Federated agent access changedclaude-tag/admins/federated-access/overview
Nearest release: v2.1.290, published under an hour before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 5 Oct 2026 18:54 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 22 Oct 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+17added
Lines−17removed
From line
10
where the diff opens
First seen
10 Sep 2026
this site's first read of the page
Recorded edits10to this page, all time
The whole hunk
from line 10, old and new numbered
/
from line 10
1010>
1111> Federated connections are managed on the [**Federated agent access**](https://claude.ai/admin-settings/claude-tag/federated-cloud-access) page, under **Claude Tag** in the admin settings sidebar. Connecting a gateway, cloud role, or authorization server needs an organization Owner, or an admin with full Claude Tag management permission.
1212
13In Slack channels, Claude Tag acts under its own [agent identity](/docs/claude-tag/concepts/agent-identity) rather than as any person. Federated agent access lets that identity prove itself to your systems with a short-lived, signed identity token instead of a credential you store in Claude.
13In Slack channels, Claude Tag acts under its own [agent identity](/docs/claude-tag/concepts/agent-identity.md) rather than as any person. Federated agent access lets that identity prove itself to your systems with a short-lived, signed identity token instead of a credential you store in Claude.
1414
15In the console, you connect your gateway, AWS role, Google Cloud identity, or authorization server under **Federated agent access**, add it to a [bundle](/docs/claude-tag/concepts/glossary#access-bundle), and [apply it to the channels](#manage-federated-connections-on-the-connectors-tab) where Claude should use it. Your cloud or gateway administrator configures that system to trust Anthropic's issuer and to check that each token's subject belongs to your organization, and the system then decides what the agent may do. To confirm the connection works, ask Claude in one of those channels to make a small request, then check its reply and your system's logs.
15In the console, you connect your gateway, AWS role, Google Cloud identity, or authorization server under **Federated agent access**, add it to a [bundle](/docs/claude-tag/concepts/glossary.md#access-bundle), and [apply it to the channels](#manage-federated-connections-on-the-connectors-tab) where Claude should use it. Your cloud or gateway administrator configures that system to trust Anthropic's issuer and to check that each token's subject belongs to your organization, and the system then decides what the agent may do. To confirm the connection works, ask Claude in one of those channels to make a small request, then check its reply and your system's logs.
1616
1717Federated agent access goes one way: Claude proves who it is to your systems. For your workloads proving who they are to the Claude API, see [Workload Identity Federation](https://platform.claude.com/docs/en/manage-claude/workload-identity-federation) on the Claude Developer Platform.
1818
from line 27
2727| **Google Cloud identity** | Google Cloud, through a workload identity pool. Google issues an access token for the federated identity, acting as a service account if you name one. | Claude should call Google Cloud APIs under an identity you govern with IAM. |
2828| **Authorization server** | Your OAuth 2.0 authorization server. It accepts the token as a JWT bearer grant (RFC 7523) and returns an access token for your APIs. | Your APIs are already protected by your own OAuth server and you'd rather issue its tokens than run a gateway. |
2929
30In every case the system on your side decides what the agent may do in your systems. Each connection type has its own setup page: [Connect a gateway](/docs/claude-tag/admins/federated-access/connect-a-gateway), [Connect an AWS role](/docs/claude-tag/admins/federated-access/aws), [Connect a Google Cloud identity](/docs/claude-tag/admins/federated-access/gcp), and [Connect an authorization server](/docs/claude-tag/admins/federated-access/authorization-server).
30In every case the system on your side decides what the agent may do in your systems. Each connection type has its own setup page: [Connect a gateway](/docs/claude-tag/admins/federated-access/connect-a-gateway.md), [Connect an AWS role](/docs/claude-tag/admins/federated-access/aws.md), [Connect a Google Cloud identity](/docs/claude-tag/admins/federated-access/gcp.md), and [Connect an authorization server](/docs/claude-tag/admins/federated-access/authorization-server.md).
3131
3232## How it works
3333
341. When a request from Claude's sandbox needs one of your systems, [Agent Proxy](/docs/claude-tag/concepts/agent-identity#agent-proxy) matches it by destination to a federated connection that applies to the channel. Until an admin connects a system in **Federated agent access** and applies the connection to the channel, nothing matches and no token is issued for Claude's requests.
