ailoud
Click on "Install 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., "@ailoudfind where we discussed the API contract in yesterday's call"
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.
Overview
One CLI (ailoud) over a local library:
Transcribe audio and video with whisper.cpp, including recordings that switch between languages, and attribute lines to speakers.
Search the whole library full-text and get back the matching lines with timestamps, not whole transcripts.
Summarise one recording or a tagged group into a saved report, shaped by a template for the kind of conversation it was.
Serve the library to an AI agent over MCP.
Nothing leaves your machine unless you choose a hosted model for summaries.
Related MCP server: Augent
Install
Needs Node.js 24 or newer.
npm install -g ailoudThen install the tools it drives -- ffmpeg, whisper.cpp, the models:
ailoud setup
ailoud doctorSee Getting Started.
CLI quick start
Import, transcribe, read:
ailoud audio import ~/Recordings --tag standup
ailoud audio transcribe
ailoud audio ls
ailoud audio show 01M1B2Find where something was said, without reading a transcript:
ailoud audio search rollback
ailoud audio f "before sunrise" --tag standupSummarise, with a shape and the context the transcript does not carry:
ailoud audio summarize 01M1B2 --template one-on-one \
--context "Ann is Ben's manager; this is their fortnightly."
ailoud report lsEvery verb has a one-letter alias, and the letter means the same in every
group -- l list, v view, r remove, f find:
ailoud audio l
ailoud report lRun ailoud --help or <command> --help for the full set, also in the
CLI Reference.
Templates
A template decides a summary's headings, because different conversations
divide differently: one-on-one, performance-review,
architecture-planning, solution-decision, offsite, meeting.
ailoud template ls
ailoud template new sprint-retro --from one-on-oneThey are YAML files in ~/.config/ailoud/templates/. Edit one and the change
takes effect; AILoud never overwrites a file you have edited. See
Templates.
MCP
{ "mcpServers": { "ailoud": { "command": "ailoud", "args": ["mcp"] } } }Sixteen tools over the same library the CLI uses. Deleting takes two calls: the first describes what would go and returns a confirmation token, the second carries it out. See MCP.
Development
A pnpm workspace: packages/core (domain and ports, no I/O),
packages/providers (adapters), apps/cli (commands and the MCP server).
pnpm build && pnpm format:check && pnpm lint && pnpm typecheck && pnpm test:covSee the Development guide and Architecture. Commit rules and the dependency licence policy are in CONTRIBUTING.md.
License
Apache-2.0. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
OCR, transcription, file extraction, and image generation for AI agents via MCP.
MCP server for Clipkit — gives AI agents a video toolbox via the Clipkit schema.
Shared memory for all your AI agents, your whole team and every MCP client — save, search, recall.
Shared long-term memory vault for AI agents with 20 MCP tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that enables AI agents to analyze videos locally by extracting transcripts, detecting scene changes, and returning key frames.56MIT

Augentofficial
AlicenseBqualityCmaintenanceMCP server that turns any audio or video source into structured, searchable intelligence for agents, enabling download, transcription, semantic search, speaker identification, and more.225MIT- AlicenseNot gradedqualityBmaintenanceEnables AI agents to query local video timelines by extracting speech, frame captions, and on-screen text into a SQLite store, exposing search and retrieval tools via MCP.PolyForm Noncommercial 1.0.0
- AlicenseNot gradedqualityAmaintenanceMCP server that enables AI agents to watch and analyze videos from 1800+ sources, with persistent indexing, OCR, transcription, and a self-verification loop for debugging.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lorem-dev/ailoud'
If you have feedback or need assistance with the MCP directory API, please join our Discord server