
Give your agent the search over MCP, or paste the wish link into any chat.
More Application Frameworks packages
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Textual is a Python framework for building cross-platform user interfaces that run in the terminal or web browser using a modern, component-based API.
Install it if you're developing CLI tools, dashboards, or interactive terminal applications.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Build and connect to Model Context Protocol servers that expose tools, resources, and prompts to LLM applications over stdio, HTTP, or SSE transports.
Install it if you need to build or connect to servers.
Werkzeug is a WSGI utility library providing request/response objects, URL routing, an interactive debugger, HTTP utilities, and a development server for building web applications.
See also agent-framework-copilotstudio · copilotkit · microsoft-agents-activity · github-copilot-sdk · microsoft-agents-hosting-aiohttp · microsoft-agents-hosting-core · agent-framework-github-copilot · jupyter-ai-magics · microsoft-agents-hosting-teams · microsoft-teams-api