# Google SecOps MCP connector

The Google SecOps connector brings alert grouping rules, announcements, case alert context and involved entities into Elaichi, so Claude, ChatGPT, Cursor, Microsoft Copilot and the Elaichi Agent can work with them under each analyst's own access.

Source: https://elaichi.ai/connectors/googlesecops/

## Facts

| | |
| --- | --- |
| Application | Google SecOps |
| Category | Security |
| AI tools | 573 |
| Authentication | Connects over OAuth |
| Bring your own OAuth app | Yes |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Google SecOps is connected

- List alert grouping rules that merge phishing alerts into one case
- Show the involved entities on case alert 4821 and summarize them
- Draft an announcement about tonight's SIEM maintenance window

## Connect Google SecOps in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Google SecOps.
2. Optionally set Share with, then press Connect.
3. Supply your own Google SecOps app, then approve. Google SecOps needs an OAuth app you register yourself, so bring its client ID and secret. One person does this once for the organization.

Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Google SecOps tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Google SecOps MCP connector for Claude

Endpoint: https://api.elaichi.ai/mcp

1. Open Customize, then Connectors.
2. Press Add.
3. Name it, paste the MCP server URL, then Continue.
4. Sign in and approve.

On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.

## Google SecOps MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Google SecOps MCP connector for ChatGPT

Endpoint: https://api.elaichi.ai/mcp

1. Open Plugins, then press the + button.
2. Name it and paste the endpoint into Server URL.
3. Leave Authentication on OAuth, then tick the risk acknowledgement.
4. Press Create, then sign in and approve.

Works on the web. The plugin directory lives at chatgpt.com/plugins.

## Google SecOps MCP connector for Cursor

Endpoint: https://api.elaichi.ai/mcp

1. Open `~/.cursor/mcp.json`.
2. Add the endpoint under `mcpServers`.
3. Reload Cursor, then sign in and approve.

Set up per machine, so repeat it on each computer you work from.

## Google SecOps MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Google SecOps to any MCP client

Endpoint: https://api.elaichi.ai/mcp

1. Add the endpoint as a remote MCP server.
2. Sign in and approve.

The Elaichi Agent already has these tools, with nothing to set up.

## What the consent screen decides

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Google SecOps tool needs "Use your connected apps". Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Google SecOps through Elaichi

### Catch a case alert up after triage

SOC. Add what you found as context properties on the case alert and record the hosts, users and addresses involved, so the next analyst on shift sees the full picture in Google SecOps.

### Tune alert grouping rules in plain language

Detection engineering. Ask which alert grouping rules exist in Google SecOps, review the one that keeps splitting related alerts, and update it so they land in a single case.

### See everyone and everything involved in an alert

Incident response. Fetch the entity cards for a case alert and get a plain summary of the accounts, machines and indicators tied to it before you join the bridge call.

### Tag an involved entity with what you know

Threat intelligence. Add or update a property on an involved entity in Google SecOps, such as a known-bad flag or a campaign name, so analysts see the intel beside the alert.

### Provision a BigQuery export for reporting

Security engineering. Set up the Google SecOps export to BigQuery from a prompt, so the analytics team can query detections without waiting on a ticket.

### Post an announcement to the whole SOC

Security leadership. Draft an announcement about a new playbook, a maintenance window or a shift change and publish it in Google SecOps where every analyst will see it.

## Elaichi vs Zapier MCP vs Composio for Google SecOps

All three can connect Google SecOps to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Google SecOps tools | Allow or restrict single Google SecOps tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Google SecOps call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Google SecOps to Claude?

Connect Google SecOps in Elaichi first, then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Google SecOps connects over OAuth, but it needs an OAuth application registered inside Google SecOps itself, so an administrator brings that client ID and secret into Elaichi once. After that, each person signs in to Google SecOps with their own account and nobody else handles a credential.

### Does Google SecOps work with ChatGPT and Cursor as well as Claude?

Yes. Once Google SecOps is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Google SecOps once and every client picks it up.

