Otter.ai MCP Server
for AI Agents
Connect your AI agent to StackOne's Otter.ai MCP server and give it ready-to-use MCP tools out of the box. Auth, tool execution, and security all managed.
StackOne 
Coverage
8 Agent Actions
Agents can read and write in Otter.ai. Extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Otter.ai MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Otter.ai tool response scanned for prompt injection in milliseconds, with 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Otter.ai call.
Tools Discovery →What is the Otter.ai MCP Server?
A Otter.ai MCP server lets AI agents read and write Otter.ai data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Otter.ai MCP server ships with pre-built actions, fully extensible via the Connector Builder, plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Otter.ai MCP Tools
Every StackOne action for Otter.ai, ready for your agent. Read and write, scoped to exactly what you need.
Channels
- List Channels
Retrieve the Otter channels accessible to the authenticated user. Returns the channel id needed by list_channel_members and by the channel_id filter on list_conversations.
Channel Members
- List Channel Members
Retrieve the members of an Otter channel by channel id (from list_channels), returning each member's id, name and email.
Conversations
- Create Conversation
Import an externally recorded audio or video file into Otter from a URL, creating a conversation that Otter transcribes and summarises.
- List Conversations
Retrieve a cursor-paginated list of Otter conversations (meetings) for the authenticated user. Returns the conversation id needed by get_conversation and get_conversation_audio.
- Get Conversation
Retrieve a single Otter conversation by its id (from list_conversations), together with the transcript, action items, insights or outline selected by the include parameter.
Conversation Audios
- Get Conversation Audio
Retrieve the MP3 download link for an Otter conversation's recording, by conversation id from list_conversations.
Workspaces
- Get Workspace
Retrieve the Otter workspace the authenticated API key belongs to, including its id, name, owner, member count, handle and type.
Workspace Conversations
- List Workspace Conversations
Retrieve every conversation in an Otter workspace, not just those owned by or shared with the authenticated user. Requires Super Admin.
Set Up Your Otter.ai MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Otter.ai in under 10 lines of code.
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}Check More AI & ML MCP Servers
182+ actions
164+ actions
126+ actions
121+ actions
62+ actions
57+ actions
42+ actions
Platform Resources
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
MCP vs A2A: Architecture, Security, and When to Use Each
MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.
12 min
MCP vs API: What Hundreds of Connector Builds Taught Us
MCP wraps APIs, it doesn't replace them. After building hundreds of connectors that serve both, here's when each approach wins.
14 min read
Otter.ai MCP Server FAQ
Does StackOne have a Otter.ai MCP server?
Otter.ai MCP server vs direct API integration: what's the difference?
How does Otter.ai authentication work for AI agents?
origin_owner_id.Are Otter.ai MCP tools vulnerable to prompt injection?
What is the context bloat of a Otter.ai agent and how do I avoid it?
Can I limit which actions my Otter.ai agent can access?
Can I create custom agent actions for my Otter.ai MCP server?
When should I NOT use a Otter.ai MCP server?
What AI frameworks and AI clients does the StackOne Otter.ai MCP server support?
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.