Wires Claude directly into QuReDec's evidence-backed decision research API. You get three tools: submit a question with decision_brief, poll progress with get_brief_status, and review history with list_recent_briefs. Each completed brief returns a structured recommendation with confidence score, cited key facts, risk analysis with severity ratings, and concrete actions ranked by effort and impact. The tool blocks and polls for up to 10 minutes by default. Useful when you need sourced, structured answers to business or technical decisions without leaving your editor. Requires a QuReDec API key and consumes credits from your account. Ships with an offline mock for development.
Run a structured QuReDec decision brief from inside Claude Code, Claude Desktop, Cursor, or any MCP-compatible client.
Status: alpha (2026-04-30). Wired to the live QuReDec public API (
/api/v1/brief*, per-user Bearer-token auth). SetQUREDEC_MOCK=1for offline development.
| Tool | Description |
|---|---|
decision_brief | Submit a question; receive a structured, evidence-backed decision brief with citations |
get_brief_status | Poll an in-progress brief by ID |
list_recent_briefs | List the caller's recent briefs |
The completed brief contains: executive_summary, recommendation,
confidence (0–1), key_facts[].citation_ids, implications[], actions[]
(with effort + impact), risks[] (with severity + citation_ids),
and citations[] (with citation_id, title, url, source_type).
pip install quredec-mcp
Or from source:
git clone https://github.com/Advanced-Binary-Operations/QuReDec_MCP
cd QuReDec_MCP
pip install -e .
Generate a QuReDec API key at https://quredec.com/account → API keys. Each key is shown to you exactly once at creation; copy it into a password manager immediately.
Add to your MCP client config (Claude Desktop example):
{
"mcpServers": {
"quredec": {
"command": "quredec-mcp",
"env": {
"QUREDEC_API_KEY": "qrd_live_xxxxxxxxxxxx"
}
}
}
}
Optional env vars:
QUREDEC_BASE_URL — defaults to https://quredec.com.QUREDEC_MOCK=1 — run against an in-process mock for development.In Claude Code or Claude Desktop:
Use the
decision_brieftool to evaluate "Should I migrate from Stripe to LemonSqueezy?"
The brief comes back with: recommendation, confidence score, key facts with inline citation ids, risks, recommended actions, and a public share URL. Briefs typically take 2–5 minutes; the tool blocks and polls by default (timeout 600 s) and falls back to a synthetic running status with a poll hint if the timeout fires.
The MCP server is free. Briefs consume credits from your QuReDec account:
See https://quredec.com/pricing.
Unit tests run against the in-process mock (no network, no key required):
pip install -e ".[dev]"
QUREDEC_MOCK=1 pytest
Run the server locally against the mock:
QUREDEC_MOCK=1 quredec-mcp
scripts/integration_test.py exercises the full path against quredec.com:
submit → poll → assert brief schema → list. It consumes 1 credit from the
account whose key you pass in, so run it sparingly.
QUREDEC_API_KEY=qrd_live_xxxxxxxxxxxx \
python scripts/integration_test.py
Optional env vars:
QUREDEC_BASE_URL — defaults to https://quredec.com.QUREDEC_QUESTION — override the default seed question.QUREDEC_TIMEOUT — poll timeout in seconds (default 600).Exit code 0 on full pass, 1 on the first failed assertion.
MIT — see LICENSE.
Advanced Binary Operations LLC · support@advancedbinaryoperations.com
QUREDEC_API_KEY*secretPer-user API key. Generate one at https://quredec.com/account.
QUREDEC_BASE_URLOverride the QuReDec API host. Defaults to https://quredec.com.
QUREDEC_MOCKSet to 1 to run against an in-process mock (no network, no API key required). Development use only.
taida957789/ida-mcp-server-plugin
zboralski/ida-headless-mcp
svnscha/mcp-windbg
fosdickio/binary_ninja_mcp
wasdubya/x64dbgmcp