Model Context Protocol · Ships today

An MCP server, built into your gateway.

Every API contract you build on VectorFlowApp becomes a Model Context Protocol tool automatically. Claude, Cursor, Cline, and any MCP-compatible client can list and call your APIs through one endpoint — no extra code, no proprietary bridges.

JSON-RPC 2.0Protocol 2025-06-18tools/list + tools/callOrg-scopedZero-config per contract

What is the Model Context Protocol?

The Model Context Protocol (MCP) is an open standard that lets large-language-model clients discover and call external tools in a uniform way. Instead of writing bespoke function-calling adapters for every provider, you expose a single MCP endpoint; every MCP-aware client can find, inspect, and invoke what you publish.

VectorFlowApp ships an MCP server as part of the control plane. It automatically enumerates the API contracts in your organization and advertises each one as a callable tool — with input schema, operation metadata, and secure proxying back to your gateway. The LLM never talks to your gateway directly; it talks to MCP, and MCP routes to the gateway using the same policies you already configured.

Zero-config exposure

Every enabled contract is already an MCP tool. No manual registration.

Policy still applies

JWT, API keys, rate limits, and schema validation run before the tool call lands.

One server, many agents

Claude Desktop, Cursor, Cline, and any MCP client — the same URL works for all.

How the MCP server works

Three things happen in order: the client handshakes, enumerates your API contracts as tools, and invokes one. The gateway keeps owning auth, rate limits, and runtime — MCP is a thin control surface on top.

  1. 01

    initialize

    The MCP client POSTs a JSON-RPC initialize call. VectorFlowApp responds with protocolVersion 2025-06-18 and a capabilities block advertising tool support.

  2. 02

    tools/list

    The client requests the tool catalog. VectorFlowApp enumerates every enabled ApiContract in the org, converting each to an MCP tool with a stable name, description, and input schema derived from the contract's method and payload shape.

  3. 03

    tools/call

    The client invokes a named tool with arguments. VectorFlowApp resolves the tool back to its contract, assembles an HTTP request, forwards it through the gateway pipeline (policies first), and returns the response to the client as structured content.

Quickstart

Already running the gateway with at least one published API contract? You already have an MCP server. Here's how to point Claude Desktop or any MCP client at it.

1. Verify the endpoint responds

curl -X POST 'http://localhost:8080/management/api/v1/mcp?org=YOUR_ORG_ID' \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize"}' | jq .

2. Enumerate your tools

Every enabled contract in your org is listed. Each tool's name maps to a contract; the inputSchema describes what the LLM needs to pass in.

curl -X POST 'http://localhost:8080/management/api/v1/mcp?org=YOUR_ORG_ID' \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}' | jq '.result.tools'

3. Call a tool

curl -X POST 'http://localhost:8080/management/api/v1/mcp?org=YOUR_ORG_ID' \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc":"2.0","id":3,"method":"tools/call",
    "params":{
      "name":"DEMO__post_customers",
      "arguments":{"customer_name":"Ada","phone":"+1-555-0100"}
    }
  }'

4. Connect Claude Desktop

Add the server to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "vectorflow": {
      "url": "https://your-gateway.example.com/management/api/v1/mcp?org=YOUR_ORG_ID"
    }
  }
}

Restart Claude. Your API contracts appear in the tool picker.

Security model

The MCP server is a thin surface. All enforcement happens on the gateway — where you already set it up.

Org scoping

Every MCP request carries an org parameter. Only contracts owned by that organization are exposed. No cross-tenant leakage.

Policy runs first

A tool call is just an HTTP call internally. JWT auth, API keys, rate limits, and schema validation all execute before any connector step.

Secrets stay in your vault

Connector credentials resolved via Vault, AWS Secrets Manager, GCP Secret Manager, or Azure Key Vault — never passed through MCP.

Observability

Every MCP-initiated call lands in the same gateway metrics stack. Trace IDs, request durations, and errors are visible in Prometheus and Grafana.

What teams build with it

Internal AI assistants

Give Claude or an in-house agent the ability to read customers, open support tickets, and fetch inventory — through your existing API contracts, with your policies.

Agentic workflows

Chain MCP tool calls inside a VectorFlowApp flow. The LLM decides which tool to call; the gateway executes it; the response feeds the next step.

Customer-facing copilots

Expose a curated subset of contracts under a partner-scoped MCP endpoint. The customer's AI agent only sees the tools you permit.

Developer accelerators

Cursor and other coding tools can read schemas, test endpoints, and generate client code against your gateway — no local SDK generation step.

Technical details

Protocol version
2025-06-18
Transport
HTTP POST, JSON-RPC 2.0
Methods
initialize, tools/list, tools/call, ping
Tool name shape
<partner>__<method>_<resource>
Execution
Proxied to the gateway contract pipeline
Isolation
Per-org; scoped via ?org= query param
Auth to gateway
JWT, API keys, schema policies — as configured
Spec
github.com/modelcontextprotocol/specification

Frequently asked questions

Do I need to write any code to expose a contract?+

No. Every enabled contract in your organization is automatically listed by tools/list. You disable exposure by disabling the contract.

Which MCP clients work?+

Any client that speaks protocol version 2025-06-18. Confirmed: Claude Desktop, Cursor, Cline. Any client that correctly implements the three methods above will work.

How do I restrict which tools are exposed?+

Via contract-level flags and the org scope. Per-partner MCP endpoints are planned; the current MVP exposes all enabled contracts in the specified org.

What happens to rate limits and auth?+

Unchanged. A tool call runs through the identical gateway pipeline as any HTTP request. Your JWT verification, API key rate limits, and schema validation apply exactly as they already do.

Can I use this in production today?+

The MCP endpoint ships enabled by default. We recommend running it behind an authenticated reverse proxy for production (the gateway's /management surface is admin-only by design).

How does this compare to OpenAI function calling?+

MCP is client-agnostic — Claude, Cursor, and any future MCP-aware runtime use the same server. OpenAI function calling is a provider-specific protocol you'd implement per-client. MCP's tool list is also discoverable at runtime; function-call schemas are static per request.

Ready to build flows & datalines?

Tell us about the systems you connect and the automations you need. We will walk through what VectorFlowApp ships today and how it fits your stack.