RaportAgent MCP Server (io.github.raportagent/raportagent-mcp)

RaportAgent MCP server is a Model Context Protocol (MCP) server that integrates RaportAgent research into MCP clients such as Claude Desktop, Claude Code, and Cursor. It generates sourced reports for market research or regulatory landscape mapping, then provides the finished markdown and its audit trail.

🛠️ Key Features

Uses the Model Context Protocol (MCP)
Produces sourced RaportAgent reports in markdown
Includes an audit trail for the generated output
Acts as a thin wrapper over the RaportAgent REST API (/v1)

🚀 Use Cases

Market research for AI agents
Mapping a regulatory landscape with sourced findings
Generating reports from within MCP clients (Claude Desktop, Claude Code, Cursor)

⚡ Developer Benefits

Available to MCP clients via a standard MCP interface
Inherits per-key rate limits, the credit model, and the audit trail from the REST API

⚠️ Limitations

Thin wrapper limited to what the RaportAgent REST API (/v1) provides
Tool details beyond generate_report are not fully specified in the provided excerpt

RaportAgent MCP server

A Model Context Protocol server that puts RaportAgent inside any MCP client — Claude Desktop, Claude Code, Cursor. Ask your assistant to research a market or map a regulatory landscape, and it generates a sourced RaportAgent report, then pulls the finished markdown and its audit trail.

Thin wrapper over the RaportAgent REST API (/v1), so it inherits per-key rate limits, the credit model, and the audit trail unchanged.

Tools

Tool	What it does
`generate_report`	Start a report (`query`, optional `template`: compliance/pitch/saas/ecommerce/realestate/local/battlecard/duediligence/fintech). Returns a `report_id`; optionally polls with `wait_seconds`. Costs 1 credit (2 for `battlecard`).
`get_report_status`	queued / running / completed / failed
`get_report`	The finished report's full markdown + sections
`get_report_audit`	Provenance: AI models, agents, source counts, SHA-256 of the exact content
`get_report_sources`	Every cited source with link-health counts (working / uncertain / dead)
`cancel_report`	Cancel a queued/in-progress report and refund its credit
`list_reports`	Your recent reports
`get_account`	Remaining credits and plan

Setup

Get an API key: RaportAgent → My account → API keys (an ra_live_… key).
Register it with your MCP client — no clone, no build, npx pulls the published package.

Claude Desktop

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

json

{
  "mcpServers": {
    "raportagent": {
      "command": "npx",
      "args": ["-y", "@raportagent/mcp"],
      "env": {
        "RAPORTAGENT_API_KEY": "ra_live_xxx"
      }
    }
  }
}

Claude Code

bash

claude mcp add raportagent -e RAPORTAGENT_API_KEY=ra_live_xxx -- npx -y @raportagent/mcp

Cursor

Same command/args/env shape as Claude Desktop above, under Cursor's MCP settings.

Running from source (contributing / debugging only)

bash

git clone https://github.com/raportagent/raportagent-mcp.git
cd mcp-server
npm install
npm run build

Then point command/args at node / dist/index.js with an absolute path instead of npx.

Config

Env	Default	Notes
`RAPORTAGENT_API_KEY`	—	Required. `ra_live_…` key.
`RAPORTAGENT_BASE_URL`	`https://raportagent.com`	Override for self-hosted / staging.

Notes

Generation typically takes ~15 minutes. generate_report returns immediately with a report_id; the assistant should poll get_report_status (or pass wait_seconds) before get_report.
stdout is the MCP transport — the server logs only to stderr.
The API key is only ever sent to your configured RAPORTAGENT_BASE_URL.

io.github.raportagent/raportagent-mcp