Meta tags:
description=Learn how to use the Memorystore for Redis Cluster remote MCP server to manage backups and clusters in Memorystore for Redis Cluster.;

Headings (most frequently used words):

mcp, and, cluster, for, you, memorystore, redis, from, the, remote, with, google, use, your, servers, why, do, region, model, armor, to, applications, server, cloud, authentication, configure, tools, required, iam, in, specific, how, can, data, connect, ai, by, using, stay, organized, collections, save, categorize, content, based, on, preferences, what, difference, between, local, before, begin, authorization, oauth, scope, an, client, available, sample, cases, optional, security, safety, configurations, roles, list, create, regional, enabled, view, all, active, clusters, retrieve, connection, endpoints, operational, metadata, optimize, intensive, protect, failures, that, might, occur, either, or, where, it, located, console, gcloud, control, deny, policies, products, pricing, support, resources, engage, permissions, enable, protection, deactivate, scanning, traffic,

Text of the page (most frequently used words):
the (159), and (91), mcp (91), for (80), you (72), cluster (61), redis (56), google (49), project (46), cloud (43), memorystore (39), #server (34), model (32), armor (30), create (30), with (29), use (28), your (25), roles (25), can (24), about (23), information (23), enable (21), servers (20), that (20), clusters (18), see (17), more (16), required (16), tools (16), this (15), remote (15), resources (14), applications (14), following (14), iam (14), gcloud (14), using (14), access (13), tool (13), service (13), list (13), manage (12), application (12), settings (12), update (12), security (12), authentication (12), get (12), how (11), connect (11), cli (11), from (11), data (11), permissions (11), api (10), oauth (10), client (10), floor (10), need (9), enabled (9), identity (9), these (9), set (9), select (9), usage (9), role (9), serviceusage (9), all (8), are (8), agent (8), have (8), services (8), region (8), apis (8), maintenance (8), specific (8), delete (8), instance (8), code (7), thumb (7), policies (7), management (7), configure (7), projects (7), run (7), command (7), console (7), overview (7), content (6), safety (6), setting (6), note (6), admin (6), grant (6), supported (6), new (6), uses (6), scope (6), user (6), users (6), vpc (6), sign (5), samples (5), control (5), make (5), traffic (5), doesn (5), might (5), enforcement (5), want (5), shell (5), which (5), contains (5), permission (5), learn (5), backup (5), scale (5), count (5), http (5), multiple (5), networking (5), search (5), persistence (5), cross (5), architecture (4), products (4), other (4), down (4), backups (4), when (4), based (4), any (4), project_id (4), uri (4), filter (4), type (4), responses (4), filters (4), different (4), calls (4), where (4), googleapis (4), com (4), endpoint (4), already (4), serviceusageadmin (4), available (4), logs (4), external (4), regional (4), then (4), capacity (4), view (4), credentials (4), guidance (4), existing (4), guide (4), selector (4), selecting (4), resourcemanager (4), guides (4), commands (4), vector (4), instances (4), support (3), sample (3), updated (3), page (3), details (3), registered (3), send (3), protocol (3), custom (3), development (3), read (3), deny (3), help (3), secure (3), scanning (3), across (3), integrated (3), replace (3), automatically (3), global (3), prompts (3), add (3), logging (3), resource (3), don (3), prompt (3), protect (3), https (3), installed (3), take (3), initialize (3), activate (3), before (3), steps (3), must (3), risks (3), practices (3), verify (3), shard (3), retrieve (3), why (3), centralized (3), require (3), their (3), reference (3), authenticate (3), agents (3), authorization (3), policy (3), managed (3), infrastructure (3), between (3), local (3), databases (3), monitoring (3), monitor (3), cmek (3), encryption (3), certificate (3), authority (3), replication (3), quickstart (3), product (3), 한국어 (2), 日本語 (2), עברית (2), português (2), brasil (2), italiano (2), indonesia (2), français (2), español (2), américa (2), latina (2), deutsch (2), english (2), our (2), action (2), terms (2), site (2), youtube (2), started (2), system (2), pricing (2), understand (2), last (2), 2026 (2), utc (2), licensed (2), under (2), its (2), license (2), feedback (2), context (2), claude (2), environments (2), features (2), like (2), principal (2), example (2), general (2), configuration (2), just (2), apply (2), floorsettings (2), full (2), google_mcp_server (2), locations (2), floorsetting (2), confidence (2), responsible (2), dangerous (2), values (2), medium_and_above (2), match (2), inspect_and_block (2), malicious (2), both (2), language (2), protection (2), location (2), modelarmor (2), session (2), environment (2), current (2), begin (2), behavior (2), call (2), sensitive (2), llm (2), prevent (2), input (2), governance (2), actions (2), optional (2), configurations (2), such (2), discovery (2), replica (2), connection (2), endpoints (2), operational (2), creating (2), workloads (2), cases (2), json (2), method (2), connecting (2), enter (2), single (2), isn (2), keys (2), also (2), predefined (2), mcppolicy (2), viewer (2), init (2), provider (2), idp (2), first (2), federated (2), previously (2), sure (2), latest (2), version (2), running (2), components (2), install (2), created (2), complete (2), plan (2), keep (2), procedure (2), instead (2), after (2), finish (2), removing (2), associated (2), creator (2), projectcreator (2), been (2), granted (2), account (2), free (2), controls (2), audit (2), communication (2), documentation (2), sdk (2), languages (2), frameworks (2), costs (2), storage (2), observability (2), migration (2), industry (2), solutions (2), distributed (2), hybrid (2), multicloud (2), analytics (2), pipelines (2), compute (2), hosting (2), high (2), issues (2), troubleshoot (2), metrics (2), info (2), rdb (2), aof (2), customer (2), shared (2), transit (2), library (2), networks (2), connections (2), network (2), best (2), technology (2), areas (2), close (2), subscribe, newsletter, third, decade, climate, join, cookies, privacy, tech, twitter, events, blog, engage, training, certification, center, getting, github, status, release, notes, community, forums, contact, sales, marketplace, easy, easytounderstand, solved, problem, solvedmyproblem, otherup, hard, hardtounderstand, incorrect, incorrectinformationorsamplecode, missing, missingtheinformationsamplesineed, otherdown, tell, except, otherwise, noted, java, trademark, oracle, affiliates, developers, apache, creative, commons, attribution, document, shows, including, gemini, chatgpt, developing, lets, platforms, benefits, properties, only, allow, block, unwanted, impact, than, because, integrates, vertex, changes, affect, behaviors, not, rules, defined, remove, stop, deactivate, level, modify, though, lower, result, false, positives, levels, enables, inspects, blocks, true, rai, confidencelevel, filtertype, case, invoked, twice, once, each, sanitization, injection, jailbreak, unless, carries, natural, tip, defines, minimum, applies, consistent, within, config, api_endpoint_overrides, rep, bottom, starts, displays, line, few, seconds, follow, jurisdiction, routing, individual, certain, regions, caution, entire, payload, expose, designed, enhance, works, proactively, screening, protecting, against, various, supporting, whether, deploying, providers, maintain, compliance, enforce, consistently, diverse, landscape, introduces, considerations, due, wide, variety, minimize, offers, default, customizable, organization, failure, occurs, restore, resume, operations, backup_cluster, failures, occur, either, located, increase, cpu, memory, throughput, significantly, increasing, update_cluster, optimize, intensive, integration, get_cluster, metadata, listing, ensure, formatted, specified, list_clusters, active, eliminates, static, passwords, favor, short, lived, highly, create_cluster, post, host, jsonrpc, request, directly, inspector, descriptions, depending, secret, transport, url, name, look, way, antigravity, instantiate, connects, clients, listed, most, www, auth, write, description, has, determine, authenticated, authorized, scopes, recommend, separate, controlled, monitored, accepts, identities, able, clone, contain, exact, expand, section, granting, folders, organizations, tooluser, ask, administrator, evaluate, perform, real, world, scenarios, customers, 300, credits, test, deploy, response, fine, grained, simplified, offer, typically, machine, standard, output, streams, stdio, same, device, what, difference, standardizes, large, models, llms, sources, let, backend, save, categorize, preferences, stay, organized, collections, home, utilization, expensive, address, health, self, simulate, find, windows, build, powered, langchain, integrate, technologies, limitations, query, syntax, indexing, vectors, dropindex, _list, generative, back, constraints, per, basic, token, deletion, work, secondary, scaling, terraform, provisioned, vpcs, provisioning, blocked, guidelines, node, specification, zone, availability, replicas, discover, start, skip, main,

Text of the page (random words):
ion hosting compute data analytics and pipelines databases distributed hybrid and multicloud industry solutions migration networking observability and monitoring security storage access and resources management costs and usage management infrastructure as code sdk languages frameworks and tools home documentation databases memorystore memorystore for redis cluster guides send feedback connect to memorystore for redis cluster from ai applications by using the remote mcp server stay organized with collections save and categorize content based on your preferences this document shows you how to use the memorystore for redis cluster remote model context protocol mcp server to connect with ai applications including gemini cli chatgpt claude and custom applications you are developing the memorystore for redis cluster remote mcp server lets you manage clusters and backups in memorystore for redis cluster from your ai enabled development environments and ai agent platforms the memorystore for redis cluster remote mcp server is enabled when you enable the memorystore for redis cluster api model context protocol mcp standardizes how large language models llms and ai applications or agents connect to external data sources mcp servers let you use their tools resources and prompts to take actions and get updated data from their backend service what s the difference between local and remote mcp servers local mcp servers typically run on your local machine and use the standard input and output streams stdio for communication between services on the same device remote mcp servers run on the service s infrastructure and offer an http endpoint to ai applications for communication between the ai mcp client and the mcp server for more information about mcp architecture see mcp architecture google and google cloud remote mcp servers google and google cloud remote mcp servers have the following features and benefits simplified centralized discovery managed global or regional http endpoints fine grained authorization optional prompt and response security with model armor protection centralized audit logging for information about other mcp servers and information about security and governance controls available for google cloud mcp servers see google cloud mcp servers overview before you begin sign in to your google cloud account if you re new to google cloud create an account to evaluate how our products perform in real world scenarios new customers also get 300 in free credits to run test and deploy workloads in the google cloud console on the project selector page select or create a google cloud project roles required to select or create a project select a project selecting a project doesn t require a specific iam role you can select any project that you ve been granted a role on create a project to create a project you need