ORAS MCP Server
The ORAS MCP Server enables AI assistants to interact with OCI registries and container registries to query and analyze container images, artifacts, and their associated metadata.
List well-known registries: Discover public registries that support catalog functionality
Browse repositories: Enumerate all repositories available in a specific registry
Explore image tags: Retrieve all tags within a repository
Analyze referrers: Identify artifacts that reference a specific container image or OCI artifact (such as signatures or SBOMs)
Fetch manifests: Retrieve detailed manifest information for images and artifacts by tag or digest
Access blob content: Download specific blob data (like image layers or configuration files) referenced by digest
Parse references: Break down container reference strings into their component parts (registry, repository, tag, digest)
This server is particularly useful for understanding container image metadata, platform support, signatures, and artifact relationships across various container registries.
Supports working with CNCF Notary signatures for container images, allowing verification of image authenticity and integrity.
Provides tools for running the ORAS MCP Server inside a Docker container, making deployment and execution straightforward without local installation requirements.
Enables interaction with GitHub Container Registry (ghcr.io) to retrieve and analyze container images and their metadata.
Provides capabilities to analyze Linux-based container images across multiple architectures including amd64, arm64, arm/v7, s390x, and ppc64le.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ORAS MCP Server what platforms does the image ghcr.io/oras-project/oras support?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ORAS MCP Server
Usage
Configure the ORAS MCP Server to run inside VS Code agent mode for registry-aware chats.
The server is implemented with the oras-go library and does not depend on the oras CLI.
Setup with Docker
It is easier to use docker to run the ORAS MCP Server.
Setup for VS Code
Add the following code to .vscode/mcp.json:
{
"servers": {
"oras-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"ghcr.io/oras-project/oras-mcp:main",
"serve"
]
}
}
}Mount Docker credentials (Linux only)
Linux users can share docker login credentials by mounting the config file:
{
"servers": {
"oras-mcp-server": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-v",
"${env:HOME}/.docker/config.json:/root/.docker/config.json:ro",
"ghcr.io/oras-project/oras-mcp:main",
"serve"
]
}
}
}Adjust the path if you keep credentials under ${env:DOCKER_CONFIG}. The container understands only inline auths entries; helper-based configs (credsStore, credHelpers) won't work. On macOS/Windows, install the released binary instead.
Setup from Released Binaries
Visit the GitHub releases page and download the archive that matches your operating system and CPU architecture (
oras-mcp_<version>_<os>_<arch>.tar.gzfor Linux or macOS,oras-mcp_<version>_windows_<arch>.zipfor Windows).Extract the archive; the folder contains a single executable named
oras-mcp(ororas-mcp.exeon Windows) and a copy of the project license.Move the binary to a directory on your
PATH(for example,/usr/local/binon Linux/macOS or%LOCALAPPDATA%\Programs\oras-mcpon Windows) or reference it directly from its extracted location.Run
oras-mcp serve --help(ororas-mcp.exe serve --help) to confirm the binary works on your system.To integrate with VS Code agent mode, update
.vscode/mcp.jsonto point at the extracted binary:{ "servers": { "oras-mcp-server": { "type": "stdio", "command": "/absolute/path/to/oras-mcp", "args": [ "serve" ] } } }On Windows, set
"command": "C:/path/to/oras-mcp.exe".
Authentication
oras-mcp reads credentials from the same stores used by the ORAS and Docker CLIs, but you need to expose those stores to the server process:
Released binary – Run
oras login <registry>ordocker login <registry>on the host machine; the binary will pick up the cached credentials automatically.Docker container – On Linux you can mount your Docker config as shown in the credential section; ensure the file contains inline
authsentries. Docker Desktop (macOS/Windows) depends on keychain helpers, so use the released binary there.
Related MCP server: oci-mcp-server
Example Chats
Q: What platform does the image ghcr.io/oras-project/oras support?
A: The image ghcr.io/oras-project/oras supports the following platforms:
Linux (amd64)
Linux (arm64)
Linux (arm, variant v7)
Linux (s390x)
Linux (ppc64le)
Let me know if you need further details!
Q: What's the latest Azure Linux 3.0 image in MCR? Does it have a signature? What's the type of it?
A: The latest Azure Linux 3.0 image in the Microsoft Container Registry (MCR) is tagged as 3.0.20250402. It has a signature, and the type of the signature is application/vnd.cncf.notary.signature.
Release Process
Maintainers can find the full release steps in the release checklist.
Available Tools
7 toolsfetch_blobC
Fetch blob referenced by a digest in a manifest.
Inputs: digest (required), registry (required), repository (required).
fetch_manifestC
Fetch manifest of a container image or an OCI artifact.
Inputs: registry (required), repository (required), digest, tag.
list_referrersC
List referrers of a container image or an OCI artifact.
Inputs: registry (required), repository (required), digest, tag.
list_repositoriesC
List repositories of a container registry.
Inputs: registry (required).
list_tagsC
List tags in a repository of a container registry.
Inputs: registry (required), repository (required).
list_wellknown_registriesB
List well-known public registries with catalog support.
Inputs: no named parameters.
parse_referenceB
Parse a reference string into its components of registry, repository, tag, and digest.
Inputs: reference (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap: fetch_blob retrieves specific blobs, fetch_manifest gets manifests, list_referrers shows referrers, list_repositories lists repositories, list_tags lists tags, list_wellknown_registries lists registries, and parse_reference parses reference strings. The descriptions make it easy to differentiate between these operations.
All tools follow a consistent verb_noun naming pattern (e.g., fetch_blob, list_repositories, parse_reference) using snake_case throughout. This predictability makes it easy for agents to understand and select the right tool based on the action and resource.
With 7 tools, this server is well-scoped for its purpose of interacting with container registries and OCI artifacts. Each tool serves a specific function, such as fetching, listing, or parsing, without redundancy, making the count appropriate and manageable.
The tool set covers core operations for registry interaction, including fetching, listing, and parsing, which supports common workflows. However, there are minor gaps, such as the lack of tools for pushing or deleting artifacts, which might require workarounds for full lifecycle management.
Maintenance
Related MCP Connectors
Query, explore, and manage your databases through natural conversation.
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Query your team's drift, vulnerability, and upgrade data from any AI assistant. OAuth 2.1, 51 tools.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables natural language interaction with Docker commands and operations. Supports container management, image operations, system information, and Docker Compose through conversational requests.14101 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables natural-language access to Oracle Cloud Infrastructure resources, allowing users to query compute instances, OKE clusters, networking, and Object Storage via MCP tools.MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to manage and analyze containers across Docker and Podman through natural language, providing unified inspection, monitoring, and diagnostics.3-
- AlicenseBqualityDmaintenanceEnables AI assistants to manage Docker containers and Kubernetes resources through natural language, supporting operations like container management, image building, and pod/deployment/service management.9MIT