datagrout

DataGrout is an enterprise MCP gateway that connects AI agents to Salesforce (700+ tools), QuickBooks Online (550+ tools), Oracle Fusion Cloud (1,000+ tools)…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Discovery.Summary: Compact overview of all available tools and integrations on this server. Returns a compressed text block agents can scan to know what to search for with discovery.discover.
  • Discovery.Discover: Searches available tools for this MCP server by semantic similarity to a goal. Returns a ranked list of matching tools together with their input/output schemas. After calling disco
  • Discovery.Perform: Execute a specific tool by name, or batch-execute multiple tools in parallel. Use this tool as the second step of the discover → perform workflow: 1. Call `discover` (data-grout@1/d

What data it sees

Do you need an account

No: the server works without sign-in

DataGrout is an enterprise MCP gateway that connects AI agents to Salesforce (700+ tools), QuickBooks Online (550+ tools), Oracle Fusion Cloud (1,000+ tools), and any MCP-compatible system through a single endpoint. It reduces LLM token costs through semantic tool discovery, intelligent context engineering, and a neuro-symbolic inference layer that offloads deterministic operations without LLM calls. Every workflow is verified with a Cognitive Trust Certificate before execution. Warden scans every tool output for prompt injection before it reaches the agent. Pre-execution cost estimates and itemized receipts are included with every tool call. Supports Bearer token, OAuth 2.1, and mTLS authentication. Compatible with Claude, Cursor, ChatGPT, n8n, LangGraph, and any MCP-compatible client.

How to connect

How to connect datagrout to Claude

The server address to paste into Claude settings:

https://datagrout.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect datagrout to ChatGPT

The server address to paste into ChatGPT settings:

https://datagrout.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect datagrout to Cursor

The server address to paste into Cursor settings:

https://datagrout.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (5)

Raw names from tools/list. Only developers need these.

discovery.summaryCompact overview of all available tools and integrations on this server. Returns a compressed text block agents can scan to know what to search for with discovery.discover.
discovery.discoverSearches available tools for this MCP server by semantic similarity to a goal. Returns a ranked list of matching tools together with their input/output schemas. After calling discover, use the `perform` tool (data-grout@1/discovery.perform@1) to actually execute a discovered tool: pass the tool_name from the results as the `tool` argument and supply any required args.
discovery.performExecute a specific tool by name, or batch-execute multiple tools in parallel. Use this tool as the second step of the discover → perform workflow: 1. Call `discover` (data-grout@1/discovery.discover@1) with a `goal` to find relevant tools and their schemas. 2. Call `perform` with the `tool_name` from the discover results and the required `args`. Works for any tool registered on this server, including first-party DataGrout tools, baked integration tools (e.g. salesforce, quickbooks), and multiplexed/external tools.
discovery.planPlans how to satisfy a natural-language goal using the tool catalog. Returns ranked plans, required inputs (holes), and a call_handle.
discovery.guideNavigate tool discovery and execution through a guided decision tree. Presents options at each step, making complex workflows simple to execute while enforcing policy constraints and providing full auditability.