Arcmira: YouTube Transcript Search
Arcmira · API docs Give your AI the ability to find who said what with timestamps, discover what’s being discussed across videos and livestreams, and…
What it can do
- Arcmira Describe: Returns the reference for the typed arcmira client the execute tools run: method arguments, return fields, entity ID rules, examples, errors, the budget and monitor rules, and docume
- Arcmira Execute Read: Runs JavaScript against the Arcmira API through the arcmira client: indexed YouTube and podcast transcripts, mentions, sponsors, recommendations, coverage, Premium transcripts (a
- Arcmira Execute Write: Runs JavaScript like arcmira_execute_read, with the account writes added: arcmira.monitors.create, arcmira.monitors.update (including paused), arcmira.monitors.addEntities, arcm
What data it sees
Do you need an account
No: the server works without sign-in
Give your AI the ability to find who said what with timestamps, discover what’s being discussed across videos and livestreams, and distinguish organic recommendations from sponsored ad reads.
Search indexed YouTube transcripts, follow speaker appearances across channels, and save research monitors. Premium transcripts include speaker names where identified. A paid read uses credits from your plan, then your enabled on-demand budget. Monitor alerts use 25 credits each. Creator captions and Premium transcripts are distinct sources.
Connect through OAuth or an account API key. Monitor changes need write access. Coverage varies; sponsored and organic labels are AI classifications, so check the linked quotes and timestamps.
How to connect
How to connect Arcmira: YouTube Transcript Search to Claude
The server address to paste into Claude settings:
https://arcmira--zeal.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Arcmira: YouTube Transcript Search to ChatGPT
The server address to paste into ChatGPT settings:
https://arcmira--zeal.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Arcmira: YouTube Transcript Search to Cursor
The server address to paste into Cursor settings:
https://arcmira--zeal.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (4)
Raw names from tools/list. Only developers need these.
| arcmira_describe | Returns the reference for the typed arcmira client the execute tools run: method arguments, return fields, entity ID rules, examples, errors, the budget and monitor rules, and documentation links. The optional topic narrows it to a method or subject. Reads no indexed content and bills nothing. Docs: https://arcmira.com/docs/mcp-server |
| arcmira_execute_read | Runs JavaScript against the Arcmira API through the arcmira client: indexed YouTube and podcast transcripts, mentions, sponsors, recommendations, coverage, Premium transcripts (a Premium read of an untranscribed video uses credits from the user's plan, then the on-demand budget; never ask for cents), and the user's monitors. Input is an async function body with arcmira, ArcmiraError, and console in scope. Output is bounded JSON with the outcome first, then call/rate/build facts and capped logs. Methods and examples: arcmira_describe. Filters require entity, channel, or video IDs. Limits: 30 seconds, 40 API calls, and 12,000 characters of output in total, 3,000 per string, and 100 items per array. |
| arcmira_execute_write | Runs JavaScript like arcmira_execute_read, with the account writes added: arcmira.monitors.create, arcmira.monitors.update (including paused), arcmira.monitors.addEntities, arcmira.monitors.addName and arcmira.monitors.attachTrackers. Use it only to save what the user asked to follow: list their monitors first, never assume one exists, and ask how they want updates (email or Slack; as it happens, hourly or daily) before creating one. Nothing is deleted; pause instead. Limits: 30 seconds, 40 API calls, and 12,000 characters of output in total, 3,000 per string, and 100 items per array. |
| arcmira_feedback | Saves a feedback record for the Arcmira team about what was wrong, slow, missing or confusing in a task. Send one when a result was empty, an error, truncated or an ask that did not serve the user, or when the user says something was off. Each call adds a record; repeated calls create separate records. Costs nothing. |