> For the complete documentation index, see [llms.txt](https://docs.balkan.id/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.balkan.id/agents/onboarding-agents/discovering-agents-from-integrations/anthropic-agents.md).
# Anthropic: Agents
### Overview
BalkanID supports discovery and governance of agents within Anthropic (Claude) as part of **IGA for Non-Human Identities (NHI)**.
{% hint style="info" %}
**Early Access:** Agents discovery is an Early Access capability. To enable Agents (Early Access) for your tenant, contact Customer Support. Anthropic managed agent discovery also requires the **Organization API Key (Managed Agents)** field on the Anthropic integration.
{% endhint %}
All agents are normalized into the BalkanID data model and surfaced on the **Agents** page under **Configure**, along with their owners, associated identities and credentials, access relationships, MCP server capabilities, and risk insights.
The associated agents can also be seen under the specific application integration (Anthropic) page.
### Required Anthropic configuration for Agent Discovery
To enable Anthropic agent discovery, please refer to the [Create an Organization API Key (Managed Agents)](/getting-started/setting-up-your-tenant/application-integrations/direct-application-integrations/anthropic-application-integration-setup.md#create-an-organization-api-key-managed-agents) section in the [Anthropic Application Integration](/getting-started/setting-up-your-tenant/application-integrations/direct-application-integrations/anthropic-application-integration-setup.md) Setup page.
You must also provide an **Admin API Key** so BalkanID can connect to your Anthropic organization. See [Create an Admin API Key](/getting-started/setting-up-your-tenant/application-integrations/direct-application-integrations/anthropic-application-integration-setup.md#create-an-admin-api-key).
These APIs allow BalkanID to build a complete view of managed agents, their MCP server connections, vault-backed credentials, and related access.
### Agent Types Supported
BalkanID tracks the following Anthropic agent types:
{% hint style="info" %}
Note: The agent types listed below are examples and do not represent the full set of supported Anthropic agents over time.
{% endhint %}
* Managed Agents
### What BalkanID discovers for Anthropic agents
For Anthropic managed agents, BalkanID can surface:
* **Managed agent inventory** — Agents discovered from the Anthropic Managed Agents APIs, including status (for example, active or archived)
* **MCP servers** — MCP servers configured on the agent, including connection details shown under agent capabilities
* **Built-in tools** — Native tools attached to the agent in Anthropic
* **Agent environments** — Environments associated through agent sessions
* **Agent vaults** — Vaults the agent can access through sessions
* **Vault credentials used by agents** — Including vault bearer tokens, vault MCP OAuth credentials, and vault environment variables
* **Invoking API keys** — Organization API keys associated with invoking or creating the agent, when available
* **Coordinator relationships** — Relationships where a coordinator managed agent coordinates other managed agents
For concepts, see [Introduction to Agents](/agents/introduction-to-agents.md). For the Agents UI after sync, see [Viewing Agents](/agents/viewing-agents.md).
### Common risks associated with Anthropic Agents include:
* **Unauthenticated MCP Server Bindings:** Managed agent MCP servers configured without credentials or authentication bindings.
* **Unowned Automation:** Managed agents synced into BalkanID without an assigned employee owner, reducing accountability.
* **Broad Credential Access:** Agents that can access multiple vault credentials or API keys, increasing blast radius if compromised.
* **Coordinator Blast Radius:** Coordinator agents that can orchestrate multiple subordinate agents across workspaces or tools.
This ensures visibility and governance of AI agent access in Anthropic, forming a critical part of IGA for Non-Human Identities.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.balkan.id/agents/onboarding-agents/discovering-agents-from-integrations/anthropic-agents.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
