ObjectStack
OfficialClick 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., "@ObjectStacklist all customer records from the sales object"
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.
ObjectStack extension for Gemini CLI
Connect Gemini CLI to any ObjectStack deployment — cloud or self-hosted — over the Model Context Protocol. Discover objects, query and change records, and run business actions, all under your own permissions and row-level security.
One extension serves every deployment: the deployment URL is the only per-environment
input (OBJECTSTACK_MCP_URL). Identity is self-serve — every ObjectStack deployment is
its own OAuth 2.1 authorization server with Dynamic Client Registration.
Install
gemini extensions install https://github.com/objectstack-ai/gemini-extensionRelated MCP server: mcp-cli-gemini
Connect
Set the deployment URL (find it on your deployment's Setup → Connect an agent
page, or append /api/v1/mcp to the address you open in the browser):
export OBJECTSTACK_MCP_URL="https://acme.objectos.app/api/v1/mcp"Headless (CI, machine accounts): configure an ObjectStack API key as an
x-api-key header on the MCP server entry in your Gemini settings instead of OAuth.
What's inside
GEMINI.md— the portable ObjectStack agent context: discover-first workflow (list_objects→describe_object→ act), the full tool surface incl. business actions (list_actions/run_action), and governance conventions. It enumerates no schema — objects and actions are discovered live, so one install keeps working as your apps evolve.gemini-extension.json— MCP server bound to$OBJECTSTACK_MCP_URL.
GEMINI.md is a copy of the single source in
@objectstack/mcp
(renderSkillMarkdown(), frontmatter stripped); CI fails on drift. Re-render with
npm run sync:skill — never hand-edit.
License
Apache-2.0 — see LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Termalin's hosted MCP server. Claude, ChatGPT or any MCP client runs commands, moves files over SFTP, queries databases and reads server metrics and monitoring alerts on your servers, keylessly through Termalin Connectors: no SSH key is handed over and no inbound port is opened. Per-host command policy and an audit log. Needs a termal.in Pro or Team account (new accounts start with a 14-day Pro trial).
List, read, edit, and deploy your GenMB AI-generated apps from any MCP client.
- TypeshipOAuthdev.typeship
Generate a typed SDK, CLI, and MCP server from any OpenAPI or GraphQL spec, and keep them current.
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- AlicenseAqualityDmaintenanceA bridge that connects the Model Context Protocol to the Gemini CLI via the Agent Client Protocol (ACP) for high-performance, stateful AI interactions. It enables MCP clients to leverage Gemini's autonomous capabilities, including multi-modal support and built-in tool execution, without cold-start overhead.441MIT
- FlicenseAqualityDmaintenanceWraps the Gemini CLI as an MCP server, enabling AI tools to perform Gemini queries, interactive sessions, and extension management via a unified tool.11-
- AlicenseNot gradedqualityDmaintenanceExposes the local Gemini CLI as an MCP stdio server, providing tools for prompting, web search, file operations, and MCP management, enabling AI clients like Codex CLI and Claude Code to interact with Gemini.7MIT
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that wraps the Gemini CLI, enabling AI assistants to send prompts, research topics, analyze code, and summarize content using Gemini.13MIT