Raportagent Mcp

io.github.raportagentPublished by GitHub account raportagentv0.1.2Updated Nov 3, 2026

Sourced market and compliance research for Claude Desktop, Claude Code and Cursor.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

RaportAgent MCP lets an assistant generate sourced market and compliance research reports, then fetch the markdown, sources and audit trail.

What you can do
  • Start a sourced research report from a query, optionally with a template such as compliance, pitch, saas, ecommerce, realestate, local, battlecard, duediligence or fintech
  • Check a report's status (queued, running, completed, failed) and cancel a queued or in-progress report
  • Retrieve the finished report's full markdown and sections
  • Inspect provenance: AI models, agents, source counts and a content hash, plus every cited source with link-health counts
  • List recent reports and check remaining credits and plan
When to use it
Useful when you want an assistant to research a market or map a regulatory landscape and hand back a written, source-cited report with an audit trail, rather than ad-hoc web answers. It fits Claude Desktop, Claude Code or Cursor users who already have a RaportAgent account.
Requirements
Runs locally over stdio via npx from the npm package @raportagent/mcp, so Node.js is needed. Requires a RaportAgent API key in RAPORTAGENT_API_KEY (created under My account, API keys). RAPORTAGENT_BASE_URL optionally overrides the default endpoint. Network access to the RaportAgent API is required.
Before you install
Reports consume RaportAgent credits (1 credit per report, 2 for battlecard), so usage costs money against your plan. The API key is a live credential sent to the configured base URL; keep it out of shared configs and be careful when overriding RAPORTAGENT_BASE_URL. Generation typically takes about 15 minutes, and reports can be cancelled to refund a credit. Research queries and results are sent to RaportAgent's service.

Installation

In SourceWeft

  1. Open Raportagent Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

ToolWhat it does
generate_reportStart 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_statusqueued / running / completed / failed
get_reportThe finished report's full markdown + sections
get_report_auditProvenance: AI models, agents, source counts, SHA-256 of the exact content
get_report_sourcesEvery cited source with link-health counts (working / uncertain / dead)
cancel_reportCancel a queued/in-progress report and refund its credit
list_reportsYour recent reports
get_accountRemaining credits and plan

Setup

  1. Get an API key: RaportAgent → My account → API keys (an ra_live_… key).
  2. 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.gitcd mcp-servernpm installnpm run build

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

Config

EnvDefaultNotes
RAPORTAGENT_API_KEY—Required. ra_live_… key.
RAPORTAGENT_BASE_URLhttps://raportagent.comOverride 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.

Source: README.md at commit 63102ce

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts