IcePanel MCP

Live

OAUTH 2.0

DEVELOPER TOOLS

Developer Tools

Connect your IcePanel software architecture models to AI agents. Query and update your C4 model landscapes — systems, apps, components, connections, and...

  • Acts as the user: Every tool call runs as the authorizing user. Access and audit trail stay intact.
  • Credentials stay vaulted: AES-256 encrypted, resolved at request time, never stored in LLM context.
  • Scoped before every call: Per-user permissions enforced automatically. 90-day audit trail included.
IcePanel MCP
agent · Acme Q3
Run
Icepanel Createadr in IcePanel MCP
S
icepanelmcp_icepanel_createadr
85ms
IcePanel MCP agent
Create a new architecture decision record (adr) in the landscape..
Sources: IcePanel MCP
icepanelmcpmcp
1 tool call
18:29
Message Claude...

IcePanel MCP tools for AI agents

CALL ANY TOOL
12 tools covering icepanel.
icepanelmcp_icepanel_createadr
Create a new architecture decision record (adr) in the lands
Create a new architecture decision record (adr) in the landscape.
Parameters
Name
Type
Required
Description
name
string
Required
The title of the ADR.
content
string
Optional
The full content or body of the ADR. Markdown is supported.
description
string
Optional
A brief summary of the ADR.
icepanelmcp_icepanel_createconnection
Create a new connection between two model objects.
icepanelmcp_icepanel_createmodelobject
Create a new model object in the landscape. types 'actor' an
icepanelmcp_icepanel_getadrdetails
Get detailed information about a specific architecture decis
icepanelmcp_icepanel_getconnectiondetails
Get full details for a single connection including descripti
icepanelmcp_icepanel_getdiagramdetails
Get detailed information about a diagram including its objec
icepanelmcp_icepanel_getdomaindetails
Get detailed information about a specific domain including i
icepanelmcp_icepanel_getflowdetails
Get detailed information about a flow including its steps, o
icepanelmcp_icepanel_getmodelobjectdetails
Get detailed information about a model object including its
icepanelmcp_icepanel_getteamdetails
Get detailed information about a specific team including its
icepanelmcp_icepanel_gettechnologydetails
Get detailed information about a specific technology includi
icepanelmcp_icepanel_landscapesearch
Search across all landscape entities (model objects, connect
Build your Agent
Same auth pattern across every framework.
Python · LlamaIndex
from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="icepanelmcp")

mcp = MultiServerMCPClient({
"icepanelmcp": {
"url": "https://mcp.scalekit.com/icepanelmcp",
"headers": {"Authorization": "Bearer " + token}
}
})
tools = await mcp.get_tools()
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "icepanelmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/icepanelmcp
// Pass: Authorization: Bearer + token
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "icepanelmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/icepanelmcp
// Pass: Authorization: Bearer + token
from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="icepanelmcp")
# Connect to MCP at https://mcp.scalekit.com/icepanelmcp
# Pass: Authorization: Bearer + token
Try these prompts
Paste any prompt into your agent to get started.
Get started
Copy the prompt
Copied
List technologies from the catalog and organization?
Copy the prompt
Copied
List connections where a model object is the origin or target?
Advanced
Copy the prompt
Copied
Search across all landscape entities (model objects, connections, diagrams, flows) by name?
Copy the prompt
Copied
Update a connection in the landscape?
SEE HOW AUTH WORKS
User authorises once. Every agent call after uses their token with scope enforcement.
1
Authorize
Your user connects
IcePanel MCP
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
IcePanel MCP
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
IcePanel MCP
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
IcePanel MCP
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other connectors.
ENGINEERING
DevOps assistant agent
Triage GitHub incidents, open Linear tickets, and notify the on-call channel in Slack with context already attached.
ENGINEERING
Auto-release notes agent
Group merged GitHub PRs by feature, fix, or chore and publish release notes per tag. No manual changelog grooming.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
One connector today. Ten tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions

Does the agent access IcePanel as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the IcePanel OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in IcePanel?
Yes. Pass a tool name filter to listScopedTools so the DevOps agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches IcePanel.

What happens when a user revokes IcePanel access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent modify our C4 architecture model?
Only landscapes the authorizing user can edit in IcePanel. Model objects, connections, and ADRs created by the agent attribute to that user, keeping the architecture change history honest.

Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""icepanelmcp"": {
""url"": ""https://mcp.scalekit.com/icepanelmcp"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.icepanelmcp]
url = ""https://mcp.scalekit.com/icepanelmcp""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""icepanelmcp"": {
""url"": ""https://mcp.scalekit.com/icepanelmcp"",
""type"": ""http""
}
}
}