Skip to main content
NVIDIA
GitHub MCP Proxy
Container
NVIDIA
GitHub MCP Proxy

Optional internal MCP source-intelligence service for POC Factory. It exposes GitHub repository and code context through an SSE endpoint, supporting blueprint discovery and matching across curated NVIDIA reference architectures.

Subscribe to get accessSubscribe to the product below to access this premium content:
POC Factory
POC FactoryPOC Factory turns natural-language requirements, proposals, and RFPs into working AI and Physical AI proofs of concept built with NVIDIA NeMo Agent Toolkit. It supports generation, validation, packaging, deployment, evaluation, optimization, synthetic data, and model fine-tuning.
Note: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.
Already Subscribed?Log in
Subscribe Now

GitHub MCP Proxy Overview

Explore the POC Factory documentation and the installation guide. Select documentation and a deployment bundle matching the image tags you deploy.

Description:

The GitHub MCP Proxy container provides optional Model Context Protocol (MCP) source intelligence for POC Factory. It bridges the poc-factory-mcp backend to GitHub so the platform can use repository and code context when matching requirements to curated NVIDIA blueprints. The container runs @modelcontextprotocol/server-github behind mcp-proxy, which adapts the server's stdio transport to an internal Server-Sent Events (SSE) endpoint.

This companion container is included in the mcp and full Docker Compose profiles. Its endpoint is reachable only on the POC Factory Compose network or through the Helm ClusterIP Service; the release does not publish it to a host port. GITHUB_TOKEN is optional and is used for authenticated GitHub lookups when needed for private repositories or rate-limit headroom. The supplied user guide recommends a read-only, least-privilege token. Do not expose the MCP endpoint publicly or grant broader permissions unless a separately approved workflow requires them.

The container components are ready for commercial or non-commercial use.

Third-Party Community Consideration:

The GitHub MCP server embedded in this container is not owned or developed by NVIDIA. The container includes the TypeScript @modelcontextprotocol/server-github reference implementation, with dependency updates applied by the container build. Its upstream source is archived; see the TypeScript GitHub MCP reference server and the Model Context Protocol specification.

License/Terms of Use:

GOVERNING TERMS: Your use of the container is governed by the NVIDIA Software License Agreement and Product-Specific Terms for AI Products. Your use of the model is governed by the NVIDIA Community Model License.

You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.

Deployment Geography:

Global

Program Classes:

The GitHub MCP Proxy container includes the following components:

ComponentDescriptionPort
@modelcontextprotocol/server-githubGitHub MCP tool server, invoked through stdio—
mcp-proxySSE transport proxy for the stdio MCP server8080 (Compose) or 8081 (Helm)
mcpPython MCP runtime used by the proxy—

The POC Factory function group is configured for get_file_contents, search_repositories, search_code, and fork_repository. A read-only token supports discovery use cases; a fork operation requires a separately authorized credential with the required repository permissions.

Deployment Details:

Supported Hardware Microarchitecture Compatibility:

  • GPUs: Not required — this container performs no GPU-accelerated computation
  • CPU: x86_64 (amd64) and ARM64 (arm64)
  • Memory: Helm defaults request 256MiB and limit the container to 512MiB; adjust for deployment traffic
  • Storage: No persistent volume is required. Docker Compose uses JSON log rotation with 10 MB files and three retained files; Helm requests 256Mi ephemeral storage and limits it to 1 GiB

Docker Compose Deployment:

The GitHub MCP Proxy is included in the mcp and full Docker Compose profiles. It is an optional source-intelligence service; POC Factory can generate POCs without authenticated GitHub lookups.

Run these commands from the extracted matching NGC release bundle, in the directory containing docker-compose.yml, env.example, and scripts/validate-compose-env.sh.

Before starting, configure .env with NIM_NGC_ORG=nvidia for the NVIDIA catalog and VERSION set to the selected image tag. For internal copies, use NIM_NGC_ORG=nvstaging/sae-poc-factory or NIM_NGC_ORG=1042542912482436 (SAE-PoC-Factory), with credentials authorized for that namespace. Choose an available release tag and keep all POC Factory images on the same version. If set, POC_FACTORY_MCP_VERSION, GITHUB_MCP_PROXY_VERSION, and FRONTEND_VERSION override VERSION; update or remove those overrides when upgrading.

Set PostgreSQL credentials and a stable ENCRYPTION_KEY in .env, following the generation instructions in env.example. Configure an administrator-managed inference profile, or allow users to supply their own profiles in Settings. For shared deployments, enable NGC_AUTH_ENABLED and supply the required ES256 JWT_PRIVATE_KEY. An optional read-only GITHUB_TOKEN enables authenticated source discovery. Put deployment values in .env so both Compose and its launch preflight receive them.

For upgrades, preserve the existing .env, encryption key, database credentials, and persistent data volumes. Back up the data before changing versions, and review the matching release documentation for any additional upgrade steps. Generate an encryption key only for a new deployment; replacing it makes previously saved credentials undecryptable.

# From the extracted matching NGC release bundle
# Create .env only for a new deployment; preserve an existing file
test -f .env || cp env.example .env

# Edit .env with the image namespace, release tag, and settings described above
# Authenticate with an NGC API key authorized to pull these images
# Enter the API key at the password prompt
docker login nvcr.io --username '$oauthtoken'

# Validate the Compose configuration, then pull and start the standard stack
docker compose --profile mcp config --quiet
docker compose --profile mcp pull
docker compose --profile mcp up -d

# Or add Phoenix observability
docker compose --profile full up -d

For Compose, the SSE endpoint is http://github-mcp-proxy:8080/sse on the internal mcp-network. Helm exposes a ClusterIP Service on port 8081, also targeting the SSE endpoint. Neither deployment makes this service host-public by default.

Environment Variables:

VariableRequiredDescription
GITHUB_TOKENNoDeployment-managed GitHub credential. Compose and Helm pass it to the container as GITHUB_PERSONAL_ACCESS_TOKEN; use a read-only, least-privilege token for source discovery.
LOG_LEVELNoLogging verbosity. The release deployment defaults to INFO.
PYTHONUNBUFFEREDNoEnables prompt log output. The release deployment sets it to 1.

GITHUB_PERSONAL_ACCESS_TOKEN is the server-internal variable, not a user-editable POC Factory setting.

Health Check: Docker Compose verifies TCP connectivity on port 8080 every 30 seconds (10-second timeout, five retries, 45-second start period). Helm probes the /sse endpoint on port 8081 with the same interval, timeout, and failure threshold.

Security Notes: The image uses Node.js and npm, and includes the MCP proxy and GitHub MCP server dependency set. It runs as the non-root node user (UID/GID 1000). The Helm deployment also sets runAsNonRoot, disallows privilege escalation, and disables service-account token automounting.

This container does not include or execute AI models. Consult the NGC Security Scanning tab for current scan and VEX information.

Reference(s):

Security Common Vulnerabilities and Exposures (CVEs)

Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.

Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

Get Help

Getting Started with GitHub MCP Proxy

Use the documentation and installation guide above for deployment instructions.

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.

Publisher
NVIDIA
LicenseNVIDIA proprietary
Latest Tag1.1.1
UpdatedOctober 10, 2026 UTC
Compressed Size154.91 MB
Multinode SupportNo
Multi-Arch SupportYes

Modal Content

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.