Skip to content

Add optional Parallel provider for WebSearch - #174

Open
georgeatparallel wants to merge 2 commits into
PawanOsman:mainfrom
georgeatparallel:george/parallel-web-search
Open

georgeatparallel wants to merge 2 commits into
PawanOsman:mainfrom
georgeatparallel:george/parallel-web-search

Conversation

@georgeatparallel

Copy link
Copy Markdown

OpenCursor users can choose Parallel for the built-in WebSearch tool without creating an account or adding an API key. DuckDuckGo stays the default.

The new selector lives under Settings > Agents > Context. It uses the existing stdio MCP client with a pinned mcp-remote bridge, discovers web_search, and returns excerpts with source URLs. Search queries go to Parallel when selected; the existing web permission controls still apply. WebFetch keeps its current behavior.

For background on the search provider, Artificial Analysis publishes DeepSearchQA results and time per task. Those benchmarks measure provider research performance, not this VS Code integration. The free MCP uses Fast search and returns excerpts the agent can use directly. DuckDuckGo isn't evaluated in that comparison.

Type checks, lint, the production build, and focused routing, settings and MCP tests pass. A hosted call through the WebSearch handler returned useful Node.js documentation excerpts and citations without a Parallel key. The harness supplied a minimal VS Code workspace stub; a full Extension Development Host session hasn't been tested. The full unit suite has two failures that reproduce on unchanged upstream, in file mutation undo and ripgrep tests.

Btw - I'm a devrel engineer at Parallel

@georgeatparallel
georgeatparallel marked this pull request as ready for review September 21, 2026 20:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant