Skip to content

docs(examples): add Parallel Search MCP over HTTP - #2014

Open
georgeatparallel wants to merge 1 commit into
anthropics:mainfrom
georgeatparallel:parallel-search-d2ac2b1b-02f7-49f4-a3f0-821d9ded0f6c
Open

georgeatparallel wants to merge 1 commit into
anthropics:mainfrom
georgeatparallel:parallel-search-d2ac2b1b-02f7-49f4-a3f0-821d9ded0f6c

Conversation

@georgeatparallel

Copy link
Copy Markdown

Give the Claude tool runner free web search and page fetching with Parallel Search MCP. The existing MCP example uses a local filesystem server over stdio; this standalone example connects over Streamable HTTP using the existing MCP adapters. Anonymous search uses Fast mode, with no Parallel account or API key.

Install anthropic[mcp] and mcp>=1.26,<2, set ANTHROPIC_API_KEY, and run python examples/parallel_search_mcp.py. Live anonymous search and fetch passed through the SDK runner with scripted model responses; repository lint and MCP adapter tests passed. No live Claude inference was run.

Changelog: add a runnable HTTP MCP search example.

I work at Parallel.

@georgeatparallel
georgeatparallel requested a review from a team as a code owner October 11, 2026 03:30

This branch has not been deployed

No deployments
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