### What can an AI agent actually do with my Google SecOps data?

It can list, read, create, update and delete alert grouping rules and announcements in Google SecOps, add context and involved entities to a case alert, fetch the entity cards tied to an alert, and provision a BigQuery export. Clients do not get a long menu of tools, they search for what they need, so short concrete asks such as list the grouping rules for phishing work better than long sentences.

### Does connecting Google SecOps give the AI access to everything in my SIEM?

No. Every call into Google SecOps runs as the person who signed in, so the agent sees the cases, rules and entities that person's Google SecOps role already allows and nothing more. Elaichi can narrow that access further with roles and restrictions, but it can never widen it beyond what Google SecOps itself grants.

### Can my team share one Google SecOps connection?

Yes. One administrator connects Google SecOps in Elaichi and shares the connection with a team, and nobody else ever sees or handles the client ID and secret. Each analyst still signs in to Google SecOps as themselves, so the audit log names the actual person behind every case update or rule change.

### Can I stop an agent from deleting or changing things in Google SecOps?

Yes. Restrictions in Elaichi work per action, so you can restrict deleting alert grouping rules or updating announcements in Google SecOps for a role or for one person. A restricted tool still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a Google SecOps connection when someone leaves?

Offboarding that person in Elaichi ends their access to Google SecOps through every client at once. A shared Google SecOps connection keeps working for everyone else on the team. If you want to remove Google SecOps entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client.

### Does the Google SecOps MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Google SecOps is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Google SecOps?

Yes. Both let Claude, ChatGPT or Cursor use Google SecOps. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Google SecOps call.

### How is Elaichi different from Composio for Google SecOps?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Google SecOps: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 573 Google SecOps tools

Every tool below is callable through https://api.elaichi.ai/mcp once Google SecOps is connected, subject to the toolbox it is in and the restrictions on the caller.

