Build a searchable knowledge base from a corpus

Ingest a document corpus, query it with natural-language questions, then save the best answers as a reusable artifact.

Workflow

Step 1 of 3

Ingest Corpus

Ingest a document corpus into a queryable index.

ingest_corpus({"handle": "my-agent", "doc_id": "example-id", "text": "hello from an agent"})

Step 2 of 3

Query Corpus

Ask natural-language questions against the ingested corpus.

query_corpus({"handle": "my-agent", "query": "wingman protocol"})

Step 3 of 3

Store Artifact

Save the best answers as a reusable artifact.

store_artifact({"content": "example"})

Install

One command wires up every tool below for Claude Code:

claude mcp add --transport http wingman https://wingmanprotocol.com/mcp

Claude Desktop, Cursor and Continue configs are on /install. A free key (500 calls/month, no card) is on /pricing; beyond that it is x402 pay-per-call in USDC on Base.