An OCI Model Context Protocol server for load-balancer
Listed on its own since 2026-09-25. Until then it was part of oracle-data-studio-mcp-server, where its earlier checks remain.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"oracle-oci-load-balancer-mcp-server","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# OCI Load Balancer MCP Server This server provides tools for interacting with Oracle Cloud Infrastructure (OCI) Load Balancer service. ## MCP client configuration (recommended) Most users should configure their MCP client to launch the server, rather than starting it manually. Add a stanza like this to your MCP client config (often called `mcp.json`; example shown is **stdio**): ```json { "mcpServers": { "oci-load-balancer": { "type": "stdio", "command": "uvx", "args": [ "oracle.oci-load-balancer-mcp-server" ], "env": { "OCI_CONFIG_PROFILE": "DEFAULT" } } } } ``` For HTTP transport, start the server with: ```sh ORACLE_MCP_HOST=<bind_host> \ ORACLE_MCP_PORT=<port> \ ORACLE_MCP_BASE_URL=<public_base_url> \ OCI_REGION=<region> \ IDCS_DOMAIN=<idcs_domain> \ IDCS_CLIENT_ID=<client_id> \ IDCS_CLIENT_SECRET=<client_secret> \ IDCS_AUDIENCE=<audience> \ uvx oracle.oci-load-balancer-mcp-server ``` Register `${ORACLE_MCP_BASE_URL}/auth/callback` in the OCI IAM confidential application. If `IDCS_REQUIRED_SCOPES` is unset, the default is `openid profile email oci_mcp.load_balancer.invoke`. `stdio` uses the configured OCI CLI profile; HTTP uses the authenticated OCI IAM user.
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.