Bring Meeting Management
to LangChain
Learn how to connect Fellow to LangChain and start using 12 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Fellow MCP Server?
Connect your Fellow workspace to any AI agent and manage your entire meeting workflow through natural conversation.
What you can do
- Meetings — List and inspect meetings with titles, participants, dates, and agendas.
- Notes — Access structured meeting notes and AI-generated summaries.
- Action Items — Create, track, and complete action items with assignees and due dates.
- Streams — Browse recurring meeting series and their schedules.
- Users — List all workspace members and their roles.
How it works
1. Subscribe to this server
2. Enter your Fellow API key (User Settings > Developer Tools)
3. Start managing meetings from Claude, Cursor, or any MCP client
Who is this for?
- Team Leads — review meeting notes and action items without opening Fellow.
- Project Managers — track follow-up tasks and ensure accountability.
- Remote Teams — stay aligned on meeting outcomes and decisions.
Built-in capabilities (12)
Verify Fellow API connectivity
Mark an action item as completed
Optionally link it to a meeting, assign to a user by email, and set a due date. Create a new action item from a meeting
Get details of a specific action item
Get full details of a specific meeting
Get full content of a specific note
Get details of a specific meeting stream
Optionally filter by status: "pending", "completed", or "archived". List action items from meetings
List recent meetings from Fellow
Optionally filter by a specific meeting ID to get notes for that meeting only. List meeting notes
List all meeting streams (recurring series)
List all users in the Fellow workspace
Why LangChain?
LangChain's ecosystem of 500+ components combines seamlessly with Fellow through native MCP adapters. Connect 12 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
- —
The largest ecosystem of integrations, chains, and agents. combine Fellow MCP tools with 500+ LangChain components
- —
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
- —
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
- —
Memory and conversation persistence let agents maintain context across Fellow queries for multi-turn workflows
Fellow in LangChain
Fellow and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Fellow to LangChain through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Fellow in LangChain
The Fellow MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 12 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LangChain only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Fellow for LangChain
Every tool call from LangChain to the Fellow MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I create an action item and assign it to a team member?
Yes! Use create_action_item with the title, assignee email, and optional due date. You can also link it to a specific meeting.
How do I get the notes from a specific meeting?
Use list_notes with the meeting ID to get all notes linked to that meeting, or get_note with a specific note ID for full content.
Can I mark action items as completed via the AI agent?
Absolutely. Use complete_action_item with the action item ID to mark it as done.
How does LangChain connect to MCP servers?
Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.
Which LangChain agent types work with MCP?
All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.
Can I trace MCP tool calls in LangSmith?
Yes. All MCP tool invocations appear as traced steps in LangSmith, showing input parameters, response payloads, latency, and token usage.
MultiServerMCPClient not found
Install: pip install langchain-mcp-adapters