Bring Crm
to LangChain
Learn how to connect Twenty CRM to LangChain and start using 25 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Twenty CRM MCP Server?
Connect your Twenty CRM account to any AI agent and take full control of your sales pipeline and contact database through natural conversation.
What you can do
- People Management — List all contacts, fetch specific details, and create or update person records directly in the CRM.
- Company Tracking — Manage organizational accounts, list companies, and inspect company metadata using unique IDs.
- Opportunity Pipeline — Query all sales opportunities (deals), track progress, and create new entries to keep your pipeline updated.
- Full Data Control — Perform CRUD operations (Create, Read, Update, Delete) on people and companies to maintain data hygiene.
- Seamless Integration — Access your CRM data from Claude, Cursor, or any MCP-compatible client without leaving your workflow.
How it works
- Subscribe to this server
- Enter your Twenty API Key and Base URL (e.g., https://api.twenty.com)
- Start managing your CRM records using natural language
Who is this for?
- Sales Teams — quickly update opportunity statuses and add new leads without switching tabs
- Account Managers — retrieve company details and contact information instantly during client calls
- Developers — manage CRM data directly from the code editor to test integrations or verify record states
Built-in capabilities (25)
Create a new company
Create a new note
Create a new opportunity
Create a new person
Create a new task
Delete a company
Delete a note
Delete an opportunity
Delete a person
Delete a task
Get a specific company by ID
Get a specific note by ID
Get a specific opportunity by ID
Get a specific person by ID
Get a specific task by ID
List companies in Twenty CRM
List notes in Twenty CRM
List opportunities in Twenty CRM
List people in Twenty CRM
List tasks in Twenty CRM
Update an existing company
Update an existing note
Update an existing opportunity
Update an existing person
Update an existing task
Why LangChain?
LangChain's ecosystem of 500+ components combines seamlessly with Twenty CRM through native MCP adapters. Connect 25 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 Twenty CRM 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 Twenty CRM queries for multi-turn workflows
Twenty CRM in LangChain
Twenty CRM and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Twenty CRM 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 | 4,000+ 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 Twenty CRM in LangChain
The Twenty CRM 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 25 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
Twenty CRM for LangChain
Every tool call from LangChain to the Twenty CRM 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 a new contact person directly through the AI?
Yes! Use the create_person tool by providing at least a first name. You can also include a last name to create a complete record in your Twenty CRM database.
How do I see all the companies currently registered in my CRM?
Simply ask the agent to run the list_companies tool. It will retrieve a list of all company records (accounts) stored in your Twenty environment.
Is it possible to update the details of an existing sales opportunity?
Yes, you can use the update_opportunity tool. You will need the specific Opportunity ID and the new fields (like name) you wish to modify.
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
Explore More MCP Servers
View all →
AutoGen
10 toolsOrchestrate Microsoft AutoGen multi-agent workflows — manage sessions, agent roles, workflows, and monitor execution logs from any AI agent.
Jibble
10 toolsTrack time, attendance, and projects via Jibble API.
Salesforce Admin & Metadata
8 toolsManage users, explore object schemas, monitor org limits, search metadata, execute Apex, and audit profiles through natural conversation.
Node-RED
11 toolsManage Node-RED flows, nodes, and system diagnostics directly from your AI agent.