- **Create a Google SecOps alert grouping rule** (Create). Creates a new alert grouping rule. Defines new criteria for alert aggregation, specifying how future incoming alerts should be consolidated into cases based on shared attributes or entity correlations. Returns a AlertGroupingRule. Required: entityType, categoryDetails, category, groupingType. [POST /v1/{parent}/alertGroupingRules]
- **Delete a Google SecOps alert grouping rule by ID** (Delete). Deletes an alert grouping rule. This permanently removes the rule from the system, and alerts previously governed by this rule will no longer be aggregated based on its criteria. The id is the alert grouping rule ID (last segment of its resource name). Required: id. [DELETE /v1/{name}]
- **Get single Google SecOps alert grouping rule by ID** (Get). Gets an alert grouping rule. Use this method to retrieve the configuration of a specific rule that defines how alerts are automatically grouped into cases based on criteria like alert type, product name, or data source upon ingestion. The id is the alert grouping rule ID (last segment of its resource name). Returns a AlertGroupingRule. Required: id. [GET /v1/{name}]
- **List all Google SecOps alert grouping rules** (List). Lists alert grouping rules. Supports filtering by category or grouping type. [GET /v1/{parent}/alertGroupingRules]
- **Update a Google SecOps alert grouping rule by ID** (Update). Updates an existing alert grouping rule. Use this method to modify rule criteria, such as the entity types used for correlation or the specific category details like alert types or products included in the rule. The id is the alert grouping rule ID (last segment of its resource name). Returns a AlertGroupingRule. Required: id, entityType, categoryDetails, category, groupingType. [PATCH /v1/{alertGroupingRule.name}]
- **Create a Google SecOps announcement** (Create). Creates a new announcement. Use this method to broadcast platform-wide information to users, specifying the content, a title, and an optional expiration time. The system automatically records the creator. Returns a Announcement. Required: content, title. [POST /v1/{parent}/announcements]
- **Delete a Google SecOps announcement by ID** (Delete). Deletes an announcement. Permanently removes the announcement from the system. The id is the announcement ID (last segment of its resource name). Required: id. [DELETE /v1/{name}]
- **Get single Google SecOps announcement by ID** (Get). Gets a specific announcement. Use this method to retrieve the details of an announcement, including its title, content, author, and expiration information. The id is the announcement ID (last segment of its resource name). Returns a Announcement. Required: id. [GET /v1/{name}]
- **List all Google SecOps announcements** (List). Lists announcements for a specific instance. Supports pagination and ordering by title or creation time, allowing users to browse through active and past platform announcements. [GET /v1/{parent}/announcements]
- **Update a Google SecOps announcement by ID** (Update). Updates an existing announcement. Allows modifying the title, content, or expiration time. The system tracks the last user who performed the update. The id is the announcement ID (last segment of its resource name). Returns a Announcement. Required: id, content, title. [PATCH /v1/{announcement.name}]
- **Google SecOps big query export provision** (Search). Provision the BigQuery export for a Chronicle instance. This will create Google Cloud resources like Cloud Storage buckets, BigQuery datasets and set default export settings for each data source. Returns a BigQueryExport. [POST /v1/{parent}/bigQueryExport:provision]
- **Google SecOps case alert context properties clear all** (Clear). Deletes all context properties associated with a specific parent context. Use this method to quickly clear all supplemental data from a case, alert, or integration. Required: case_id, case_alert_id. [POST /v1/{parent}/contextProperties:clearAll]
- **Create a Google SecOps case alert context property** (Create). Creates a new context property. Use this method to attach custom data to a specific context. Property keys must be unique within their context. Returns a ContextProperty. Required: case_id, case_alert_id, value. [POST /v1/{parent}/contextProperties]
- **Delete a Google SecOps case alert context property by ID** (Delete). Deletes a specific context property. Use this method to remove a custom data point that is no longer relevant to the context. The id is the context property ID (last segment of its resource name). Required: id, case_id, case_alert_id. [DELETE /v1/{name}]
- **Get single Google SecOps case alert context property by ID** (Get). Gets a single context property by its resource name. Use this method to retrieve the value of a specific key within a given context (e.g., a custom metadata tag for a case). The id is the context property ID (last segment of its resource name). Returns a ContextProperty. Required: id, case_id, case_alert_id. [GET /v1/{name}]
- **List all Google SecOps case alert context properties** (List). Lists all context properties for a specific parent entity. Use this method to discover all custom data points associated with a case, alert, or integration component. Required: case_id, case_alert_id. [GET /v1/{parent}/contextProperties]
