Skip to main content

​
What is MCP?

The Model Context Protocol (MCP) is an open standard created by Anthropic that lets AI agents connect to external data sources and tools in a structured, secure way. Instead of an AI agent relying solely on its training data, MCP allows it to query live, up-to-date context from any MCP-compatible server. SIMCEL exposes two MCP integrations:
MCP ServerWhat it provides
Docs MCP (via Mintlify)Your AI agent can read all of developers.simcel.io as context — API docs, guides, examples
Data MCP (coming soon)Your AI agent can call SIMCEL Insights API endpoints directly as MCP tools

​
Docs MCP — Connect your agent to SIMCEL documentation

The SIMCEL developer portal is automatically available as an MCP server. This means any MCP-compatible AI agent (Claude, Cursor, custom GPT agent) can query the full documentation without scraping or manual context injection.

​
Endpoint

https://developers.simcel.io/mcp

​
Configure in Claude Desktop

Add this to your claude_desktop_config.json: 
{
  "mcpServers": {
    "simcel-docs": {
      "url": "https://developers.simcel.io/mcp"
    }
  }
}

​
Configure in Cursor

Add this to your .cursor/mcp.json: 
{
  "mcpServers": {
    "simcel-docs": {
      "url": "https://developers.simcel.io/mcp"
    }
  }
}

​
Configure in a custom agent (Python)

import anthropic

client = anthropic.Anthropic()

# The agent can now query SIMCEL docs as a tool
response = client.beta.messages.create(
    model="claude-opus-4-5",
    max_tokens=1024,
    mcp_servers=[
        {
            "type": "url",
            "url": "https://developers.simcel.io/mcp",
            "name": "simcel-docs",
        }
    ],
    messages=[
        {
            "role": "user",
            "content": "How do I call the SIMCEL P&L endpoint and compare two scenarios?"
        }
    ],
    betas=["mcp-client-2025-04-04"],
)

print(response.content)

​
What the agent can do with Docs MCP

Once connected, your agent can answer questions like:
  • “What parameters does the Demand endpoint accept?”
  • “Show me a Python example for fetching P&L data”
  • “What does ebitPercent mean in the P&L response?”
  • “What are the rate limits for the Growth plan?”
The agent reads the live docs, so it always has up-to-date information — including any new endpoints or parameter changes you publish.

​
Data MCP — Call SIMCEL API as agent tools (Coming Soon)

The SIMCEL Data MCP server is under development. It will allow AI agents to call the Insights API directly as MCP tools — no manual HTTP calls required.
When available, the Data MCP will expose tools like: 
simcel_get_pnl_summary(planId, scenarioIds, interval, currency)
simcel_get_demand_forecast(planId, scenarioIds, interval, groupBy)
simcel_list_scenarios(planId)
An agent will be able to answer questions like:
“What is our EBIT margin in the Optimistic scenario vs Committed for FY2025?”
…and call the SIMCEL API automatically to fetch the answer — with no code from the user. Join the waitlist to be notified when the Data MCP is available.

​
Why MCP matters for SIMCEL integrations

Traditional API integrations require developers to write HTTP clients, handle auth, parse responses, and format data for the LLM. MCP eliminates all of that:
Without MCPWith MCP
Write HTTP client codeZero integration code
Manually inject API docs into promptsAgent reads docs automatically
Re-prompt when API changesAgent always reads latest docs
Handle token refresh manuallyMCP handles auth context
One agent per integrationOne agent, many MCP servers
For supply chain AI agents specifically, this means you can connect SIMCEL, your ERP, and your BI tool to the same agent — and it reasons across all three sources simultaneously.