Repository navigation
docs: add an opt-in Parallel Search MCP example - #40
Open
georgeatparallel wants to merge 1 commit into
Open
georgeatparallel wants to merge 1 commit into
georgeatparallel wants to merge 1 commit into
Conversation
Contributor
|
Hi George, Parallel Search looks like a great and genuinely useful product! Would it be possible to mention Swival in Parallel's documentation alongside Claude Code, Codex, and Cursor? |
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds an opt-in setup for web search and page extraction through Swival's existing HTTP MCP support. Users add a small table to
swival.toml; Parallel's anonymous free tier needs no API key or local server and has rate limits. The example identifies Swival with a User-Agent header and includes a search-then-fetch prompt. Model selection and existing MCP configuration keep their current behavior.The docs source and generated HTML page are included. Validation passed 373 MCP/config tests, Ruff lint and formatting checks, and the website build with its local link checks. The installed CLI loaded the documented table, discovered both tools, executed live anonymous search and fetch, and printed a sourced TaskGroup summary. Inference was supplied by a deterministic local fixture, so this checks Swival's tool round trip rather than any model's search decisions.
For context, Parallel Fast records 80.2 average answer-item F1 on a 0-to-100 scale in DeepSearchQA, with 18.8 seconds per task in Artificial Analysis's benchmark harness. That's useful context for a lightweight search option, not a Swival speed measurement or a comparison with its browser tools.
Btw - I'm a devrel engineer at Parallel