341. When a request from Claude's sandbox needs one of your systems, [Agent Proxy](/docs/claude-tag/concepts/agent-identity.md#agent-proxy) matches it by destination to a federated connection that applies to the channel. Until an admin connects a system in **Federated agent access** and applies the connection to the channel, nothing matches and no token is issued for Claude's requests.
35352. Anthropic issues an identity token. The token is a JSON Web Token (JWT) signed by Anthropic and valid for 10 minutes. Its subject names your organization and the agent, in the form `wimse://identity.anthropic.com/org/<your organization ID>/agent/<agent ID>`, and its audience names the destination. Claude reuses one token for a session's requests to the same gateway for about five minutes, or until the gateway answers 401, and then requests a new one. The other connection types use a token once, in an exchange.
36363. Your side accepts the token. A gateway verifies it directly. AWS or Google Cloud exchanges it for a short-lived cloud credential. Your authorization server exchanges it for an access token. Agent Proxy attaches the result to Claude's request, or signs the request with it for AWS, and forwards the request. The model and the sandbox are never given the token or the credential that comes back.
3737
from line 42
4242* **Expiry**. This proves the token is fresh.
4343* **Subject**. This is what names your organization. Every Claude Tag organization's tokens come from the same issuer, and every organization's AWS tokens share the same audience, so the first four checks can pass for a token that belongs to someone else. Every connection type therefore requires a subject check. The strongest form accepts only the exact subjects of your own agents. The minimum form requires the subject to start with your **Subject prefix**, `wimse://identity.anthropic.com/org/<your organization ID>/agent/`, including the `/agent/`; a gateway, authorization server, or Google Cloud attribute condition can pin `iss` and `tenant` instead, since `tenant` carries the same organization ID.
4444
45The console shows the issuer, the signing-key location, and your **Subject prefix** with copy buttons, and each setup page says where they go. The [identity token reference](/docs/claude-tag/admins/federated-access/token-reference) lists every value and claim and [compares the two forms of the subject check](/docs/claude-tag/admins/federated-access/token-reference#authorize-on-the-subject).
45The console shows the issuer, the signing-key location, and your **Subject prefix** with copy buttons, and each setup page says where they go. The [identity token reference](/docs/claude-tag/admins/federated-access/token-reference.md) lists every value and claim and [compares the two forms of the subject check](/docs/claude-tag/admins/federated-access/token-reference.md#authorize-on-the-subject).
4646
47Anthropic stores no long-lived credential for your systems, and each call carries a short-lived signed token, so there is no key of yours to rotate or leak. Anthropic rotates its own signing keys, and the [token reference](/docs/claude-tag/admins/federated-access/token-reference#key-rotation) says how a verifier follows them.
47Anthropic stores no long-lived credential for your systems, and each call carries a short-lived signed token, so there is no key of yours to rotate or leak. Anthropic rotates its own signing keys, and the [token reference](/docs/claude-tag/admins/federated-access/token-reference.md#key-rotation) says how a verifier follows them.
4848
4949To cut off access, remove the connection in the console. These lifetimes then apply:
5050
from line 63
6363* **Federated agent access** appears under **Claude Tag** in the console's left navigation. It's missing for organizations whose compliance configuration excludes federated agent access.
6464* An organization Owner, or an admin with full Claude Tag management permission, makes the connection in the console.
6565* Your cloud or gateway administrator configures the system on your side: the gateway operator, your AWS or Google Cloud IAM administrator, or your authorization server's operator. Each setup page lists the values they configure.
66* You know which channels, workspaces, or all of Slack Claude should use the connection in. A connection applies wherever its [bundle](/docs/claude-tag/concepts/glossary#access-bundle) applies. A gateway can also be added to more than one bundle; an AWS role or authorization server is connected in one bundle only.
66* You know which channels, workspaces, or all of Slack Claude should use the connection in. A connection applies wherever its [bundle](/docs/claude-tag/concepts/glossary.md#access-bundle) applies. A gateway can also be added to more than one bundle; an AWS role or authorization server is connected in one bundle only.