the project creator role roles resourcemanager projectcreator which contains the resourcemanager projects create permission learn how to grant roles note if you don t plan to keep the resources that you create in this procedure create a project instead of selecting an existing project after you finish these steps you can delete the project removing all resources associated with the project go to project selector if you re using an existing project for this guide verify that you have the permissions required to complete this guide if you created a new project then you already have the required permissions enable the memorystore for redis cluster api roles required to enable apis to enable apis you need the service usage admin iam role roles serviceusage serviceusageadmin which contains the serviceusage services enable permission learn how to grant roles enable the api install the google cloud cli note if you installed the gcloud cli previously make sure you have the latest version by running gcloud components update if you re using an external identity provider idp you must first sign in to the gcloud cli with your federated identity to initialize the gcloud cli run the following command gcloud init in the google cloud console on the project selector page select or create a google cloud project roles required to select or create a project select a project selecting a project doesn t require a specific iam role you can select any project that you ve been granted a role on create a project to create a project you need the project creator role roles resourcemanager projectcreator which contains the resourcemanager projects create permission learn how to grant roles note if you don t plan to keep the resources that you create in this procedure create a project instead of selecting an existing project after you finish these steps you can delete the project removing all resources associated with the project go to project selector if you re using an existing project for this guide verify that you have the permissions required to complete this guide if you created a new project then you already have the required permissions enable the memorystore for redis cluster api roles required to enable apis to enable apis you need the service usage admin iam role roles serviceusage serviceusageadmin which contains the serviceusage services enable permission learn how to grant roles enable the api install the google cloud cli note if you installed the gcloud cli previously make sure you have the latest version by running gcloud components update if you re using an external identity provider idp you must first sign in to the gcloud cli with your federated identity to initialize the gcloud cli run the following command gcloud init required roles to get the permissions that you need to use the memorystore for redis cluster mcp server ask your administrator to grant you the following iam roles on the project where you want to use the memorystore for redis cluster mcp server make mcp tool calls mcp tool user roles mcp tooluser create a cluster in memorystore for redis cluster redis admin roles redis admin get a cluster or list all clusters in a project redis viewer roles redis viewer manage service usage policies service usage admin roles serviceusage serviceusageadmin for more information about granting roles see manage access to projects folders and organizations these predefined roles contain the permissions required to use the memorystore for redis cluster mcp server to see the exact permissions that are required expand the required permissions section required permissions the following permissions are required to use the memorystore for redis cluster mcp server get information about a service usage policy serviceusage mcppolicy get update a service usage policy serviceusage mcppolicy update make mcp tool calls mcp tools call create a cluster redis clusters create list clusters redis clusters list get information about a cluster redis clusters get clone a cluster redis clusters create update a cluster redis clusters update backup a cluster redis clusters backup delete a cluster redis clusters delete create a user redis users create list users redis users list get information about a user redis users get update a user redis users update delete a user redis users delete you might also be able to get these permissions with custom roles or other predefined roles authentication and authorization memorystore for redis cluster mcp servers use the oauth 2 0 protocol with identity and access management iam for authentication and authorization all google cloud identities are supported for authentication to mcp servers the memorystore for redis cluster remote mcp server accepts api keys we recommend creating a separate identity for agents using mcp tools so that access to resources can be controlled and monitored for more information on authentication see authenticate to google and google cloud mcp servers memorystore for redis cluster mcp oauth scope oauth 2 0 uses a scope and credentials to determine if an authenticated principal is authorized to take a specific action on a resource for more information about oauth 2 0 scopes at google read using oauth 2 0 to access google apis memorystore for redis cluster has the following mcp tool oauth scope scope uri description https www googleapis com auth redis read write create list backup update and delete clusters configure an mcp client to use the memorystore for redis cluster mcp server ai applications and agents such as claude or antigravity can instantiate an mcp client that connects to a single mcp server an ai application can have multiple clients that connect to different mcp servers if your application isn t listed in the client specific guidance then you can use the following information to connect from most applications in your ai application look for a way to add or connect to a remote mcp server for the memorystore for redis cluster mcp server enter the following information as required server name memorystore for redis cluster mcp server server url or endpoint https redis googleapis com mcp transport http authentication details depending on how you want to authenticate you can enter your google cloud credentials your oauth client id and secret or an agent identity and credentials for more information on authentication see authenticate to google and google cloud mcp servers oauth scope the oauth 2 0 scope that you want to use when connecting to the memorystore for redis cluster mcp server for application specific guidance about setting up and connecting to mcp server see client specific guidance for more general guidance see the following resources connect to remote mcp servers configure mcp in an ai application available tools to view details of available mcp tools and their descriptions for the memorystore for redis cluster mcp server see the memorystore for redis cluster mcp reference list tools use the mcp inspector to list tools or send a tools list http request directly to the memorystore for redis cluster remote mcp server the tools list method doesn t require authentication post mcp http 1 1 host redis googleapis com content type application json jsonrpc 2 0 method tools list sample use cases the following are sample use cases for the memorystore for redis cluster mcp server why do you create a regional cluster with iam authentication enabled creating this type of cluster eliminates static passwords in favor of centralized short lived credentials for highly secure regional workloads the ai agent of the memorystore for redis cluster mcp server uses the create_cluster mcp tool to create the cluster why do you view all active clusters in a specific region by listing these clusters you can ensure that resources match your current architecture the ai agent of the memorystore for redis cluster mcp server uses the list_clusters mcp tool to retrieve a formatted list of clusters in the specified region why do you retrieve connection endpoints and operational metadata from a cluster in a specific region you need this information for application integration and system maintenance the ai agent of the memorystore for redis cluster mcp server uses the get_cluster mcp tool to retrieve information about the cluster such as its discovery endpoint shard count and replica count how can you optimize memorystore for redis cluster for your data intensive applications to increase both the cpu capacity and the memory throughput for these applications significantly you can scale a cluster by increasing the cluster s shard count the ai agent of the memorystore for redis cluster mcp server uses the update_cluster mcp tool to update the shard count for the cluster how can you protect your data from failures that might occur from either a cluster or the region where it s located create a backup of the cluster if a regional or cluster failure occurs then you can restore your data to a new cluster to resume operations the ai agent of the memorystore for redis cluster mcp server uses the backup_cluster mcp tool to create a backup of the cluster optional security and safety configurations mcp introduces new security risks and considerations due to the wide variety of actions that you can do with the mcp tools to minimize and manage these risks google cloud offers default settings and customizable policies to control the use of mcp tools in your google cloud organization or project for more information about mcp security and governance see ai security and safety use model armor model armor is a google cloud service designed to enhance the security and safety of your ai applications it works by proactively screening llm prompts and responses protecting against various risks and supporting responsible ai practices whether you are deploying ai in your cloud environment or on external cloud providers model armor can help you prevent malicious input verify content safety protect sensitive data maintain compliance and enforce your ai safety and security policies consistently across your diverse ai landscape when model armor is enabled with logging enabled model armor logs the entire payload this might expose sensitive information in your logs caution model armor is available in certain regions when model armor is enabled and you use an mcp server in a jurisdiction that model armor doesn t support the routing behavior of the call might be different for different mcp servers for more information about the behavior of individual mcp servers see model armor supported products enable model armor you must enable model armor apis before you can use model armor console enable the model armor api roles required to enable apis to enable apis you need the service usage admin iam role roles serviceusage serviceusageadmin which contains the serviceusage services enable permission learn how to grant roles enable the api select the project where you want to activate model armor gcloud before you begin follow these steps using the google cloud cli with the model armor api in the google cloud console activate cloud shell activate cloud shell at the bottom of the google cloud console a cloud shell session starts and displays a command line prompt cloud shell is a shell environment with the google cloud cli already installed and with values already set for your current project it can take a few seconds for the session to initialize run the following command to set the api endpoint for the model armor service gcloud config set api_endpoint_overrides modelarmor https modelarmor location rep googleapis com replace location with the region where you want to use model armor configure protection for google and google cloud remote mcp servers to help protect your mcp tool calls and responses you can use model armor floor settings a floor setting defines the minimum security filters that apply across the project this configuration applies a consistent set of filters to all mcp tool calls and responses within the project tip don t enable the prompt injection and jailbreak filter unless your mcp traffic carries natural language data set up a mod...