mcpField
O
Oi

Oi

Remote
oioioi.aiAI & Agents1Updated 11w ago
RepositoryVisit website

About Oi

Oi is a hosted MCP server for managing a team's shared AI setup. It provides discovery and execution for contexts, workflows and skills, alongside authoring, durable memory, connections and usage reporting.

Key features

  1. 01Discover and run contexts, workflows and skills
  2. 02Create and manage contexts, workflows, skills and guardrails
  3. 03Find and use stable connections
  4. 04Update organization and personal durable memory
  5. 05Report usage and cross-surface effectiveness

Use cases

  1. 01Find and execute a shared team workflow
  2. 02Author or update reusable contexts and guardrails
  3. 03Store durable updates in team or personal memory
  4. 04Review usage across contexts and workflows

MCP support

Oi exposes a hosted MCP server at `https://api.oioioi.ai/mcp`. It provides tools for identity and routing, context and workflow operations, skills, connections, memory and reporting.

#context#workflows#prompts#guardrails#shared#enterprise#collaboration

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.oioioi.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://api.oioioi.ai/mcpAuth required

Tools

Details

From the project README

Oi Logo Oi - MCP

Website | App

Registry metadata for the hosted Oi MCP server, including Contexts, Workflows, Skills, Guardrails, Brain, Connections, and reporting.

Connect

Server URL: https://api.oioioi.ai/mcp

Authentication:

  • OAuth via the Oi app
  • Authorization: Bearer <api-token>

Tool surface

  • Identity and routing
  • Context, Workflow, and available Skill discovery and execution
  • Context, Workflow, Skill, and Guardrail authoring/lifecycle operations
  • Stable Connection discovery and execution through oi.connections.list, oi.connections.get, and oi.connections.use
  • Org Brain and User Brain durable-memory updates
  • Context/Workflow usage reporting and cross-surface effectiveness reporting

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.