// SCAN REPORT

RedisNexus

169 tools. 83 can modify or destroy data without limits.

22 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

83 can modify or destroy data

86 read-only

169 tools total

Community server · catalogue entry verified 03/07/2026

How to control RedisNexus ↓

TOOL MAP

What RedisNexus exposes to your agents

Read (86) Write / Execute (61) Destructive / Financial (22)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous RedisNexus tools

Destructive · Critical argocd_apps The tool explicitly supports 'delete' and 'rollback' operations on ArgoCD applications, which are irreversible or highly impactful actions in a production environment. Destructive · High argocd_repos The tool supports 'remove' operations on ArgoCD repositories, which is an irreversible destructive action. Destructive · Critical aws_s3 Although this tool performs multiple operations (list, browse, check size, create), the ability to delete S3 buckets makes it Destructive rather than Write. Destructive · Critical az_vm The delete action cannot be undone and results in permanent loss of infrastructure.

83 of RedisNexus's 169 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control RedisNexus

PolicyLayer is an MCP gateway — it sits between your AI agents and RedisNexus, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "argocd_apps": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "argocd_projects": {
    "limits": [
      {
        "counter": "argocd_projects_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "argocd_clusters": {
    "limits": [
      {
        "counter": "argocd_clusters_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register RedisNexus — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON REDISNEXUS →

Instant setup, no code required.

FULL CATALOGUE

All 169 RedisNexus tools

DESTRUCTIVE 22 tools

Destructive argocd_apps Manage ArgoCD applications: list, get, sync, diff, history, rollback, delete. Destructive argocd_repos Manage ArgoCD repositories: list, add, remove. Destructive aws_s3 Manage S3 buckets: list, browse objects, check size, create, delete. Destructive az_vm Manage Azure Virtual Machines — list, show, start, stop, deallocate, restart, delete. Destructive docker_images Manage Docker images: list, pull, remove, inspect, prune unused, view history. Destructive docker_networks Manage Docker networks: list, create, inspect, remove. Destructive docker_system Docker system info, disk usage, and system prune. Destructive docker_volumes Manage Docker volumes: list, create, inspect, remove, prune unused. Destructive es_document Index, get, update, delete individual documents or bulk index. Destructive es_index Manage Elasticsearch indexes: list, create, delete, stats, mappings. Destructive gcp_compute Manage GCP Compute Engine — list, describe, start, stop, delete instances, list disks. Destructive gcp_storage Manage Google Cloud Storage — list buckets, objects, create/delete buckets. Destructive gh_releases Manage GitHub releases: list, view, create, delete. Destructive git_branch Manage git branches: create, delete, checkout, merge, rebase. Destructive glab_releases Manage GitLab releases: list, view, create, delete. Destructive k8s_namespaces Manage Kubernetes namespaces: list, create, delete, describe. Destructive mongo_collection Manage collections: list, create, drop, stats, indexes, schema analysis. Destructive mongo_databases List, inspect, or drop MongoDB databases. Destructive redis_delete Delete one or more Redis keys. Requires explicit confirmation (confirm=True). Destructive rmq_queue_delete Delete a queue entirely or purge all its messages. Requires confirmation. Destructive vault_pki Manage PKI certificates: issue, list, revoke, and view CA info. Destructive vault_secret Manage Vault secrets: read, write, delete, list. Supports KV v2 secrets engine.

EXECUTE 23 tools

Execute argocd_sync Sync an ArgoCD application with fine-grained control: prune, dry-run, force. Execute aws_ec2 Manage EC2 instances: list, describe, start, stop, terminate, security groups. Execute aws_lambda Manage Lambda functions: list, describe, invoke, view logs. Execute docker_container_action Perform actions on containers: start, stop, restart, pause, kill, remove, inspect, top, stats. Execute gh_actions Manage GitHub Actions: list runs, view run details, trigger, cancel, rerun, view logs. Execute glab_pipelines Manage GitLab CI/CD pipelines: list, view, trigger, cancel, retry, delete. Execute k8s_apply Apply a YAML manifest to the cluster. Supports dry_run mode for safe preview. Execute k8s_deployment Manage Kubernetes deployments: inspect, scale, restart, rollback. Execute k8s_exec Execute a command inside a running pod container. Execute k8s_helm Manage Helm releases: list, install, upgrade, uninstall, status, history, rollback. Execute k8s_nodes List cluster nodes with status, capacity, and resource usage. Cordon/uncordon/drain nodes. Execute kafka_produce Produce messages to a Kafka topic with optional key, headers, and partition. Execute nginx_ssl_manage SSL certificate management: generate self-signed, certbot commands, check expiry. Execute nginx_test_config Test Nginx configuration syntax without applying. Execute pg_connections Manage PostgreSQL connections: list active, kill idle, view stats. Execute pg_query Execute a SQL query against PostgreSQL. Supports SELECT, INSERT, UPDATE, DELETE. Execute prom_query Execute instant or range PromQL queries against Prometheus. Execute redis_pipeline_execute Execute multiple Redis commands in a single pipeline for maximum performance. Execute rmq_consume rmq_consume Execute sys_cron Manage cron jobs: list, add, remove, and AI-generate cron expressions. Execute sys_service Manage systemd services: list, status, start, stop, restart, enable, disable, logs. Execute tf_apply Apply Terraform changes. Requires confirmation. Execute tf_plan Run terraform plan to preview infrastructure changes.

WRITE 38 tools

Write argocd_projects Manage ArgoCD projects: list, get details, create. Write aws_eks Inspect EKS clusters: list, describe, nodegroups, update kubeconfig. Write az_storage Manage Azure Storage — accounts, containers, blobs. Write gcp_gke Manage Google Kubernetes Engine — list clusters, describe, get credentials, nodepools. Write gh_issues Manage GitHub issues: list, view, create, close, reopen, comment, edit. Write gh_pull_requests Manage pull requests: list, view, create, merge, close, reopen, review, diff, checks. Write gh_repos Manage GitHub repositories: list, view, create, clone, fork. Write git_cicd_generate Generate production-ready CI/CD pipelines for GitHub Actions, GitLab CI, Jenkins, or Bitbucket. Write git_commit_msg_generate AI-generated commit message based on staged changes. Write git_hook_generate Generate git hooks for pre-commit, commit-msg, pre-push quality gates. Write glab_issues Manage GitLab issues: list, view, create, close, reopen, comment. Write glab_merge_requests Manage GitLab merge requests: list, view, create, merge, close, reopen, approve, diff. Write glab_projects Manage GitLab projects: list, view, create, fork. Write jira_issues Manage Jira issues: search by JQL, view details, create, update, transition status, add comments, and assign. Write kafka_topic_create Create a Kafka topic with configurable partitions, replication, retention, and cleanup policy. Write nginx_config_generate Generate production-ready Nginx configuration with load balancing, SSL, rate limiting, Write prom_alert_rule_generate Generate PrometheusRule YAML for common alert patterns. Write prom_dashboard_generate Generate PromQL queries for a Grafana dashboard based on service type. Write redis_hash_set Set multiple fields in a Redis Hash. Hashes are ideal for storing structured Write redis_list_push Push values to a Redis List. Use 'left' for LPUSH (stack/queue head) Write redis_publish Publish a message to a Redis Pub/Sub channel. Subscribers listening on Write redis_set redis_set Write redis_sorted_set_add Add members with scores to a Redis Sorted Set. Ideal for leaderboards, Write redis_stream_add Add an entry to a Redis Stream. Streams are append-only logs ideal for Write redis_tenant_ops Multi-tenant Redis operations for SaaS platforms. Manages per-tenant Write rmq_binding_create rmq_binding_create Write rmq_dead_letter Manage dead letter queues (DLQ). Set up DLQ infrastructure, inspect Write rmq_exchange_create Create a new exchange. Types: direct (exact routing key match), fanout (broadcast), Write rmq_policy_set Create or update a RabbitMQ policy. Policies apply configurations to Write rmq_publish Publish a message to an exchange with routing key. The exchange routes Write rmq_queue_create Create a new RabbitMQ queue with configurable durability, TTL, max-length, Write rmq_vhost_manage Manage RabbitMQ virtual hosts for multi-tenant isolation. Write sys_process Manage processes: list top consumers, find by name, kill by PID. Write tf_module_generate Generate production-ready Terraform modules for common AWS resources. Write tf_workspaces Manage Terraform workspaces: list, create, select. Write vault_auth Manage Vault authentication methods: list, enable, disable. Write vault_policy Manage Vault policies. AI can generate least-privilege policies for services. Write vault_rotate_secret Rotate a secret by writing new values. Creates a new version in KV v2.

READ 86 tools

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about RedisNexus

Can an AI agent delete data through the RedisNexus MCP server? +

Yes. The RedisNexus server exposes 22 destructive tools including argocd_apps, argocd_repos, aws_s3. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through RedisNexus? +

The RedisNexus server has 38 write tools including argocd_projects, aws_eks, az_storage. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach RedisNexus.

How many tools does the RedisNexus MCP server expose? +

169 tools across 4 categories: Destructive, Execute, Read, Write. 86 are read-only. 83 can modify, create, or delete data.

How do I enforce a policy on RedisNexus? +

Register the RedisNexus MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every RedisNexus tool call.

Deterministic rules across all 169 RedisNexus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON REDISNEXUS →

Instant setup, no code required.

169 RedisNexus tools catalogued and risk-classified — across an index of 43,000+ MCP servers.