ORANO MCP Server

io.github.infotikPublished by GitHub account infotikv0.1.0Updated Oct 24, 2026

Read-only MCP server exposing a user ORANO library to their own AI agent.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Read-only remote MCP server that lets your own AI agent read your personal ORANO library of saved-video projects, tasks, research, roadmaps and memory facts.

What you can do
  • List and filter your projects by status (active, completed, skipped, archived)
  • Fetch a single project's full structured understanding, summary, tasks, resources, research and roadmap
  • Pull only selected context fields such as summary, transcript, visual context, links or raw source, as structured data, Markdown or text
  • Search your library by title, summary, source title or URL
  • Read curated memory facts (preferences, skills, goals) with confidence and freshness signals
  • Retrieve projects explicitly handed off from the ORANO app to a target agent
When to use it
Useful when you keep saved Reels, TikToks and YouTube Shorts organized as ORANO projects and want ChatGPT, Claude, Cursor or Ollama to answer with that context. It suits personal second-brain style recall of your own summaries, tasks and roadmaps rather than general web search.
Requirements
A remote endpoint at the ORANO backend; no local package to install. An ORANO account with the iOS app and at least one saved project. A personal API key created manually in the app (Settings, MCP access) with scope orano:read, sent as a bearer token, for example via the ORANO_MCP_KEY environment variable in client configs. Per-user limit of 240 calls per 60 minutes and at most 10 active keys.
Before you install
The bearer API key grants read access to your personal library, so keep it out of shared configs and revoke unused keys. Reading pending handoffs marks each delivery as acknowledged, which is the only state change. No OAuth flow exists, so key handling is manual. The public repository is documentation and a reference implementation; the production server is closed source and runs on ORANO's infrastructure, so your project data is read through that service.

Installation

In SourceWeft

  1. Open ORANO MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.infotik%2Forano-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "orano": {
      "type": "http",
      "url": "https://api.oranoai.com/mcp/"
    }
  }
}

README

ORANO MCP Server

A personal, read-only MCP (Model Context Protocol) server that lets a user's own AI agent (ChatGPT, Claude, Cursor, Ollama) read their ORANO library as grounded context.

Note: This public repository contains documentation, the MCP server manifest, and a reference implementation. The production MCP server runs as an authenticated endpoint mounted at /mcp on the ORANO backend (FastAPI + Postgres + pgvector). See the ORANO product site for the live endpoint and authentication flow.

What is ORANO?

ORANO turns saved Reels, TikToks, YouTube Shorts, and reference material into structured projects — summary, key takeaways, ordered tasks, research context, and a learning roadmap. Live on the iOS App Store (App Store listing).

A personal, read-only MCP server so a user's own AI agent can read that context is the differentiator.

MCP tools exposed

The ORANO MCP server exposes the following tools:

ToolDescription
list_projectsList the user's projects with optional status filters (active, completed, skipped, archived).
get_projectReturn a single project's full structured understanding + summary + tasks + resources + research + roadmap.
get_project_contextReturn only the requested context fields (summary, overview, caption, transcript, visual_context, links, tasks, roadmap, source, or raw_source) in structured, Markdown, or text output.
search_librarySearch the user's projects by title, summary, source title, or URL.
read_memory_factsReturn curated memory facts (preferences, skills, goals) with confidence and freshness signals.
get_pending_handoffsRetrieve projects explicitly sent from the ORANO app to a target agent. Each handoff is acknowledged once on read so concurrent polls do not duplicate.

Authentication

  • Mechanism: Bearer personal API key, scope orano:read.
  • No OAuth. Manual key creation only (per landing/mcp-access.html).
  • Per-user budget: 240 calls per 60 minutes.
  • Maximum active keys per user: 10.

MCP server manifest (server.json)

The canonical MCP server manifest follows the official MCP server.json schema:

json
{  "$schema": "https://static.modelcontextprotocol.io/schemas/server.json",  "name": "io.github.infotik/orano-mcp-server",  "displayName": "ORANO",  "description": "Personal, read-only MCP server that exposes the user's ORANO library (projects, tasks, research, roadmaps, memory facts) as tools for their own AI agent.",  "version": "0.1.0",  "repository": {    "type": "git",    "url": "https://github.com/infotik/orano-mcp-server"  },  "homepage": "https://oranoai.com/mcp",  "categories": [    "knowledge-management",    "personal-assistant",    "productivity",    "second-brain"  ],  "tools": [    { "name": "list_projects", "description": "List the user's ORANO projects with optional status filters." },    { "name": "get_project", "description": "Return a single project's full structured understanding." },    { "name": "get_project_context", "description": "Return only the requested context fields (summary, overview, transcript, visual_context, links, tasks, roadmap, source, raw_source)." },    { "name": "search_library", "description": "Search the user's projects by title, summary, source title, or URL." },    { "name": "read_memory_facts", "description": "Return curated memory facts with confidence and freshness signals." },    { "name": "get_pending_handoffs", "description": "Retrieve acknowledged-once projects explicitly sent from the ORANO app to a target agent." }  ],  "transports": [    { "type": "http", "endpoint": "https://orano-ai-backend-1037939693300.us-central1.run.app/mcp/" }  ],  "authentication": {    "type": "bearer",    "scope": "orano:read",    "user_specific": true,    "rate_limit": "240 calls / 60 minutes / user"  }}

Reference implementation (Python)

The production server runs as part of the ORANO backend (FastAPI + SQLAlchemy + pgvector). The reference implementation pattern is:

python
from mcp.server.fastmcp import FastMCPfrom mcp.server.auth.settings import AuthSettingsfrom mcp.server.auth.provider import AccessToken
mcp = FastMCP(    name="orano",    auth=AuthSettings(issuer_url="https://orano-ai-backend-1037939693300.us-central1.run.app", required_scopes=["orano:read"]),)
@mcp.tool()async def list_projects(status: str | None = None) -> list[dict]:    """List the user's ORANO projects."""    ...
@mcp.tool()async def get_project(project_id: str, fields: list[str] | None = None) -> dict:    """Return a single project's full structured understanding."""    ...
# ... plus get_project_context, search_library, read_memory_facts,# get_pending_handoffs

The full production server (787 lines + 290 lines of auth/handshake helpers) lives in ExecutionOSBackend/app/mcp_server.py and is part of the private ORANO backend repository. Open-sourcing the full production code requires extracting the SQLAlchemy models + ingest services into a public package, which is on the product roadmap but not yet complete.

How to use

End users:

  1. Install the ORANO iOS app from the App Store.
  2. Sign in, save at least one Reel/TikTok/YouTube Short to generate your first project.
  3. Open Settings → MCP access → Create new key (scope orano:read).
  4. Connect your AI agent (ChatGPT, Claude, Cursor, Ollama) to your personal MCP endpoint with the key as a bearer token.

Privacy and trust

  • The MCP server is read-only. It does not write to projects, sources, tasks, memory, or account data.
  • The single state mutation is get_pending_handoffs acknowledging a queued app-triggered delivery by setting its delivery timestamp.
  • No agent write access is promised; no one-click OAuth flow exists.

License

MIT — see LICENSE.

Links

Setup guides

Source: README.md at commit e627136

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declaredRequired10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts