Nyne.ai MCP Server
Connect AI assistants like ChatGPT and Claude directly to Nyne.ai's people data workflows using the Model Context Protocol (MCP).
Model Context Protocol (MCP) is an open standard that enables AI assistants to securely connect to external data sources and tools - a universal plugin system for AI. The hosted Nyne.ai MCP Server brings Nyne.ai's common people search and enrichment workflows directly into your assistant conversations.
People Search
Semantic search across millions of profiles by company, role, location, or keywords.
Profile Enrichment
Comprehensive person profiles with contact info, work history, education, and socials.
AI-Powered Insights
Ask natural-language questions about profiles and get intelligent analysis.
Coverage
The hosted MCP exposes a curated subset of Nyne.ai workflows: people search, person enrichment, targeted lookup fields, person newsfeed, person Q&A, company search, and company enrichment. For the broader endpoint surface, point agents at the machine-readable docs first.
Available tools
person_search
Search for people by company, role, location, or keywords. Perfect for lead generation and talent discovery.
- Natural-language query or structured search inputs
- Cursor/request_id pagination support
- Up to 100 results per query
- Requires 'search' product access
Example: "Find software engineers at Google in San Francisco"
person_enrichment
Get detailed profile information for a person using email, phone, social profile URL, or name. Also the way to look up specific contact fields (best work email, mobile, headline, current company, photo URL): the profile already includes them.
- Lookup by email, phone, name, or social URL
- Comprehensive contact information (emails, mobile, title, headline, photo URL)
- Use for targeted field lookups: the result includes the individual fields
- Work history and education
- Social media profiles
- Requires 'enrichment' product access
Example: "Get the profile for [email protected]" or "Find the best work email and mobile for this LinkedIn URL"
person_newsfeed
Fetch recent social posts or activity for a social profile URL.
- LinkedIn URL alias support
- Optional date filtering
- Async polling via check_status
Example: "Show recent activity for this LinkedIn profile"
person_ask
Ask AI-powered questions about a person's profile using natural language.
- Natural language Q&A
- AI-powered analysis
- Context-aware answers
- Synthesizes multiple data points
- Requires 'enrichment' product access
Example: "What is this person's current role and experience?"
company_search
Search for companies by industry, website keyword, and location.
- Industry and keyword search
- Optional location filter
- Up to 50 results per query
Example: "Find AI companies in San Francisco"
company_enrichment
Enrich a company from domain, social URL, email, or phone.
- Domain lookup
- LinkedIn URL alias support
- Company profile enrichment
Example: "Enrich openai.com"
Why use Nyne.ai MCP?
Instant access
No code required. Connect once and query Nyne.ai data from ChatGPT or Claude.
Secure
Uses your existing Nyne.ai API credentials. All requests are authenticated and logged.
Natural language
Ask in plain English. The assistant handles the technical details.
Accurate
Real-time data from Nyne.ai's people intelligence workflows, no integration code.
Cost-effective
Uses your existing Nyne.ai subscription and credit balance. No additional fees.
Comprehensive
The hosted MCP is a curated subset; the full HTTP API is covered by llms.txt + the manifest.
Integration guides
ChatGPT
- Open ChatGPT and go to Settings → Connectors (custom connectors require Developer mode; Plus, Pro, Business, or Enterprise).
- Click Add custom connector.
- Enter the Nyne.ai MCP endpoint
https://api.nyne.ai/mcp. - When prompted for authentication, choose OAuth (recommended). The flow uses:
Authorization URL: https://api.nyne.ai/mcp/oauth/authorize Token URL: https://api.nyne.ai/mcp/oauth/token
- ChatGPT handles Dynamic Client Registration and sends the public OAuth
client_idduring token and refresh requests. - OAuth returns short-lived access tokens plus rotating refresh tokens so ChatGPT can silently renew access without asking you to log in again.
- Do not choose ChatGPT's Access token/API key Bearer option for Nyne API credentials. Nyne API credentials are a key/secret pair; ChatGPT's single Bearer field cannot send both values.
- If OAuth is unavailable, select No authentication only for discovery. Tool execution requires
OAuth or a client/proxy that can send
X-API-KeyandX-API-Secretheaders. - Click Save. ChatGPT discovers Nyne.ai tools from the manifest.
Claude Desktop
- Open or create the MCP configuration file at
~/.claude/mcp.json. - Add Nyne.ai to your configuration:
{ "mcpServers": { "nyne": { "url": "https://api.nyne.ai/mcp", "headers": { "X-API-Key": "your_nyne_api_key", "X-API-Secret": "your_nyne_api_secret" } } } } - Restart Claude Desktop. Nyne.ai tools are now available.
Other MCP clients
- Discovery endpoint:
https://api.nyne.ai/.well-known/mcp - MCP endpoint:
https://api.nyne.ai/mcp - OAuth authorization server metadata:
https://api.nyne.ai/.well-known/oauth-authorization-server - OAuth protected resource metadata:
https://api.nyne.ai/.well-known/oauth-protected-resource - Authentication: OAuth2 (recommended) via
/mcp/oauth/authorizeand/mcp/oauth/token; or theX-API-Key+X-API-Secretheaders.
Pricing & usage
Nyne.ai MCP uses your existing subscription and credit balance. MCP tools use the same credit costs as the REST API.
| Tool | Uses credits like | Required product |
|---|---|---|
| person_search | Person Search | Search |
| person_enrichment | Person Enrichment | Enrichment |
| person_newsfeed | Person Newsfeed | Enrichment |
| person_ask | Person Ask | Enrichment |
| company_search | Company Search | Search |
| company_enrichment | Company Enrichment | Enrichment |
Credit costs are dynamic
Async processing & polling
MCP tools use the same async request pattern as the REST API. Your assistant handles the polling automatically - you just ask naturally.
# 1. Call an MCP tool with JSON-RPC POST /mcp { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "person_search", "arguments": { "query": "software engineers at Google", "limit": 1 } } } # Response content text contains JSON like: { "request_id": "abc123...", "status": "pending", "endpoint": "person_search", "next_action": { "tool": "check_status", "args": { "request_id": "abc123...", "endpoint": "person_search" } } } # 2. Poll with check_status POST /mcp { "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "check_status", "arguments": { "request_id": "abc123...", "endpoint": "person_search" } } } # Response content while processing: { "status": "pending", "message": "Processing..." } # Response content when complete: { "status": "complete", "endpoint": "person_search", "request_id": "abc123...", "data": { "results": [] } }
Status & result shapes
Use the MCP check_status tool for assistant workflows. Terminal
success is complete in JSON-RPC MCP responses. The legacy GET /mcp/status route uses completed; both are terminal-success statuses.
| Tool | Completed result path |
|---|---|
| person_search | data.results |
| company_search | data.results |
| company_enrichment | data.result |
| person_enrichment | profile fields directly under data |
| person_ask | answer fields directly under data |
| person_newsfeed | data when found, or status=error with message |