// SCAN REPORT

Oci

19 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 3 Jul 2026

0 can modify or destroy data

19 read-only

19 tools total

Community server · catalogue entry verified 03/07/2026

How to control Oci ↓

TOOL MAP

What Oci exposes to your agents

Read (19) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control Oci

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

Cap read operations

{
  "get_bucket": {
    "limits": [
      {
        "counter": "get_bucket_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 Oci — 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 OCI →

Instant setup, no code required.

FULL CATALOGUE

All 19 Oci tools

READ 19 tools

Read get_bucket Get metadata for a specific bucket: storage tier, versioning, replication, access type. Read get_instance Get full details of a compute instance by its OCID. Read get_object_storage_namespace Get the Object Storage namespace for this tenancy. Required for bucket operations. Read get_oke_cluster Get full details for an OKE cluster including endpoint config, add-ons, and node pool summary. Read get_tenancy Get details about the OCI tenancy: name, OCID, home region, and description. Read list_availability_domains List availability domains in a compartment (defaults to root tenancy). Read list_buckets List Object Storage buckets in a compartment. Read list_cluster_options List Kubernetes versions and shapes available for new OKE clusters in a compartment. Read list_compartments List active OCI compartments. Defaults to top-level compartments under the root tenancy. Read list_instances List compute instances in a compartment. Read list_internet_gateways List internet gateways attached to a VCN. Read list_node_pools List OKE node pools in a compartment. Read list_objects List objects in an Object Storage bucket. Read list_oke_clusters List Oracle Container Engine for Kubernetes (OKE) clusters in a compartment. Read list_regions List all OCI regions the tenancy is subscribed to, marking the home region. Read list_security_lists List security lists for a given VCN, showing ingress/egress rule counts. Read list_shapes List compute shapes available in a compartment, grouped by family. Read list_subnets List subnets in a compartment. Read list_vcns List Virtual Cloud Networks (VCNs) in a compartment.

FAQ

Questions about Oci

Is the Oci MCP server safe to use without restrictions? +

The Oci server is primarily read-only with 19 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Oci MCP server expose? +

19 tools across 1 categories: Read. 19 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on Oci? +

Register the Oci 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 Oci tool call.

Deterministic rules across all 19 Oci tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON OCI →

Instant setup, no code required.

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