Platform MCP Server

Works with MCP, LangChain, OpenAI Agents, Claude Agent SDK, and 15+ more.

Remote serverstreamable-httpPython

What is the Platform MCP server?

Works with MCP, LangChain, OpenAI Agents, Claude Agent SDK, and 15+ more. The platform mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

Its toolset

Everything the assistant can do here goes through one of these:

  • MCP-native — governance proxy for any MCP server
  • Framework-agnostic — LangChain, Vercel AI, OpenAI, CrewAI, Pydantic AI, Composio, Claude Agent SDK, Google ADK, LlamaIndex, NemoClaw, or plain functions
  • RBAC — admin, reviewer, viewer roles with enforced permissions
  • Webhooks — real-time notifications for approvals, traces, lifecycle events
  • Self — serve signup** — GitHub, Google, email/password
  • Emailadmin@example.com / Password: admin
  • Integrations — MCP, OpenClaw, NemoClaw, LangChain, OpenAI, Claude Agent SDK, Google ADK, Copilot Studio, GitHub Copilot, and more
  • Compliance — 🇺🇸 FINRA · 🇪🇺 EU AI Act · 🇨🇭 FINMA · 🇸🇬 MAS TRM · 🇺🇸 NIST AI RMF · 🌐 OWASP
  • Website — Documentation
  • Dashboard — TypeScript SDK (npm)
  • create-sidclaw — app (npm)
  • Approach — What it solves

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need 6 environment variables: SIDCLAW_API_KEY, SIDCLAW_AGENT_ID, SIDCLAW_UPSTREAM_CMD, SIDCLAW_UPSTREAM_ARGS, SIDCLAW_BASE_URL, NEXT_PUBLIC_API_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Platform's toolset — MCP-native, Framework-agnostic, RBAC and 11 more — is a fair guide to whether it matches your workflow. It is maintained by sidclawhq; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Platform.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the platform mcp server does with a few real requests.

Available tools

ToolWhat it does
MCP-nativegovernance proxy for any MCP server
Framework-agnosticLangChain, Vercel AI, OpenAI, CrewAI, Pydantic AI, Composio, Claude Agent SDK, Google ADK, LlamaIndex, NemoClaw, or plain functions
RBACadmin, reviewer, viewer roles with enforced permissions
Webhooksreal-time notifications for approvals, traces, lifecycle events
Selfserve signup** — GitHub, Google, email/password
Emailadmin@example.com / Password: admin
IntegrationsMCP, OpenClaw, NemoClaw, LangChain, OpenAI, Claude Agent SDK, Google ADK, Copilot Studio, GitHub Copilot, and more
Compliance🇺🇸 FINRA · 🇪🇺 EU AI Act · 🇨🇭 FINMA · 🇸🇬 MAS TRM · 🇺🇸 NIST AI RMF · 🌐 OWASP
WebsiteDocumentation
DashboardTypeScript SDK (npm)
create-sidclawapp (npm)
ApproachWhat it solves
SidClawAll of the above, plus the **Approval** primitive
LangChain@sidclaw/sdk/langchain

How to install the Platform MCP server

{
  "mcpServers": {
    "postgres-governed": {
      "command": "npx",
      "args": ["-y", "@sidclaw/sdk", "sidclaw-mcp-proxy", "--transport", "stdio"],
      "env": {
        "SIDCLAW_API_KEY": "ai_your_key",
        "SIDCLAW_AGENT_ID": "your-agent-id",
        "SIDCLAW_UPSTREAM_CMD": "npx",
        "SIDCLAW_UPSTREAM_ARGS": "-y,@modelcontextprotocol/server-postgres,postgresql://localhost/mydb"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
SIDCLAW_API_KEYCredential the server authenticates with.Yes
SIDCLAW_AGENT_IDConfiguration value read at startup.Optional
SIDCLAW_UPSTREAM_CMDConfiguration value read at startup.Optional
SIDCLAW_UPSTREAM_ARGSConfiguration value read at startup.Optional
SIDCLAW_BASE_URLEndpoint or connection string the server talks to.Yes
NEXT_PUBLIC_API_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Platform to MCP-native.
  • Use Platform to Framework-agnostic.
  • Use Platform to RBAC.

Frequently asked questions

It connects Platform to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (MCP-native, Framework-agnostic, RBAC, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Platform directly.