studiomeyer-crm

studiomeyer-crm

AI-native CRM with 33 tools. Pipeline, leads, health scores, revenue analytics, CSV import/export.

Category
访问服务器

README

StudioMeyer CRM

AI-native CRM as MCP Server. 33 tools, 3 resources, 3 prompts. No dashboard needed — your AI is the interface.

MCP Registry MCPize Glama


What is this?

StudioMeyer CRM is a headless contact server built as an MCP server. Instead of clicking through a CRM dashboard, you talk to your AI assistant — it manages companies, contacts, deals, leads, follow-ups, and revenue analytics for you.

The only production-ready standalone MCP CRM on the market. Not a bridge to HubSpot or Salesforce — a complete CRM that lives inside your AI workflow.


Quick Start

Option 1: Claude Desktop / Cowork

Add the server URL in Claude Desktop settings:

https://crm.studiomeyer.io/mcp

OAuth 2.1 authentication will guide you through setup.

Option 2: Claude Code

claude mcp add crm --transport streamable-http https://crm.studiomeyer.io/mcp

Option 3: Cursor / VS Code / Windsurf / Zed

npx mcp-remote https://crm.studiomeyer.io/mcp

Option 4: MCPize

https://mcpize.com/mcp/studiomeyer-crm

Subscribe and connect via the MCPize gateway.


Tools (33)

Core CRM (23)

Tool Description
crm_company Create, get, or update a company
crm_list_companies List companies with filters, pagination, sorting
crm_contact Add or update contacts
crm_list_contacts List contacts with filters
crm_deal Create or update deals (auto-probability by stage)
crm_list_deals List deals with filters
crm_get_pipeline Pipeline view: deals by stage, forecast, MRR/ARR
crm_log_interaction Log emails, calls, meetings (auto-updates lastInteractionAt)
crm_get_timeline Chronological timeline of interactions + notes
crm_add_note Add notes to companies or deals
crm_list_notes List notes with filters
crm_lead Ingest, list, update, or convert leads (auto-dedup, temperature detection)
crm_follow_up Create, list, or complete follow-ups with priority and overdue tracking
crm_search Full-text search across all entities (German + English stemming)
crm_health_scores Health scores 0-100 with factor breakdown
crm_dashboard Pipeline + MRR + health + activity + alerts in one call
crm_stats Aggregate metrics
crm_sync_stripe Sync revenue data from Stripe
crm_revenue_report MRR/ARR/growth by company and product
crm_import Bulk CSV/JSON import (auto-maps DE+EN headers, dedup, dry-run)
crm_export CSV/JSON export: contacts, companies, deals, leads
crm_audit_log Audit trail: who changed what, when
crm_connect Zero-knowledge credentials: configure integrations via browser

Management (5 Delete Tools)

Tool Description
crm_company_delete Hard-delete company + cascaded data
crm_contact_delete Hard-delete contact
crm_deal_delete Hard-delete deal
crm_note_delete Hard-delete note
crm_lead_delete Hard-delete lead
crm_follow_up_delete Hard-delete follow-up

System (5)

Tool Description
crm_guide Interactive onboarding with 12 topics
crm_handoff Task queue between Claude Code and Cowork
server_status Server health and configuration

Resources (3)

Resource Description
crm://pipeline Current pipeline state
crm://dashboard Dashboard overview
crm://follow-ups Pending follow-ups

Prompts (3)

Prompt Description
client-review Weekly client review
daily-briefing Morning briefing with priorities
pipeline-forecast Revenue forecast

Search

3-phase search cascade for maximum recall:

  1. Full-text search with German stemming (tsvector + GIN index)
  2. Trigram fuzzy matching with unaccent + word_similarity
  3. ILIKE prefix fallback

Searches across companies, contacts, interactions, deals, notes, leads, and tags. Perfect for DACH market with umlaut support.


What Makes This Different

Feature StudioMeyer CRM HubSpot MCP Pipedrive MCP nxt3d/mcp-crm
Standalone CRM Yes Bridge only Bridge only SQLite PoC
Tools 33 ~10 ~8 ~5
MCP-native Yes Wrapper Wrapper Yes
Pipeline + Deals Yes Via HubSpot Via Pipedrive No
Lead Management Yes Via HubSpot Via Pipedrive No
Follow-ups Yes No No No
CSV Import/Export Yes No No No
Revenue Analytics Yes Via HubSpot Via Pipedrive No
Health Scores Yes No No No
Audit Log Yes No No No
Built-in Guide 12 topics No No No
Stripe Sync Yes No No No
Zero-Knowledge Creds Yes No No No
Hosted MCP Yes No No No

Pricing

Plan Price Included
Free $0/mo 33 tools, 200 calls/day, 1 user
Pro $29/mo 33 tools, 10K calls/day, priority support
Team $49/mo 33 tools, unlimited, 5 users, shared pipeline

Security

  • OAuth 2.1 with PKCE S256 (RFC 8414, 7591, 9728, 7009)
  • Database: Supabase EU (Frankfurt, Germany), SOC 2 Type II
  • Multi-tenant: Shared-table isolation with Row Level Security
  • Zero-Knowledge Credentials: AES-256-GCM encryption, browser-based entry
  • Input Validation: Zod schemas on all 33 tools
  • Audit Log: Every mutation tracked with tenant isolation

Built by StudioMeyer

AI agency from Mallorca. Building AI tools since 2024.


License

MIT — see LICENSE. This repository contains documentation only. The CRM server is hosted at crm.studiomeyer.io.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选