BIDIRECTIONAL MCP · AGENT GOVERNANCE

Your business talks to AI. And AI talks to your systems.

Cord's MCP is no longer a one-way street. Cord is a server: an AI like Claude queries your AR and builds quotes using 7 tools. And Cord is a client: it connects to your CRM or ERP's MCP servers, under permissions you sign off on. You decide who touches what.

Start for free Ver planes

Available on all plans · uses the same API key (more active keys as you upgrade; live consumption is metered by use)

Claude · AI
overdue_invoices
Cord
✓
Your CRM / ERP
1 AI invokes one of your 7 tools
2 Cord queries your CRM, with permission
3 Context returns to the conversation
4 AI builds the quote with that context
tools Cord exposes to AI via JSON-RPC 7
inbound transports: stateless HTTP and session HTTP/SSE 2
max agent loop iterations before quoting (safety limit) 5

CORD AS A SERVER

7 tools. Two ways to connect.

Connect Cord to an assistant like Claude and the AI works with your real data: checks the pipeline, finds overdue accounts, looks up a client, or drafts a quote. There are two entry doors: JSON-RPC 2.0 over stateless HTTP at /api/mcp, where the 7 tools live; and an HTTP/SSE channel with session at /api/mcp/sse + /api/mcp/message. Both authenticate with your API key and respect each tool's scope.

  • The 7 tools run inside your org — the AI queries, it doesn't make things up
  • Write actions require a key with write permission
  • The SSE session is tied to your org_id: every query respects your RLS
JSON-RPC 2.0
Cord como servidor
HTTPSSE
listar_cotizaciones
cartera_vencida
resumen_negocio
buscar_cliente
listar_productos
detalle_cotizacion
crear_cotizacion_borradorwrite

CORD AS A CLIENT

Cord also queries your client's systems.

Flip the arrow. You register the URL of your CRM or ERP's MCP servers and Cord connects to them as a client. When you build a quote with AI, the agent loop at /api/cotizaciones/ai-draft first asks those remote systems —a client's balance, last order, agreed conditions— and then builds the lines with that context. Up to 5 loops max, and it closes every connection when done.

  • Connects via SSE injecting each remote server's authorization token
  • Each external tool is prefixed by server to prevent collisions
  • The agent loop interleaves your tools and remote ones in a single conversation
max 5 vueltas
Cord como cliente
Cord
CRM
conectando…
listTools() → 4 tools
contexto recibido ✓

AGENT GOVERNANCE

Each agent touches only what you sign off on.

No open access. Each org has a default agent, the Cord Assistant, and a permissions table dictating which external servers it can connect to. If a server isn't on its allowlist, the agent doesn't even see it. Everything lives with Row Level Security in the database: every query filters by your org_id and no one crosses data between businesses.

  • Register and toggle MCP servers in Settings › Developers
  • Grant or revoke the agent's permission per server, instantly
  • RLS on mcp_servers, agentes_ia, and agentes_permisos: org isolation
RLS · por org
GobernanzaAsistente Cord
Servidor A · ventaspermitido
CRM externosin acceso
Servidor C · finanzassin acceso

EN TRES PASOS

Listo en minutos, no en semanas.

1
Generate your key The same API key from Settings › Developers › API. One key works for the REST API and inbound MCP.
2
Connect the server Add https://cord.flouvia.com/api/mcp in your AI client with the authorization header. For session streaming, use the SSE channel.
3
Register and allow Add your CRM or ERP's MCP server URL and grant your agent access to them. The AI now queries your systems before quoting.
REST API REST API Cord stops being just a screen for humans and becomes a system your other systems can talk to.

START TODAY

Connect AI to your business.
In both directions.

Same header, same key. Expose your 7 tools and link your systems with permissions you control.

Start for free

No credit card required · Free plan forever