- **Update a Google SecOps case alert context property by ID** (Update). Updates an existing context property. Use this method to modify the value of a previously saved key. The id is the context property ID (last segment of its resource name). Returns a ContextProperty. Required: id, case_id, case_alert_id, value. [PATCH /v1/{contextProperty.name}]
- **Google SecOps case alert involved entities add property** (Add). Adds a new custom property to an InvolvedEntity. Use this method to attach arbitrary metadata or enrichment results to an actor. Returns a InvolvedEntity. Required: case_id, case_alert_id, involved_entity_id, key, value. [POST /v1/{name}:addProperty]
- **Create a Google SecOps case alert involved entity** (Create). Manually adds a new InvolvedEntity to a case and alert. Use this method to include additional actors discovered through manual analysis that were not automatically identified by ingestion. Returns a InvolvedEntity. Required: case_id, case_alert_id, id, type, suspicious, internal. [POST /v1/{parent}/involvedEntities]
- **Google SecOps case alert involved entities fetch cards** (Action). Returns metadate of each involved entity in a specific alert, including their connectivity and high-level status. Use this method to populate visual graphs or high-level summaries of an investigation scope. Required: case_id, case_alert_id. [GET /v1/{parent}/involvedEntities:fetchCards]
- **Get single Google SecOps case alert involved entity by ID** (Get). Gets a single InvolvedEntity by its resource name. Use this method to retrieve the detailed attributes, suspicion status, and enriched properties for a specific actor in an investigation. The id is the involved entity ID (last segment of its resource name). Returns a InvolvedEntity. Required: id, case_id, case_alert_id. [GET /v1/{name}]
- **List all Google SecOps case alert involved entities** (List). Lists all InvolvedEntities associated with a specific case and alert. Required: case_id, case_alert_id. [GET /v1/{parent}/involvedEntities]
- **Update a Google SecOps case alert involved entity by ID** (Update). Updates an existing InvolvedEntity. Use this method to modify core attributes like suspicion levels or os information. The id is the involved entity ID (last segment of its resource name). Returns a InvolvedEntity. Required: id, case_id, case_alert_id, id, type, suspicious, internal. [PATCH /v1/{involvedEntity.name}]
- **Google SecOps case alert involved entities update property** (Update). Updates the value of an existing custom property on an InvolvedEntity. Use this method to refine or correct metadata attached to an actor. Returns a InvolvedEntity. Required: case_id, case_alert_id, involved_entity_id, key, value. [POST /v1/{name}:updateProperty]
- **Google SecOps case alerts create recommendation long running** (Create). Initiates an asynchronous request to generate a new AI recommendation for an alert. This is an asynchronous process that analyzes the alert context to provide tailored investigation or response suggestions. Required: case_id, case_alert_id. [POST /v1/{parent}:createRecommendationLongRunning]
- **Google SecOps case alerts fetch recommendation** (Action). Fetches a previously generated AI-driven recommendation for an alert. Use this method to retrieve suggested actions or insights derived from similar historical alerts. Required: case_id, recommendationId. [GET /v1/{parent}/caseAlerts:fetchRecommendation]
- **Get single Google SecOps case alert by ID** (Get). Gets a single CaseAlert. Use this method to retrieve detailed information about a specific alert, including its current status, priority, and associated metadata. The id is the case alert ID (last segment of its resource name). Returns a CaseAlert. Required: id, case_id. [GET /v1/{name}]
- **Google SecOps case alerts get alert overview data** (Get). Retrieves a view of widgets for a specific alert. Use this method to get a high-level summary of the alert, potentially tailored to a specific playbook view. Returns a OverviewData. Required: case_id, case_alert_id. [GET /v1/{name}:alertOverviewData]
- **List all Google SecOps case alerts** (List). Lists CaseAlerts within a specific Case. Use this method to retrieve a paginated list of alerts associated with a case. Supports filtering by status, priority, and other alert attributes. Required: case_id. [GET /v1/{parent}/caseAlerts]
- **Google SecOps case alerts move** (Move). Moves a CaseAlert to a different Case. Use this method to reassign an alert to a more appropriate case. The alert must be open, and both the source and destination cases must also be open. Required: case_id, case_alert_id. [POST /v1/{name}:move]
- **Update a Google SecOps case alert by ID** (Update). Updates an existing CaseAlert. Use this method to modify alert properties such as status, priority, or closure details. When closing an alert, valid closure reason and comments must be provided. The id is the case alert ID (last segment of its resource name). Returns a CaseAlert. Required: id, case_id. [PATCH /v1/{caseAlert.name}]
- **Google SecOps case alerts pause SLA** (Pause). Pauses the SLA timer for a CaseAlert. Use this method when alert investigation is temporarily halted (e.g., waiting for external input). A message explaining the reason for the pause is required. Required: case_id, case_alert_id. [POST /v1/{name}:pauseSla]
