282 pages for trigger.

Connect an authorization server Claude Documentation · in the page claude-tag/admins/federated-access/authorization-server …d) and exchanges a new one on the next request. A plain `403` doesn't trigger this. ## Register the endpoint and connect the server **1. Open the Connect an authorization server dialog** In **Autho… Restrict where Claude Tag operates Claude Documentation · in the page claude-tag/admins/restrict-access …e responds without being tagged, a restricted member's messages never trigger a response. * **Their thread replies aren't treated as requests.** In a thread an allowed member started, a restricted mem… Set a spend limit Claude Documentation · in the page claude-tag/admins/set-spend-limit …ed the threshold, so everyone there sees it, not only the thread that triggered it. Usage in a one-to-one DM with Claude doesn't post one. * **What it says**: it begins `:warning: Heads up`, names the… How Claude Tag works Claude Documentation · in the page claude-tag/concepts/how-it-works …f and scheduled tasks A session starts the same way whether a person triggers it or a schedule does. A tagged task runs in its thread's session, and the sandbox is released once the work finishes. A… Security and data handling Claude Documentation · in the page claude-tag/concepts/security-and-data …unts. Every channel request, whether a person typed it or a schedule triggered it, follows the same path: it runs in an isolated sandbox, and the credentials you provision aren't placed in that sandb… Work with Claude Tag Claude Documentation · in the page claude-tag/overview …de Tag run tasks on a schedule? Scheduled jobs, channel watching, and triggers](https://claude.com/docs/claude-tag/users/proactivity.md) ## Billing and spend limits Adding Claude to Slack doesn't ad… Troubleshoot Claude Tag in channels and DMs Claude Documentation · in the page claude-tag/users/troubleshooting …. **What it means** Editing a sent message to add a mention doesn't trigger a response; Claude only picks up mentions from new messages. **How to resolve** Send a new message with the mention incl… Catch up Claude Documentation · in the page claude-tag/users/use-cases/catch-up …//claude.com/docs/claude-tag/users/proactivity.md) > > Scheduling and triggers Track projects and chase approvals Claude Documentation · in the page claude-tag/users/use-cases/track-projects …ude.com/docs/claude-tag/users/proactivity.md) > > Schedules and event triggers > [card] [Good habits](https://claude.com/docs/claude-tag/users/good-habits.md) > > Definitions of done that close threa… Watch monitors and alerts Claude Documentation · in the page claude-tag/users/use-cases/watch-monitors …ude.com/docs/claude-tag/users/proactivity.md) > > Schedules and event triggers > [card] [Claude on call](https://claude.com/blog/ai-ci-cd-on-call) > > How Anthropic runs Claude as first responder for… Control when Claude Tag responds Claude Documentation · in the page claude-tag/users/when-claude-responds …laude-tag/users/proactivity.md), which has its own controls. ## What triggers a response Whether Claude replies to a message without an @-mention depends on where you send it. | Where you write | R… Lazy authentication for MCP servers Claude Documentation · in the page connectors/building/lazy-authentication …in it retries the same tool call. The challenge your server sends to trigger that prompt follows the [MCP authorization specification](https://modelcontextprotocol.io/specification/latest/basic/autho… Changelog Claude Documentation · in the page cowork/changelog …ll allow them. * Changed the built-in GitHub connector’s `actions_run_trigger` tool to ask before every call whatever `toolPolicy` says. `toolPolicy` can still block it. * Changed the built-in Microso… Monitoring Claude Documentation · in the page cowork/monitoring …`prompt.id` attribute links all events back to the single prompt that triggered them. | Attribute | Description | | - | - | | `prompt.id` | UUID v4 identifier linking all events produced while proces… Configure a custom OpenTelemetry collector Claude Documentation · in the page office-agents/opentelemetry …ens_saved` | Delta | | `compaction.success` | Boolean | | `compaction.trigger` | Currently always `reactive` | ### file.upload One span per uploaded file, emitted as its own root span rather than un… Performance and limits Claude Documentation · in the page office-agents/performance …*. “Office supports no more than 50 batch jobs in the queue. Any more triggers errors.”