Bring Lead Management
to Pydantic AI
Learn how to connect Close to Pydantic AI and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Close MCP Server?
Connect your Close CRM account to any AI agent and take full control of your sales workflows through natural conversation.
What you can do
- Lead Management — List all leads in your pipeline and retrieve full company profiles with contacts, custom fields, and activity history
- Lead Creation — Add new leads directly from conversation, including company name and website URL
- Opportunity Tracking — Monitor your active deals with stage, value, and expected close dates
- Task Management — Review pending and completed CRM tasks to stay on top of follow-ups
- User Context — Retrieve your authenticated user profile to understand your current permissions and role
How it works
1. Subscribe to this server
2. Enter your Close API Key from Settings > Developer > API Keys
3. Start managing your sales pipeline from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Sales Representatives — query your pipeline, check lead details, and create new prospects without leaving your AI workspace
- Sales Managers — monitor team opportunities and task completion rates through conversational analytics
- Revenue Operations — automate lead creation workflows and pipeline visibility across the organization
Built-in capabilities (6)
Create a new lead
Get information about the authenticated API user
Get details of a specific lead
List CRM tasks
List all leads in Close CRM
List sales opportunities
Why Pydantic AI?
Pydantic AI validates every Close tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Close integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Close connection logic from agent behavior for testable, maintainable code
Close in Pydantic AI
Close and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Close to Pydantic AI 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 Close in Pydantic AI
The Close 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 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI 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
Close for Pydantic AI
Every tool call from Pydantic AI to the Close 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 new leads directly through the AI agent?
Yes! The create_lead tool accepts a company name and an optional website URL. Your agent will create the lead record in Close and return the new Lead ID for immediate reference.
How does the API authentication work with Close?
Close uses HTTP Basic Authentication. Your API Key is sent as the username with an empty password. Navigate to Settings > Developer > API Keys in your Close dashboard to generate a new key. The key is encrypted at rest and injected securely at runtime.
Can I view my sales opportunities and their current stages?
Yes. The list_opportunities tool retrieves all active deals in your pipeline, including stage name, expected value, probability, and projected close date. Combine it with list_crm_tasks to check pending follow-ups associated with each opportunity.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Close MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai