FeaturedAI Agents#DuckDuckGo#Web Search#Citations#Evidence#Python#MCP

DuckDuckGo Claim Evidence Finder

Search DuckDuckGo Lite for a factual claim and turn the result snippets into a cited evidence brief.

Workflow at a glance

The full canvas, before you import it

#DuckDuckGo#Web Search#Citations#Evidence#Python#MCP

Select a node to see its settings.

6 nodes · Free & source-available

Check what the search results actually say

Enter a claim or search query. DuckDuckGo Lite returns a page of results, Search Clips extracts up to six distinct links and snippets, and Evidence Editor assesses what those snippets support. Evidence Packet returns the verdict alongside the original result list, with numbered links retained from the search.

Try it

Select an LLM credential and GPT-5.5 in Evidence Editor, then run the included NASA query about Hubble's first image. The HTTP node needs no search key. The Code node runs in Heym's Python sandbox.

If DuckDuckGo serves a challenge or no results, the response carries the search status and reports insufficient evidence. The workflow reads result snippets only. Open the links to check the original pages before citing them.

Use it as an MCP tool

Save the imported workflow as DuckDuckGo Claim Evidence Finder. In Heym's MCP / A2A tab, enable the workflow on your MCP server. Call duckduckgo_claim_evidence_finder with a text argument containing your query. The tool returns the evidence packet as JSON. See the Heym MCP setup guide.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3Press Cmd+V / Ctrl+V — nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime▲
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym