namakan-mcp-crm
Provides CRM integration with HubSpot as a backend, allowing AI agents to search contacts and accounts, list and retrieve deals, create deals, and log activities through unified MCP tools.
Provides CRM integration with Salesforce as a backend, allowing AI agents to search contacts and accounts, list and retrieve deals, create deals, and log activities through unified MCP tools.
Provides CRM integration with Zoho as a backend, allowing AI agents to search contacts and accounts, list and retrieve deals, create deals, and log activities through unified MCP tools.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
namakan-mcp-crm
Internal MCP server: one CRM tool surface for Namakan agents. They call crm_find_contact whether the plant runs HubSpot, Salesforce, Dynamics, Pipedrive, or Zoho.
The client never configures MCP. integration-engineer (and delivery-manager, solution-architect, data-engineer, agent-systems-engineer) get this server from bootstrap. Writes stay off until ciso approves.
How agents connect
mcp_servers:
namakan-mcp-crm:
command: uvx
args:
- --from
- git+https://github.com/cfollette18/namakan-mcp-crm.git
- namakan-mcp-crm
- serve
env:
NAMAKAN_CRM_BACKEND: mock
trust: fullSwap NAMAKAN_CRM_BACKEND per engagement in clients/<slug>/ config — never by teaching the agent a vendor API.
Related MCP server: ai-crm-engine
Architecture
Full AI workflow
Playbook path (playbooks/phase-2-erp-crm-automation.md):
integration-engineeris assigned the connector card.Agent calls
crm_run_workflow(or the individualcrm_*tools).The last step is a blocked write. That is the demo, not a failure.
Production writes require
NAMAKAN_MCP_ALLOW_WRITES=1, dry-run, andciso.
Demo without an agent process:
namakan-mcp-crm workflowExpected: four JSON steps. Last step "error": "writes_disabled".
Tools
Tool | Read/write | Arguments |
| read |
|
| read |
|
| read |
|
| read |
|
| write |
|
| write |
|
| read + blocked write |
|
Potential use cases
Use case | Which agent | Why it matters |
Who owns this account? |
| Same tool on HubSpot today and Salesforce after a migration. |
Open Phase 2 pipeline |
| Mock data ships; no token needed to rehearse the call. |
Log the plant visit |
| Stays blocked until writes are enabled and |
use_case: who-owns-account (default), open-pipeline, log-plant-visit.
Tests
pip install -e ".[dev]"
pytestLicense
MIT. Copyright (c) 2026 Namakan AI Engineering.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
AI agent platform: manage leads, conversations, bots, calendar and CRM via MCP.
CRM + visual automation builder AI agents can drive via MCP: contacts, tags, maps, email/SMS flows.
Native MCP access to CRM contacts, organizations, deals and tasks with user permissions.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to interact with Bitrix24 CRM through standardized MCP tools, including searching and managing contacts, deals, leads, tasks, and replying in chats.MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP-native CRM backend for AI agents, enabling customer, opportunity, note, follow-up, and pipeline health management through 15 MCP tools.-
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to read and write CRM data—companies, contacts, opportunities, tasks, and interactions—through MCP, with OAuth and provenance tracking for every value.MIT
- AlicenseAqualityCmaintenanceEnables AI agents to perform go-to-market workflows such as company and contact enrichment, CRM querying, and controlled, audited writes to a CRM through MCP tools callable from any MCP client.1MIT