</li> <li id="cite-note-5">[↑](#cite-ref-5) “[File size limits for workbooks in SharePoint](https://support.mic… Create custom skills Claude Documentation · in the page skills/how-to …the desktop app and turn the skill on. **2. Try prompts that should trigger it** Send prompts that should trigger the skill, and review Claude's thinking to confirm it's loading the skill. **3. It… Configuration reference Claude Documentation · in the page third-party/claude-desktop/configuration …`, `push_files`, `create_or_update_file`, `delete_file`, `actions_run_trigger`, `pull_request_review_write`, `delete_repository`. Where no prompt can be shown, their calls are refused. > > > > **readO… Configuration changelog Claude Documentation · in the page third-party/claude-desktop/configuration-changelog …ith a tool's exact name, or `"*"`, can still allow them. `actions_run_trigger` now asks before every call whatever `toolPolicy` says, and `toolPolicy` can still block it. * `sshClientPath` (beta) on W… Connect to GitHub Claude Documentation · in the page third-party/claude-desktop/connectors-github …eversible GitHub actions (merging a pull request, pushing commits, or triggering a workflow, for example) stay at ask or stricter no matter what the policy says. The default `repo` OAuth scope grants… Connect to Microsoft 365 Claude Documentation · in the page third-party/claude-desktop/connectors-m365 …tem browser automatically. > > A missing broker redirect URI does not trigger the fallback on Windows. The broker shows Entra error `AADSTS50011` in its own sign-in dialog, and closing that dialog cou… MCP, plugins, skills, and hooks Claude Documentation · in the page third-party/claude-desktop/extensions …r on `oauth` entries. While the connection is open, the TTL schedule triggers renewal, and a request that the server rejects with HTTP 401 or 403 also re-runs the helper and, when it returns new head… Deploy Claude Desktop on 3P with an LLM gateway Claude Documentation · in the page third-party/claude-desktop/gateway …ts a request. | Where the provider's too-long error is the compaction trigger, the session compacts and retries only if that error reaches it unchanged. With a rewritten error, the session shows the e… Tasks and Events Charter Model Context Protocol · in the page community/working-groups/tasks-events …anges to its lifecycle. * **Specification Work**: SEPs defining the trigger/callback mechanism, subscription lifecycle, delivery semantics, and event ordering guarantees. * **Reference Implementatio… Working Groups and Interest Groups Model Context Protocol · in the page community/working-interest-groups …by the deadline, the proposal is accepted. 2. Formal vote. A vote is triggered when a WG Member blocks during the lazy consensus period, or when a Lead or three or more WG Members request one. Quorum… Roadmap Model Context Protocol · in the page development/roadmap …est-groups/agents.md) IG. Primitives in the making, such as Tasks and Triggers, need to compose cleanly with each other and fit concrete use cases. Beyond these, we expect continued work on Tasks ([S… Build with Agent Skills Model Context Protocol · in the page docs/2024-11-05/develop/build-with-agent-skills …lled, ask your agent to help you build an MCP server. The entry skill triggers on natural-language requests, or you can invoke it directly using your agent's skill-invocation syntax. The skill runs a… Understanding MCP servers Model Context Protocol · in the page docs/2024-11-05/learn/server-concepts …s. Tools can write to databases, call external APIs, modify files, or trigger other logic. | Search flights Send messages Create calendar events | Model | | **Resources** | Passive data sources that p… Understanding Authorization in MCP Model Context Protocol · in the page docs/2024-11-05/tutorials/security/authorization …rage. With Keycloak configured, every time the authorization flow is triggered, your MCP server will receive a token like this: ```text theme={null} eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6I… Security Best Practices Model Context Protocol · in the page docs/2024-11-05/tutorials/security/security_best_practices …Service interaction**: POST requests (e.g., to token endpoints) can trigger mutations on internal services * **Firewall bypass**: The MCP client acts as a proxy, bypassing network perimeter contro… Build with Agent Skills Model Context Protocol · in the page docs/2025-03-26/develop/build-with-agent-skills …lled, ask your agent to help you build an MCP server. The entry skill triggers on natural-language requests, or you can invoke it directly using your agent's skill-invocation syntax. The skill runs a… Understanding MCP servers Model Context Protocol · in the page docs/2025-03-26/learn/server-concepts …s. Tools can write to databases, call external APIs, modify files, or trigger other logic. | Search flights Send messages Create calendar events | Model | | **Resources** | Passive data sources that p… Understanding Authorization in MCP Model Context Protocol · in the page docs/2025-03-26/tutorials/security/authorization …rage. With Keycloak configured, every time the authorization flow is triggered, your MCP server will receive a token like this: ```text theme={null} eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6I… Security Best Practices Model Context Protocol · in the page docs/2025-03-26/tutorials/security/security_best_practices …Service interaction**: POST requests (e.g., to token endpoints) can trigger mutations on internal services * **Firewall