Skip to content
MCP server

ORANO MCP

Save videos and links, then let agents read transcripts, research and task plans from them

Pricing
Paid
Platforms
Web, iOS, Android
Runs
Remotely
Version
2.0.0
Listing updated
2 days ago

About ORANO MCP

ORANO MCP is a paid MCP server for productivity. It runs as a hosted remote server, so there is nothing to install locally.

ORANO is an app that turns saved Reels, TikToks, YouTube videos, articles and PDFs into transcripts, frame evidence, key points, resources and step-by-step task plans. The MCP server gives an agent the same abilities without opening the app: save a link, wait for the analysis, search the library, run research, generate tasks or a learning roadmap, and ask Ori, ORANO's assistant.

Authentication is a personal key sent as a bearer token; there is no OAuth. Keys carry orano:read and orano:write scopes unless created read-only. An agent can even start its own signup by supplying a person's email, after which that person approves by email and subscribes.

The README counts 43 tools. The hosted server is closed source, and the examples repository holds client configurations.

Install

Run in a terminal

claude mcp add --transport http orano-personal-context-mcp https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/

Add to Settings → Connectors → Add custom connector

https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "orano-personal-context-mcp": {
      "url": "https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "orano-personal-context-mcp": {
      "type": "http",
      "url": "https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "orano-personal-context-mcp": {
      "serverUrl": "https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "orano-personal-context-mcp": {
      "type": "http",
      "url": "https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/"
    }
  }
}

Tools this server provides (16)

Taken from the project documentation; the running server may differ.

save_link
Saves a link and optionally waits for analysis.
get_project
Reads the full analysis of a saved project.
get_processing_status
Checks whether a save has finished processing.
get_project_context
Reads chosen fields such as transcript or frame analysis.
create_video_upload
Starts an upload of a video file.
finish_video_upload
Completes an upload and starts analysis.
run_research
Runs sourced web research on a save.
generate_tasks
Generates a step plan.
generate_roadmap
Generates a learning path.
ask_about_project
Answers questions grounded in a project.
search_library
Searches the library by meaning.
ask_ori
Asks Ori for an answer across the library.
get_pending_handoffs
Fetches saves the person sent from the app.
get_account
Shows plan, scopes and limits.
list_projects
Lists saved projects, newest updated first.
get_memory_facts
Reads curated memory facts such as preferences and goals.

What it does

Save and analyse links
save_link waits for analysis, then get_project returns the transcript, key points and tasks.
Library search
Find saved projects by meaning, topic or title, or ask Ori for an answer.
Deeper work
Run sourced research, generate task plans and learning roadmaps for a save.
Handoffs from the app
Projects a person sends from the app queue until the agent fetches them.
Video upload
Upload a file from disk and have it analysed.
Read-only keys
Create a key limited to orano:read.

Good for

  • Turn a saved tutorial video into an ordered task list
  • Search everything you have saved about a topic
  • Let an agent pick up links you send from your phone
  • Research the claims in a saved post with sourced findings
  • Build a learning roadmap from saved resources

Pricing

Paid, from $5 a month

$5 per month per person

Prices change. Check oranoai.com before you buy.

ORANO MCP FAQ

How much does it cost?

$5 a month per person; the person pays once and an agent can start the signup.

How does an agent authenticate?

With a personal orano_sk key sent as a bearer token; OAuth is not offered.

Is the server open source?

No. The hosted server is closed source; the examples repository is public.

Where is it hosted?

There are Asia-Southeast and US regional endpoints serving the same data.

Is ORANO MCP free?

No. ORANO MCP is a paid product. Paid plans start at $5 a month.

How do I add ORANO MCP to Claude Code?

Run this command in your terminal: claude mcp add --transport http orano-personal-context-mcp https://orano-ai-backend-1037939693300.asia-southeast1.run.app/mcp/

What are the best alternatives to ORANO MCP?

The closest alternatives to ORANO MCP are Codebase Memory, XERJ, Ha MCP, Claude Code Ultimate Guide and Nautilus Compass Memory.

Alternatives to ORANO MCP

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. Ha MCP

    MCP server

    MCP server for managing and automating Home Assistant from AI assistants

    Runs locally
    • 8 tools
    • Open source
    • 7.9K GitHub stars
    • Productivity
  4. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  5. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  6. Concord MCP

    MCP server

    Local-first MCP server for messaging and shared work-state between coding agents

    Runs locally
    • Freemium
    • 1.3K GitHub stars
    • Developer tools