Home›Agents›Microsoft Agent Framework

AgentenCode evidence profileAutomation

✓ Editorially reviewedChecked: October 1, 2026

Agent profile · Automation

Microsoft Agent Framework

Microsoft Agent Framework is classified by AgentenCode as a agent framework from Microsoft. It belongs to the Automation category. This English profile does not maintain a separate factual record: it renders the same underlying evidence, trust and history data as the German profile.

MicrosoftAutomationDevelopers & businesses

View profile ↓Check sources ↓

AGENTENCODE RESEARCH

Multi-Agent Intelligence: Research & Architecture

How collaborating AI agents work: orchestration, delegation, external benchmarks and auditable evidence.

Explore the research guide → · Orchestration patterns · Studies & benchmarks · Evidence methodology

ECOSYSTEM ASSOCIATION

This agent profile links to a curated provider view. Security controls are not inherited across products.

Microsoft · Copilot & Foundry ↗

Automationeditorial classification

Microsoftprovider

9 primary sourcessource status

October 1, 2026last verification

AgentenTrust 2.0 · EU & governance evidence

Trust, privacy and control evidence for Microsoft Agent Framework

Direct answer: AgentenCode currently documents 0 of 36 normalized trust controls for this profile. Missing fields remain Unknown and are never automatically interpreted as “no”.

EU AI ActEvidence context only. AgentenCode does not infer legal applicability or compliance from individual product controls.

GDPRPrivacy and security signals are documented field by field. Data residency alone is not a compliance or transfer assessment.

Privacy contextPrivacy & data0 of 8 documentedResidency, training, retention, DPA, subprocessors and processing scope.

Security contextSecurity & access0 of 10 documentedEncryption, SSO, SCIM, RBAC, roles and credential handling.

Human controlHuman control0 of 10 documentedApproval, oversight, permissions and stop or rollback controls.

TraceabilityAudit & traceability0 of 8 documentedAudit logs, APIs, SIEM, observability, tracing and activity history.

Important: these numbers show evidence coverage, not a product rating. 0 of 10 means that no field-level public evidence is stored for those ten controls in the current dataset. It does not mean the product lacks those capabilities.

Field-level evidence

Documented controls and values from primary sources.

Documented yesDocumented valueUnknown remains unknown

High confidence

API · Openai Compatible

Yes — documented

OpenAI-compatible serving endpoints are documented.

Scope: self_hosted_and_managed · verified 2026-10-01 · Primary source ↗

High confidence

API · Rest

Yes — documented

Agent Framework can expose agents through documented HTTP/REST-style API endpoints.

Scope: agent_framework_openai_compatible_http_endpoints · verified 2026-10-01 · Primary source ↗

High confidence

API · Webhooks

Yes — documented

The Durable Extension supports webhook-driven Agent Framework orchestration.

Scope: agent_framework_durable_extension_event_driven_hosts · verified 2026-10-01 · Primary source ↗

High confidence

Hosting · Managed Provider

Microsoft Foundry

Microsoft Foundry is a documented managed host.

Scope: framework · verified 2026-10-01 · Primary source ↗

High confidence

Hosting · Managed

Yes — documented

Managed hosting through Microsoft Foundry is documented.

Scope: framework · verified 2026-10-01 · Primary source ↗

High confidence

Hosting · Private Network

Yes — documented

Agent Framework deployments on the supported Azure Functions host can be placed behind private endpoints and VNet integration.

Scope: agent_framework_on_azure_functions_supported_host · verified 2026-10-01 · Primary source ↗

High confidence

Hosting · Self Hosted

Yes — documented

Self-hosting is supported.

Scope: framework · verified 2026-10-01 · Primary source ↗

High confidence

Protocols · A2A · Client

Yes — documented

Microsoft Agent Framework can invoke remote agents through the A2A protocol.

Scope: microsoft_agent_framework_remote_a2a_agent_service · verified 2026-10-01 · Primary source ↗

High confidence

Protocols · A2A · Server

Yes — documented

Microsoft Agent Framework agents can be exposed as A2A servers.

Scope: microsoft_agent_framework_a2a_hosting · verified 2026-10-01 · Primary source ↗

High confidence

Protocols · A2A · Supported

Yes — documented

A2A integration/hosting is documented.

Scope: framework · verified 2026-10-01 · Primary source ↗

High confidence

Protocols · Mcp · Auth · Api Key

Yes — documented

API-key authentication for MCP connections is documented.

Scope: framework · verified 2026-10-01 · Primary source ↗

High confidence

Protocols · Mcp · Client

Yes — documented

Agent Framework includes MCP client integration.

Scope: framework · verified 2026-10-01 · Primary source ↗

High confidence

Protocols · Mcp · Server

Yes — documented

Agents can be exposed as MCP servers.

Scope: framework · verified 2026-10-01 · Primary source ↗

Evidence-backed overview

What is Microsoft Agent Framework?

Product-specific evidence for Microsoft Agent Framework

This profile links 9 unique primary sources across the product profile, field-level evidence, trust controls and documented relations. The points below describe this product’s stored evidence rather than generic characteristics of Automatisierung.

protocols · a2a · client

Yes · Scope: microsoft_agent_framework_remote_a2a_agent_service · verified 2026-10-01.

Primary source ↗

protocols · a2a · server

Yes · Scope: microsoft_agent_framework_a2a_hosting · verified 2026-10-01.

Primary source ↗

protocols · a2a · supported

Yes · Scope: framework · verified 2026-10-01.

Primary source ↗

protocols · mcp · auth · api_key

Yes · Scope: framework · verified 2026-10-01.

Primary source ↗

protocols · mcp · client

Yes · Scope: framework · verified 2026-10-01.

Primary source ↗

protocols · mcp · server

Yes · Scope: framework · verified 2026-10-01.

Primary source ↗

AgentenCode treats this page as a reference profile rather than a ranking. Product facts are separated from editorial classification, and the profile is tied to a specific verification date. If a capability is not backed by sufficiently precise public evidence, it remains unknown instead of being inferred from marketing language or from similar products.

1primary source

13field-level evidence claims

0documented trust controls

2history events

How to read the evidence

The field-level evidence layer records a value, a scope, a confidence level, a verification date and one or more primary sources. Scope matters: an enterprise-only security feature must not be generalized to every plan or deployment surface. The same rule applies to hosting, privacy, audit and protocol claims.

AgentenCode also keeps Unknown distinct from false. A missing claim means the public dataset does not currently contain sufficiently precise evidence for that field. A negative value is used only when a reliable primary source explicitly documents a restriction or non-availability.

Decision context

Provider and category

Microsoft Agent Framework is documented under Automation and is associated with Microsoft. Category labels help navigation but do not replace product-specific evidence.

Verification status

The public profile is marked editorially reviewed and was last checked on October 1, 2026.

Trust coverage

0 of 36 normalized trust controls currently have field-level public evidence. The remaining controls are not treated as negative findings.

Source-first use

For procurement, security or legal decisions, use the linked primary sources and verify the plan, region and configuration that apply to your organization.

Capabilities, strengths and deployment checks for Microsoft Agent Framework

Microsoft Agent Framework is classified as Agenten-Framework from Microsoft. The profile’s editorial layer is derived from the stored use cases, strengths and checks below; claims about security, privacy or governance remain separate and require field-level evidence.

Agenten entwickeln

This use case is part of the stored profile for Microsoft Agent Framework. The related strength is “Microsoft-Ökosystem”. In a production evaluation, the practical boundary to verify is: Versionen wegen schneller Framework-Entwicklung fixieren.

Multi-Agent-Orchestrierung

This use case is part of the stored profile for Microsoft Agent Framework. The related strength is “Agenten- und Workflow-Abstraktionen”. In a production evaluation, the practical boundary to verify is: Identitäts- und Tool-Rechte prüfen.

Enterprise-Tools anbinden

This use case is part of the stored profile for Microsoft Agent Framework. The related strength is “Tool- und Middleware-Unterstützung”. In a production evaluation, the practical boundary to verify is: Eigene Evaluierungs- und Observability-Schicht vorsehen.

Agentische Anwendungen

This use case is part of the stored profile for Microsoft Agent Framework. The related strength is “Für Enterprise-Entwicklung ausgelegt”. In a production evaluation, the practical boundary to verify is: Versionen wegen schneller Framework-Entwicklung fixieren.

What to verify before adoption

Versionen wegen schneller Framework-Entwicklung fixieren. Treat undocumented controls as Unknown and verify the exact plan, region and deployment scope.
Identitäts- und Tool-Rechte prüfen. Treat undocumented controls as Unknown and verify the exact plan, region and deployment scope.
Eigene Evaluierungs- und Observability-Schicht vorsehen. Treat undocumented controls as Unknown and verify the exact plan, region and deployment scope.

Editorial boundary: The use-case and strength descriptions are product-specific editorial context based on the stored profile. Trust, privacy and governance statements are only presented as facts when field-level primary-source evidence exists.

Verified history

The public history layer records only confirmed profile changes and verification events. Monitoring signals are not published as product facts until they have been reviewed.

October 1, 2026 · Source Maintenance
September 30, 2026 · New profile

Official sources

This profile links 9 unique primary sources across the product profile, field-level evidence, trust layer and documented relations. Provider documentation remains authoritative when the product changes between verification cycles.

Frequently asked questions

What is Microsoft Agent Framework?

Microsoft Agent Framework is listed by AgentenCode as an automation agent or agentic product from Microsoft.

How much trust evidence is documented for Microsoft Agent Framework?

The current trust layer documents 0 of 36 normalized controls. Missing controls remain unknown rather than being treated as false.

When was this profile last checked?

The current profile verification date is October 1, 2026. The linked primary sources remain authoritative if the product changes between checks.

Method note: AgentenCode does not certify GDPR or EU AI Act compliance. It documents evidence that can support a separate legal, security or procurement assessment.