bypass**: The MCP client acts as a proxy, bypassing network perimeter contro… Build with Agent Skills Model Context Protocol · in the page docs/2025-06-18/develop/build-with-agent-skills …lled, ask your agent to help you build an MCP server. The entry skill triggers on natural-language requests, or you can invoke it directly using your agent's skill-invocation syntax. The skill runs a… Understanding MCP servers Model Context Protocol · in the page docs/2025-06-18/learn/server-concepts …s. Tools can write to databases, call external APIs, modify files, or trigger other logic. | Search flights Send messages Create calendar events | Model | | **Resources** | Passive data sources that p… Understanding Authorization in MCP Model Context Protocol · in the page docs/2025-06-18/tutorials/security/authorization …rage. With Keycloak configured, every time the authorization flow is triggered, your MCP server will receive a token like this: ```text theme={null} eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6I… Security Best Practices Model Context Protocol · in the page docs/2025-06-18/tutorials/security/security_best_practices …Service interaction**: POST requests (e.g., to token endpoints) can trigger mutations on internal services * **Firewall bypass**: The MCP client acts as a proxy, bypassing network perimeter contro… Build with Agent Skills Model Context Protocol · in the page docs/2025-11-25/develop/build-with-agent-skills …lled, ask your agent to help you build an MCP server. The entry skill triggers on natural-language requests, or you can invoke it directly using your agent's skill-invocation syntax. The skill runs a… Understanding MCP servers Model Context Protocol · in the page docs/2025-11-25/learn/server-concepts …s. Tools can write to databases, call external APIs, modify files, or trigger other logic. | Search flights Send messages Create calendar events | Model | | **Resources** | Passive data sources that p… Understanding Authorization in MCP Model Context Protocol · in the page docs/2025-11-25/tutorials/security/authorization …rage. With Keycloak configured, every time the authorization flow is triggered, your MCP server will receive a token like this: ```text theme={null} eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6I… Security Best Practices Model Context Protocol · in the page docs/2025-11-25/tutorials/security/security_best_practices …Service interaction**: POST requests (e.g., to token endpoints) can trigger mutations on internal services * **Firewall bypass**: The MCP client acts as a proxy, bypassing network perimeter contro… Build with Agent Skills Model Context Protocol · in the page docs/2026-07-28/develop/build-with-agent-skills …lled, ask your agent to help you build an MCP server. The entry skill triggers on natural-language requests, or you can invoke it directly using your agent's skill-invocation syntax. The skill runs a… Understanding MCP servers Model Context Protocol · in the page docs/2026-07-28/learn/server-concepts …s. Tools can write to databases, call external APIs, modify files, or trigger other logic. | Search flights Send messages Create calendar events | Model | | **Resources** | Passive data sources that p… Configuration and flags Model Context Protocol · in the page docs/2026-07-28/tools/inspector/configuration …rypted is left in place. Setting `MCP_INSPECTOR_SECRET_STORE=keyring` triggers the same hand-off. Choosing `file` or `memory` never copies anything out of the keychain. ## Catalog file format A cata… Protocol eras Model Context Protocol · in the page docs/2026-07-28/tools/inspector/protocol-eras …t`. * **Invalid Parameters**: any other `-32602`. Reproduce with the `trigger_invalid_params` tool in the config above. The two share one error code, so the Inspector reads the message to tell them a… Web client Model Context Protocol · in the page docs/2026-07-28/tools/inspector/web …nt-scope response**, which decides whether a `403 insufficient_scope` triggers [step-up](https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector/authorization.md#mid-session-re-authorization)… Local Server Security Model Context Protocol · in the page docs/2026-07-28/tutorials/security/local-server-security …at connect stdio clients to remote servers have had critical flaws triggered by nothing more than connecting to a malicious endpoint, and local developer tools listening on a port have been e… Security Best Practices Model Context Protocol · in the page docs/2026-07-28/tutorials/security/security_best_practices …Service interaction**: POST requests (e.g., to token endpoints) can trigger mutations on internal services * **Firewall bypass**: The MCP client acts as a proxy, bypassing network perimeter contro… Build with Agent Skills Model Context Protocol · in the page docs/draft/develop/build-with-agent-skills …lled, ask your agent to help you build an MCP server. The entry skill triggers on natural-language requests, or you can invoke it directly using your agent's skill-invocation syntax. The skill runs a…