{
  "markdown": "# Nynch MCP Server\n\nA hosted [Model Context Protocol](https://modelcontextprotocol.io) server that gives AI agents full access to **Nynch** — a relationship-led growth platform for consultants and professional services firms.\n\n**47 tools** across 5 categories: CRM read, CRM write, relationship intelligence, context query, and multi-agent orchestration.\n\n## Endpoint\n\n```\nhttps://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server\n```\n\n**Transport:** 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`.\n\n## Quick Start\n\n### 1. Get an API Key\n\nSign up at [nynch.com](https://nynch.com), then go to **Settings → Integrations → Claude & AI Assistants** and create an API key.\n\n**Scopes:**\n- `read` — Search, browse, and retrieve data\n- `read-write` — Read + create, update, delete records\n- `admin` — Full access including agent orchestration\n\n### 2. Configure Your Client\n\n#### Claude Desktop\n\nAdd to `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"nynch\": {\n      \"url\": \"https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n#### Cursor\n\nAdd to `.cursor/mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"nynch\": {\n      \"url\": \"https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server\",\n      \"headers\": {\n        \"Authorization\": \"Bearer YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\n#### Python (MCP SDK)\n\n```python\nfrom mcp import ClientSession\nfrom mcp.client.streamable_http import streamablehttp_client\n\nasync with streamablehttp_client(\n    \"https://crcrwtjzqzinfzokianr.supabase.co/functions/v1/mcp-server\",\n    headers={\"Authorization\": \"Bearer YOUR_API_KEY\"}\n) as (read, write, _):\n    async with ClientSession(read, write) as session:\n        await session.initialize()\n        result = await session.call_tool(\"search_contacts\", {\"query\": \"Acme Corp\"})\n        print(result)\n```\n\n### 3. Start Using Tools\n\nYour AI client discovers available tools automatically. Ask it to search contacts, check your pipeline, create tasks, or analyze relationships.\n\n## Tool Catalog\n\n### CRM Read (11 tools)\n\n| Tool | Description |\n|------|-------------|\n| `search_contacts` | Search contacts by name, company, or tags |\n| `get_contact_context` | Full contact context: profile, interactions, activities, notes, network |\n| `search_deals` | Search deals by title, stage, or company |\n| `get_deal_context` | Full deal context: stakeholders, learnings, coaching actions |\n| `search_deals_by_inactivity` | Find stalled deals with no recent activity |\n| `get_pipeline_summary` | Pipeline health: stage distribution, at-risk deals, upcoming closes |\n| `get_next_best_actions` | AI-powered recommendations for what to do next |\n| `get_who_list` | People to reach now, including identified site visitors. Never mention a specific page in outreach |\n| `list_buckets` | List all buckets (lists/segments) |\n| `get_bucket_contacts` | Get contacts in a specific bucket |\n| `get_bucket_game_queue` | Get contacts waiting to be sorted into buckets |\n\n### CRM Write (12 tools)\n\n| Tool | Description |\n|------|-------------|\n| `log_interaction` | Record a contact interaction (call, email, meeting, note) |\n| `update_deal_stage` | Move a deal to a new pipeline stage |\n| `create_task` | Create a task linked to a contact or deal |\n| `create_note` | Add a note to a contact (supports markdown) |\n| `create_contact` | Create a new contact (auto-links to company by domain) |\n| `update_contact` | Update fields on an existing contact |\n| `add_contact_to_bucket` | Add a contact to a bucket |\n| `create_deal` | Create a new deal in the pipeline |\n| `create_company` | Create a new company |\n| `delete_contact` | Soft-delete a contact (recoverable) |\n| `bulk_delete_contacts` | Soft-delete contacts by tag or ID list |\n| `update_commitment` | Mark a commitment as completed or update details |\n\n### Relationship Intelligence (11 tools)\n\n| Tool | Description |\n|------|-------------|\n| `get_authority_score` | Authority score across 6 dimensions |\n| `get_commitments` | Commitments with Say/Do tracking and due dates |\n| `get_buying_committee` | Stakeholder map: roles, influence, sentiment |\n| `get_contact_signals` | Job changes, company changes, buying intent, identified website visits (no page paths) |\n| `get_interaction_history` | Full interaction timeline with direction and sentiment |\n| `get_relationship_score` | 5-factor relationship strength score |\n| `export_context_briefing` | AI-ready context briefing for any contact or deal |\n| `get_relationship_trends` | Is engagement growing, stable, or declining? |\n| `get_at_risk_relationships` | Contacts with dropping scores or no recent contact |\n| `get_deal_intelligence` | Deal health: velocity, stakeholder coverage, risk factors |\n| `get_weekly_briefing` | Weekly summary: interactions, changes, recommendations |\n\n### Agent Orchestration (8 tools)\n\n| Tool | Description |\n|------|-------------|\n| `register_agent` | Register an external agent with capabilities and archetype |\n| `list_agents` | List registered agents with status |\n| `agent_heartbeat` | Confirm agent liveness |\n| `write_context` | Write to the shared agent context store |\n| `read_context` | Read from context store (supports prefix wildcards) |\n| `create_handoff` | Request another agent to perform a task |\n| `get_handoffs` | Get pending handoffs for your agent |\n| `complete_handoff` | Mark a handoff as completed or failed |\n\n### Context Query (5 tools)\n\nDiscover and read bounded slices of Nynch and connected-app context, metadata-first. Read-only — never accepts raw SQL.\n\n| Tool | Description |\n|------|-------------|\n| `list_context_sources` | List safe read-only context sources available to you |\n| `search_context_sources` | Search context sources by natural-language keyword (metadata only) |\n| `describe_context_source` | Describe one source: purpose, columns, filters, limits, availability |\n| `list_context_columns` | List selectable columns and allowed filters for one source |\n| `query_context` | Read a bounded slice from one source via a constrained query object |\n\n## MCP Resources\n\n| URI Template | Description |\n|---|---|\n| `nynch://contacts/{id}` | Full contact context: profile, score, interactions, network |\n| `nynch://deals/{id}` | Deal context: details, stakeholders, coaching actions |\n| `nynch://pipeline/summary` | Pipeline health overview |\n\n## Agent Orchestration\n\nNynch supports multi-agent workflows where AI agents register, share context, and hand off tasks:\n\n- **Register** with a name, capabilities, and archetype (producer, consumer, coordinator, critic)\n- **Share state** via a key-value context store with namespaces and TTLs\n- **Route tasks** by agent name or capability matching\n- **Track liveness** with heartbeats\n\n## Rate Limits\n\n- 1,000 requests per hour per API key\n\n## Documentation\n\nFull developer documentation: [nynch.com/developers](https://nynch.com/developers)\n\n## About Nynch\n\n[Nynch](https://nynch.com) 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.\n\n## License\n\nThis repository (documentation and configuration) is released under the [MIT License](./LICENSE). The Nynch MCP Server itself is a hosted service — no local installation required.\n",
  "bytes": 7543,
  "sha": "1c457d180caf43730893cfd6aeeff7c1cae40378c16c712dc71d26accae1651d",
  "repo_slug": "peterod99/nynch-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_peterod99_nynch_9a1ff01c/readme"
}