mcp-oci
MCP server for Oracle Cloud (OCI) — live resource discovery, dependency mapping, and Terraform generation, with security modes and access-control flags.
Documentation
mcp-oci
A Model Context Protocol server for Oracle Cloud Infrastructure (OCI). It gives an MCP-capable client (Claude Desktop, Claude Code, Cursor, Copilot, …) the ability to discover live OCI resources, map how they relate, and generate reproducible Terraform — with behaviour controlled entirely by flags.
Think of it as a Playwright-MCP for your cloud: instead of rebuilding infrastructure knowledge by hand, the model can ask *"show all VCNs in the prod compartment"* and *"generate Terraform for this compartment"* and get structured, secret-free answers.
Features
- Live discovery — compartments, regions, and any resource via OCI Resource Search.
- Terraform generation — faithful HCL for known types (VCN, subnet, instance, bucket, compartment) and annotated skeletons for the rest; whole-compartment modules with provider variables.
- Dependency graph — nodes/edges plus a suggested provisioning order (dependencies first).
- Secrets never reach the model — every payload is redacted before return.
- Security flags — access modes, compartment/region allowlists, provisioning gate, dry-run, and JSON audit logging (see below).
- Standard auth — OCI config file (`~/.oci/config`) or instance principals. No credentials stored by the server.
Security model
| Concern | Flag | Default | Effect |
|---|---|---|---|
| What can the server do? | `OCI_MODE` | `read-only` | All shipped tools are read-only. `read-write`/`admin` are reserved for future provisioning and currently expose no extra tools. |
| Which compartments are in scope? | `OCI_COMPARTMENT_ALLOWLIST` | *(all)* | When set, operations on other compartments are refused. |
| Which regions are reachable? | `OCI_REGION_ALLOWLIST` | *(configured region)* | When set, only these regions may be targeted. |
| Can it run `terraform apply`? | `OCI_ALLOW_APPLY` | `false` | Reserved gate for provisioning (not yet shipped). |
| Preview without executing | `OCI_DRY_RUN` | `false` | For future write tools: validate + log intent without executing. |
| Audit trail | `OCI_AUDIT_LOG` | `true` | Emits a JSON line to stderr per guarded operation. |
| Secret redaction | *(always on)* | — | Secret-shaped fields are replaced with `*REDACTED*` before any result is returned. |
Tools
Discovery (read): `list_compartments`, `list_regions`, `search_resources`, `list_compartment_resources`, `get_resource`
Terraform (read): `generate_terraform`, `generate_compartment_terraform`, `build_dependency_graph`
Quickstart — add to your agent
Published on npm as `@dockndevai/mcp-oci`. No clone or build needed — your MCP client runs it on demand with `npx`. Start in `read-only` mode; see `.env.example` for every variable and docs/CLIENTS.md for the full per-client guide.
Claude Code (CLI)
claude mcp add oci -e OCI_PROFILE="DEFAULT" -e OCI_MODE="read-only" -- npx -y @dockndevai/mcp-ociClaude Desktop · Cursor · Windsurf — same block in `claude_desktop_config.json`, `.cursor/mcp.json`, or `~/.codeium/windsurf/mcp_config.json`:
{
"mcpServers": {
"oci": {
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-oci"
],
"env": {
"OCI_PROFILE": "DEFAULT",
"OCI_MODE": "read-only"
}
}
}
}OpenAI Codex CLI — in `~/.codex/config.toml`:
[mcp_servers.oci]
command = "npx"
args = ["-y", "@dockndevai/mcp-oci"]
env = { OCI_PROFILE = "DEFAULT", OCI_MODE = "read-only" }VS Code (GitHub Copilot, Agent mode) — in `.vscode/mcp.json`:
{
"servers": {
"oci": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@dockndevai/mcp-oci"
],
"env": {
"OCI_PROFILE": "DEFAULT",
"OCI_MODE": "read-only"
}
}
}
}Configure
Point it at a standard OCI config profile. For safety, use an IAM user/policy with
read-only (`inspect`/`read`) permissions on the compartments you want the agent to see.
Example prompts
- *"List all compartments, then show every resource in the `prod` compartment."*
- *"Generate Terraform for VCN `ocid1.vcn.oc1..…`."*
- *"Build a dependency graph for compartment `…` and tell me the provisioning order."*
Run from source (development)
Prefer the published package above. To run from a clone:
npm install
npm run build
node dist/index.js # with the environment variables setDevelop
npm run dev # watch mode
npm test # security policy + terraform generation + graph + redaction
npm run typecheckRoadmap
- `terraform plan` / `apply` execution behind `read-write`/`admin` + `OCI_ALLOW_APPLY`.
- More resource-type mappers (load balancers, databases, DRGs, IAM policies).
- Cross-environment drift comparison.
Publishing
This server ships a `server.json` for the official MCP registry and an `mcpName` for npm ownership validation. See **PUBLISHING.md** for publishing to npm and listing on the MCP registry, Smithery, Glama, Cursor, and PulseMCP.
License
MIT
Frequently asked questions
What is mcp-oci?
mcp-oci is MCP server for Oracle Cloud (OCI) — live resource discovery, dependency mapping, and Terraform generation, with security modes and access-control flags.
How do I install mcp-oci?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-oci open source?
Yes — it is hosted on GitHub at https://github.com/dockndevai/mcp-oci and has 1 stars.
Related MCP tools
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
MCP Aggregator, Orchestrator, Middleware, Gateway in one docker
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP