---
type: "post"
slug: "restrict-where-claude-tag-operates"
title: "Restrict where Claude Tag operates"
description: "Claude Tag answers only where it was added and addressed, but the default lets anyone in that channel address it — and it may reply without a mention when it judges one is warranted."
retrieval_nugget: "Claude Tag answers only where it was added and addressed, but the default lets anyone in that channel address it — and it may reply without a mention when it judges one is warranted."
published_at: "2026-08-31"
updated_at: "2026-09-12"
record_date: "2026-08-25"
date_kind: "discovered_at"
topics: ["agent-integrations","agents","ai"]
entities: ["Claude"]
source_url: "https://claude.com/docs/claude-tag/admins/restrict-access"
source_title: "Restrict where Claude Tag operates - Claude.ai Documentation"
source_domain: "claude.com"
source_terms: ["Restrict","Claude","operates","your","Slack"]
summary_word_count: 189
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:restrict-where-claude-tag-operates"
status: "published"
source_urls: ["https://claude.com/docs/claude-tag/admins/restrict-access"]
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:5bd5a0aa3bab2a2f7a125611df06e37c2eefd68dfbea2e87d51779c044a9a010","reviewed_at":"2026-09-12T10:00:00Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":1,"watch_condition_count":1,"related_record_count":2}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Anthropic's governance page for Claude Tag sets out where the agent is allowed to act.","observed_facts":[{"text":"In channels Claude Tag responds only where it has been added and addressed, and an @-mention guarantees a response.","source_urls":["https://claude.com/docs/claude-tag/admins/restrict-access"]},{"text":"Most narrowing controls require the Owner role, with a smaller set available to channel managers and members.","source_urls":["https://claude.com/docs/claude-tag/admins/restrict-access"]}],"mechanism":"Anyone in a channel where the app has been added can address it until a single toggle narrows that to people inside the Claude organization, which matters in guest and Slack Connect channels where the membership is not the organization.","why_now":"the agent may reply to a message that does not mention it, when it judges a reply is warranted — so the boundary is where it was invited, not where it was asked","implications":["Direct messages are a separate surface running on the user's own account, which means the channel controls do not describe the whole exposure."],"evidence_boundary":"The page documents controls and permissions rather than observed behaviour, and the judgement rule for unprompted replies is described without criteria.","watch_conditions":["The condition to watch is whether unprompted replies become separately auditable, because a control surface that assumes an explicit mention understates where the agent can speak."],"related_records":[{"url":"https://newruntime.com/posts/organization-agent-runtime-qm-vercel-eve","relation":"Prior coverage of scoping an organization agent's runtime."},{"url":"https://newruntime.com/topics/agent-security","relation":"Topic hub for invitation and access scope."}]}
routes: {"html":"https://newruntime.com/posts/restrict-where-claude-tag-operates/","markdown":"https://newruntime.com/posts/restrict-where-claude-tag-operates.md","json":"https://newruntime.com/posts/restrict-where-claude-tag-operates.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Restrict where Claude Tag operates

## Retrieval answer

Claude Tag answers only where it was added and addressed, but the default lets anyone in that channel address it — and it may reply without a mention when it judges one is warranted.

Anthropic's governance page for Claude Tag sets out where the agent is allowed to act. In channels it responds only where it has been added and addressed, an @-mention guarantees a response, and once a thread is active it follows the replies in that thread. Most of the narrowing controls require the Owner role in the Claude organization, while a channel manager or member can take a smaller listed set of actions.

Two defaults deserve attention. Anyone in a channel where the app has been added can address it until a single toggle narrows that to people inside the Claude organization, which matters in guest and Slack Connect channels where the membership is not the organization. And the agent may reply to a message that does not mention it, when it judges a reply is warranted — so the boundary is where it was invited, not where it was asked.

Direct messages are a separate surface running on the user's own account, which means the channel controls do not describe the whole exposure. That is the same shape as [an organization agent being a scoped runtime rather than one bot](https://newruntime.com/posts/organization-agent-runtime-qm-vercel-eve/), and it is why the [agent security hub](https://newruntime.com/topics/agent-security/) treats invitation scope as an access-control question.

The page documents controls and permissions rather than observed behaviour, and the judgement rule for unprompted replies is described without criteria. The condition to watch is whether unprompted replies become separately auditable, because a control surface that assumes an explicit mention understates where the agent can speak.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Integrations](https://newruntime.com/topics/agent-integrations.md): Explore the agent-integrations topic hub.
- topic hub: [Agents](https://newruntime.com/topics/agents.md): Explore the agents topic hub.
- topic hub: [Ai](https://newruntime.com/topics/ai.md): Explore the ai topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)