nextiva-mcp

nextiva-mcp

MCP server for Nextiva (contact center platform, built on the acquiredThrio product — API host is login.thrio.com / *.thrio.io). Exposesthe Thrio data and analytics API's users, campaigns, contacts, queues, andwork item history as MCP tools.

Naming note: MSPbots' own integration is registered as "Nextiva"(subjectCode=NEXTIVA); the underlying API and all documentationreference "Thrio", the contact-center product Nextiva acquired. This MCPcovers exactly the 5 methods MSPbots itself has configured.

MSPbots Connector gives your AI clients one MCP URL to reach your entire MSP stack (RMM, PSA, documentation, security, finance), and gives you control over who can call which tool and a record of everything that was called.

Hosted service: connect.mspbots.ai · Free to use.

Why Connector

Quick start

1. Sign up at connect.mspbots.ai.
2. Connect your vendors. Pick from 150+ connectors and authorize each one on the vendor's own page, or bring your own API keys. No extra vendor accounts needed.
3. Set access. Create roles and decide which tools each role may call. Nothing is allowed until you allow it.
4. Add your MCP URL to your AI client. Copy the URL from your Connector dashboard into Claude, ChatGPT, Cursor, VS Code, Gemini, Codex, or any MCP-capable client.
5. Ask your AI to do real work, and watch every call appear in the audit log.

Features

Unified gateway

• One MCP URL for all your AI clients
• 150+ connectors across the MSP stack
• Custom MCP servers supported, free
• Authorization happens on each vendor's own page; the AI never sees passwords or tokens
• Bring your own credentials: use the vendor API keys you already have
• Multiple accounts per app; connect once, reuse across AI clients
• Tool search: finds the right action for the task
• One sign-in; vendor credentials are injected behind the scenes and OAuth tokens refresh automatically

Visibility

• Audit log for every tool call (who, which vendor, when)
• Usage dashboard: call volume, top vendors, error rate, per-user activity
• Export audit logs to CSV, or stream to Loki, Graylog, or LogScale (SIEM)
• Optional recording of tool arguments and result summaries (off by default, enabled per organization)

Control

• Per-role, per-tool allowlist, deny by default
• owner / admin / member roles
• SCIM provisioning with Entra ID, Okta, JumpCloud, and Google Workspace

Security

• Credentials encrypted one record at a time (AES-256-GCM, per-record key)
• AI clients authenticate with OAuth 2.1 + PKCE
• Vendor responses are scanned for prompt-injection patterns and returned as structured data. This is one layer of defense, not a guarantee against every attack.
• Static egress IP for customer firewall and API allowlisting

Pricing

Free.

Links: connect.mspbots.ai · mspbots.ai

Overview

• Stateless HTTP service. No credentials are ever persisted — each requestsupplies its own username/password via headers, used only for thelifetime of that single request.
• Supports concurrent requests; per-request credential isolation is done viaPython contextvars, not a global/shared client instance.
• Entry points: POST /mcp (MCP protocol) and GET /health (health check).
• Default port: 8080 (configurable via MCP_HTTP_PORT).

Authentication

Thrio's auth call returns both a token and the actual per-tenant APIhost to use — Thrio is deployed across multiple regional clusters, sothere is no single fixed data-plane hostname:

1. GET https://login.thrio.com/provider/token-with-authorities withHTTP Basic Auth (username:password) → {"location": "https://<tenant-cluster>.thrio.io", "token": "..."}.
2. Every real data/analytics call then goes to {location} (notlogin.thrio.com) with the token sent as-is in an Authorizationheader — no Bearer prefix.

Since there is no session to preserve, this server re-authenticates freshon every single tool call — nothing is cached or persisted across MCPrequests.

HEADER authentication parameters

Missing either header returns 401:

{
  "error": "Missing credentials",
  "message": "This server requires the X-Nextiva-Username and X-Nextiva-Password headers",
  "required_headers": ["X-Nextiva-Username", "X-Nextiva-Password"],
  "optional_headers": []
}

An invalid username/password surfaces as a tool-level error during theinternal login step, not an HTTP-level error from this server.

Environment Variables

MCP Endpoint

• POST /mcp — MCP protocol (streamable HTTP transport)
• GET /health — health check, returns {"status": "ok"} (pure local probe, does not call the Nextiva/Thrio API)

Tool List

All 5 tools are read-only (readOnlyHint=True, idempotentHint=True); there are no write/delete tools.

Per-parameter documentation lives on each tool's parameter schema (visible via tools/list), not in this table — this table is a quick-reference only and parameter names here are kept in sync with the code.

Successful responses are the vendor's JSON, compactly serialized (nopretty-printing, ensure_ascii=False) and capped at ~20,000 characters —an oversized list response is truncated with truncated/original_countmarkers rather than returned in full. There is no vendor-documentedlimit/page-size parameter for these endpoints (pagination is a startoffset only, see Known Gaps below), so there is nothing to clamp beyondthis automatic character cap.

Errors are returned as a JSON error envelope (not an exception/HTTPerror), e.g.:

{"error": {"code": "upstream_error", "message": "...", "retryable": true}}

code is one of not_configured / unauthorized / not_found /invalid_argument / rate_limited / upstream_error, mapped from theThrio API's HTTP status code (see error_envelope/NextivaError.to_envelopein api_client.py). Outbound calls use a 5s connect / 30s read timeout,and retry up to 3 times with capped exponential backoff on 429/5xxresponses (respecting Retry-After).

Test Example

# Health check
curl -s http://localhost:8080/health

# Call a tool via the MCP protocol (streamable HTTP) — requires an
# initialize handshake first per the MCP spec; abbreviated example below
# shows the tool-call request body only:
curl -s -X POST http://localhost:8080/mcp \
  -H "X-Nextiva-Username: [email protected]" \
  -H "X-Nextiva-Password: <your-password>" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "mcp-session-id: <session-id-from-initialize>" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "nextiva_get_users",
      "arguments": {}
    }
  }'

Live-verified (2026-07-30) against a real Nextiva/Thrio tenant, all 5tools called end-to-end through this running server: nextiva_get_usersreturned 101 real users; nextiva_get_campaigns returned 9 real campaigns(e.g. "Nextiva - Transfers"); nextiva_get_contacts returned 99 realcontacts; nextiva_get_queues returned 18 real queues; andnextiva_get_workitems_history returned real summary totals (e.g.297 inbound, 195 outbound, 500 contacts in the last 7 days) — all withthe login step resolving the tenant's real cluster host dynamically(https://mancity.thrio.io).

API Reference

• Public, no login required: https://api.thrio.com/ (Postman-generateddocumentation covering Authentication, Objects/Data API, Analytics, andmore)

Known Gaps

• Scope is exactly MSPbots' 5 configured endpoints, not the vendor'sfull API surface — Thrio's API also covers Workitem actions, ListManagement, Dashboards, Recordings, Contact Consent, State DID, Chat,CRM, Client, Number Verification, WFM, TEAMS, Callbacks, and more (perthe public docs' own navigation); those are out of scope here.
• Pagination is a start offset, confirmed empirically (passingstart=1 shifted the result window by one and updated the response'sprevious field accordingly) — the vendor's public docs describe thisless explicitly than the request/response shape actually demonstrates,so this was verified against the live API rather than assumed from thedocs alone.
• The session/login step described in the vendor's docs (POST {location}/users/api/login) is NOT used by this server — it appearednecessary only for creating a full interactive agent session (e.g. fortelephony/ACD state), not for the read-only data/analytics endpointsMSPbots uses, which worked correctly with just the Authenticationtoken. Confirmed by successfully calling all 5 endpoints without it.