- **Google SecOps case alerts resolve overview widget** (Action). Resolves the data for a specific alert overview widget. Use this method to fetch updated content for a UI widget (e.g., graphs, activity feeds, or entity highlights) associated with an alert view. Required: case_id, case_alert_id, widgetIdentifier, caseId. [GET /v1/{name}:resolveOverviewWidget]
- **Google SecOps case alerts resume SLA** (Resume). Resumes a previously paused SLA timer for a CaseAlert. Use this method to resume the countdown once investigation activities continue. Required: case_id, case_alert_id. [POST /v1/{name}:resumeSla]
- **Google SecOps case alerts set SLA** (Set). Sets the Service Level Agreement (SLA) for a specific CaseAlert. Use this method to define or update the total and critical time limits for handling the alert. The alert must be open to update its SLA. Required: case_id, case_alert_id. [POST /v1/{name}:setSla]
- **Google SecOps case chat message attachments download** (Download). Downloads the raw content of a ChatMessageAttachment . Use this method to retrieve shared files for analysis. Required: case_id, chat_message_id, attachment_id. [GET /v1/{name}:download]
- **Create a Google SecOps case chat message** (Create). Creates a new ChatMessage in a Case . Use this method to post updates or questions to the case chat. Mentioning users with '@' will trigger notifications. Returns a ChatMessage. Required: case_id, text. [POST /v1/{parent}/chatMessages]
- **Get single Google SecOps case chat message by ID** (Get). Gets a single ChatMessage by its resource name. Use this method to retrieve the content and author details of a specific message. The id is the chat message ID (last segment of its resource name). Returns a ChatMessage. Required: id, case_id. [GET /v1/{name}]
- **List all Google SecOps case chat messages** (List). Lists ChatMessages for a specific Case . Use this method to retrieve the communication history and chronological dialogue between analysts. Required: case_id. [GET /v1/{parent}/chatMessages]
- **Google SecOps case chat messages pin message** (Action). Pins a specific ChatMessage to the Case wall. Use this method to highlight important messages in the case history. Required: case_id, chat_message_id. [POST /v1/{name}:pinMessage]
- **Google SecOps case chat messages unpin message** (Action). Unpins a pinned ChatMessage from the Case wall. Required: case_id, chat_message_id. [POST /v1/{name}:unpinMessage]
- **Google SecOps case chat messages unread messages count** (Action). Returns the number of ChatMessages in the Case chat that the current user has not yet read. Required: case_id. [GET /v1/{parent}/chatMessages:unreadMessagesCount]
- **Create a Google SecOps case close definition** (Create). Creates a new CaseCloseDefinition. Use this method to add a new pairing of root cause and reason to the system. Similar root cause and reason combinations cannot be duplicated. Returns a CaseCloseDefinition. Required: closeReason, rootCause. [POST /v1/{parent}/caseCloseDefinitions]
- **Delete a Google SecOps case close definition by ID** (Delete). Deletes a CaseCloseDefinition. Use this method to remove an obsolete or incorrect case closure definition from the system. The id is the case close definition ID (last segment of its resource name). Required: id. [DELETE /v1/{name}]
- **Get single Google SecOps case close definition by ID** (Get). Gets a single CaseCloseDefinition by its resource name. Use this method to retrieve the detailed reason and root cause content of a definition. The id is the case close definition ID (last segment of its resource name). Returns a CaseCloseDefinition. Required: id. [GET /v1/{name}]
- **List all Google SecOps case close definitions** (List). Lists all CaseCloseDefinitions. Use this method to discover the available root cause and reason pairings for case closure. Supports filtering by reason or root cause. [GET /v1/{parent}/caseCloseDefinitions]
- **Update a Google SecOps case close definition by ID** (Update). Updates an existing CaseCloseDefinition. Use this method to modify the root cause description or the associated reason for a definition. The id is the case close definition ID (last segment of its resource name). Returns a CaseCloseDefinition. Required: id, closeReason, rootCause. [PATCH /v1/{caseCloseDefinition.name}]
- **Create a Google SecOps case comment** (Create). Creates a new CaseComment. Use this method to add investigative notes or collaborate with other analysts. Comments can optionally include base64 encoded attachments. Returns a CaseComment. Required: case_id, comment. [POST /v1/{parent}/caseComments]
- **Delete a Google SecOps case comment by ID** (Delete). Performs a soft delete of a CaseComment. Use this method to remove the comment's content from general view while preserving its metadata for audit purposes. The id is the case comment ID (last segment of its resource name). Required: id, case_id. [DELETE /v1/{name}]
- **Get single Google SecOps case comment by ID** (Get). Gets a single CaseComment by its resource name. Use this method to retrieve the content and metadata of a specific comment. The id is the case comment ID (last segment of its resource name). Returns a CaseComment. Required: id, case_id. [GET /v1/{name}]
- ...and 523 more tools. Call `tools/list` via the MCP endpoint, or see the full catalog via the API, for the complete set.