6767
68Federated connections work in Slack channels, where Claude acts under your organization's agent identity. They don't work in one-to-one direct messages from members who have connected a Claude account, which run under [the individual's own account](/docs/claude-tag/concepts/agent-identity#direct-message-channels).
68Federated connections work in Slack channels, where Claude acts under your organization's agent identity. They don't work in one-to-one direct messages from members who have connected a Claude account, which run under [the individual's own account](/docs/claude-tag/concepts/agent-identity.md#direct-message-channels).
6969
7070## Manage federated connections on the Connectors tab
7171
from line 73
7373
7474The connection then also appears as a connector on the **Connectors** tab under **Claude's access** at [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag), where the tab's search finds it by name or host and its row in the connector's **Access from** table shows its type in the **Credential** column. Manage it from there:
7575
76* **Choose where it applies**: a bundle you create in the connect dialog applies nowhere until you choose places. The bundle is listed on the **Bundles** tab, where you add places under **Where it applies** and click **Save changes**. To choose places from the connector's page instead, see [Give Claude access](/docs/claude-tag/admins/add-connections).
76* **Choose where it applies**: a bundle you create in the connect dialog applies nowhere until you choose places. The bundle is listed on the **Bundles** tab, where you add places under **Where it applies** and click **Save changes**. To choose places from the connector's page instead, see [Give Claude access](/docs/claude-tag/admins/add-connections.md).
7777* **Edit its allowed hosts**: in the connector's **Access from** table, open the connection's **⋮** menu and choose **Edit** to open the **Edit connection** dialog.
7878* **Delete it from its bundle**: open the connection's bundle from the **Bundles** tab, and under **What's in it** choose **Remove credential** from the connection's **⋮** menu, then click **Delete** to confirm. The **Set by** column of the connector's **Access from** table names that bundle.
7979
8080## Related resources
8181
82* [How agent identity works](/docs/claude-tag/concepts/agent-identity): the identity these tokens represent, and how Agent Proxy attaches credentials
83* [Connect a gateway](/docs/claude-tag/admins/federated-access/connect-a-gateway): verify the token at a service you run
84* [Connect an AWS role](/docs/claude-tag/admins/federated-access/aws): the IAM OIDC provider and trust policy
85* [Connect a Google Cloud identity](/docs/claude-tag/admins/federated-access/gcp): the workload identity pool, provider, and attribute condition
86* [Connect an authorization server](/docs/claude-tag/admins/federated-access/authorization-server): accept the token as a JWT bearer grant
87* [Identity token reference](/docs/claude-tag/admins/federated-access/token-reference): every claim, the lifetime, and key rotation
88* [Limits](/docs/claude-tag/admins/federated-access/limits): counts, lengths, lifetimes, and unsupported configurations
89* [Troubleshoot federated agent access](/docs/claude-tag/admins/federated-access/troubleshooting): console messages, blocked requests, and rejections in your logs
82* [How agent identity works](/docs/claude-tag/concepts/agent-identity.md): the identity these tokens represent, and how Agent Proxy attaches credentials
83* [Connect a gateway](/docs/claude-tag/admins/federated-access/connect-a-gateway.md): verify the token at a service you run
84* [Connect an AWS role](/docs/claude-tag/admins/federated-access/aws.md): the IAM OIDC provider and trust policy
85* [Connect a Google Cloud identity](/docs/claude-tag/admins/federated-access/gcp.md): the workload identity pool, provider, and attribute condition
86* [Connect an authorization server](/docs/claude-tag/admins/federated-access/authorization-server.md): accept the token as a JWT bearer grant
87* [Identity token reference](/docs/claude-tag/admins/federated-access/token-reference.md): every claim, the lifetime, and key rotation
88* [Limits](/docs/claude-tag/admins/federated-access/limits.md): counts, lengths, lifetimes, and unsupported configurations
89* [Troubleshoot federated agent access](/docs/claude-tag/admins/federated-access/troubleshooting.md): console messages, blocked requests, and rejections in your logs
9090
No line in this hunk matches that.