Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Nynch MCP Server who should I contact today?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A hosted Model Context Protocol server that gives AI agents full access to Nynch — a relationship-led growth platform for consultants and professional services firms.
47 tools across 5 categories: CRM read, CRM write, relationship intelligence, context query, and multi-agent orchestration.
https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-serverTransport: JSON-RPC 2.0 over Streamable HTTP. The server is stateless (no session to manage) and negotiates the protocol version with your client — it speaks 2025-11-25, 2025-06-18, and 2025-03-26.
Related MCP server: Lofty MCP Server
Sign up at nynch.com, then go to Settings → Integrations → Claude & AI Assistants and create an API key.
Scopes:
read — Search, browse, and retrieve data
read-write — Read + create, update, delete records
admin — Full access including agent orchestration
Add to claude_desktop_config.json:
{
"mcpServers": {
"nynch": {
"url": "https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}Add to .cursor/mcp.json:
{
"mcpServers": {
"nynch": {
"url": "https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client
async with streamablehttp_client(
"https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server",
headers={"Authorization": "Bearer YOUR_API_KEY"}
) as (read, write, _):
async with ClientSession(read, write) as session:
await session.initialize()
result = await session.call_tool("search_contacts", {"query": "Acme Corp"})
print(result)Your AI client discovers available tools automatically. Ask it to search contacts, check your pipeline, create tasks, or analyze relationships.
Tool | Description |
| Search contacts by name, company, or tags |
| Full contact context: profile, interactions, activities, notes, network |
| Search deals by title, stage, or company |
| Full deal context: stakeholders, learnings, coaching actions |
| Find stalled deals with no recent activity |
| Pipeline health: stage distribution, at-risk deals, upcoming closes |
| AI-powered recommendations for what to do next |
| People to reach now, including identified site visitors. Never mention a specific page in outreach |
| List all buckets (lists/segments) |
| Get contacts in a specific bucket |
| Get contacts waiting to be sorted into buckets |
Tool | Description |
| Record a contact interaction (call, email, meeting, note) |
| Move a deal to a new pipeline stage |
| Create a task linked to a contact or deal |
| Add a note to a contact (supports markdown) |
| Create a new contact (auto-links to company by domain) |
| Update fields on an existing contact |
| Add a contact to a bucket |
| Create a new deal in the pipeline |
| Create a new company |
| Soft-delete a contact (recoverable) |
| Soft-delete contacts by tag or ID list |
| Mark a commitment as completed or update details |
Tool | Description |
| Authority score across 6 dimensions |
| Commitments with Say/Do tracking and due dates |
| Stakeholder map: roles, influence, sentiment |
| Job changes, company changes, buying intent, identified website visits (no page paths) |
| Full interaction timeline with direction and sentiment |
| 5-factor relationship strength score |
| AI-ready context briefing for any contact or deal |
| Is engagement growing, stable, or declining? |
| Contacts with dropping scores or no recent contact |
| Deal health: velocity, stakeholder coverage, risk factors |
| Weekly summary: interactions, changes, recommendations |
Tool | Description |
| Register an external agent with capabilities and archetype |
| List registered agents with status |
| Confirm agent liveness |
| Write to the shared agent context store |
| Read from context store (supports prefix wildcards) |
| Request another agent to perform a task |
| Get pending handoffs for your agent |
| Mark a handoff as completed or failed |
Discover and read bounded slices of Nynch and connected-app context, metadata-first. Read-only — never accepts raw SQL.
Tool | Description |
| List safe read-only context sources available to you |
| Search context sources by natural-language keyword (metadata only) |
| Describe one source: purpose, columns, filters, limits, availability |
| List selectable columns and allowed filters for one source |
| Read a bounded slice from one source via a constrained query object |
URI Template | Description |
| Full contact context: profile, score, interactions, network |
| Deal context: details, stakeholders, coaching actions |
| Pipeline health overview |
Nynch supports multi-agent workflows where AI agents register, share context, and hand off tasks:
Register with a name, capabilities, and archetype (producer, consumer, coordinator, critic)
Share state via a key-value context store with namespaces and TTLs
Route tasks by agent name or capability matching
Track liveness with heartbeats
1,000 requests per hour per API key
Full developer documentation: nynch.com/developers
Nynch is a relationship-led growth platform that helps consultants and professional services firms turn relationships into revenue. It combines CRM, relationship intelligence, and AI-powered coaching into a single platform.
This repository (documentation and configuration) is released under the MIT License. The Nynch MCP Server itself is a hosted service — no local installation required.
This server cannot be deployed
Run B2B outreach from your AI agent: 250+ tools for campaigns, leads, LinkedIn and email workflows.
Global B2B intelligence for AI agents: 35M+ companies, 1.6M sanctions, KYB pack. 78 tools.
Agent-native CRM. 25 tools — contacts, deals, sequences, enrichment waterfall, audit log.
Give your AI agents the tools to build, manage, and run automation workflows.
