webclaw-mcp: add lead + lead_batch cloud-proxy tools

The hosted /v1/lead (single) and /v1/lead/batch (async) endpoints had no
MCP surface, so Claude Desktop/Cursor/etc. couldn't enrich leads and the
skill advertised a `lead` tool that didn't exist. Add `lead` and
`lead_batch` mirroring the existing `research` tool: cloud-only (require
WEBCLAW_API_KEY), no in-process founder-recovery. `lead` proxies
POST /v1/lead; `lead_batch` starts POST /v1/lead/batch then polls
GET /v1/lead/batch/{id} to completion (up to 25 URLs, ~10 min cap).
Tool count 12 → 14 (get_info string + CLAUDE.md synced).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Valerio 2026-07-18 18:38:02 +02:00
parent 0c1dddb6df
commit 4892faea21
3 changed files with 113 additions and 2 deletions

View file

@ -71,7 +71,7 @@ Three binaries: `webclaw` (CLI), `webclaw-mcp` (MCP server), `webclaw-server` (R
### MCP Server (`webclaw-mcp`)
- Model Context Protocol server over stdio transport
- 12 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, research, search, list_extractors, vertical_scrape. `search` is local-first via the caller's `SERPER_API_KEY` (falls back to the hosted API when unset); `research` uses the hosted deep-research API. The rest run locally.
- 14 tools: scrape, crawl, map, batch, extract, summarize, diff, brand, research, search, list_extractors, vertical_scrape, lead, lead_batch. `search` is local-first via the caller's `SERPER_API_KEY` (falls back to the hosted API when unset); `research`, `lead`, and `lead_batch` are hosted-only cloud proxies (require `WEBCLAW_API_KEY`) — `lead`/`lead_batch` call `/v1/lead` and the async `/v1/lead/batch`. The rest run locally.
- Works with Claude Desktop, Claude Code, and any MCP client
- Uses `rmcp` crate (official Rust MCP SDK)