mcp-prospector is the prospector copilot MCP for Claude desktop coworker (Executor) to use central intelligence.
- New tool `classify_message(text, handle?, phone?, has_call?, local_is_known_contact?)`: runs fast efficient rules classifier (our distilled model from training data) + full central stack (LLM via GPU model-boss if deployed, mrnumber, macsync/quinn-messenger context via thread/classify, qualification). Supports passing local desktop context for Contacts gate.
- Local fastClassify/fastTemplate inlined for the MCP (pure, no extra dep issues).
- Updated README with full architecture:
- Composition: quinn-messenger (messaging), mrnumber (screening), classifier (fast + GPU LLM), macsync (data), quinn-desktop (local MCP for addressbook/Contacts gate, other sensors).
- Desktop coworker loads multiple MCPs (this central + quinn-messenger MCP + quinn-desktop local MCP).
- SKILL instructs workflow: desktop local lookup first, then central classify_message for combined result using optimized model + all sources.
- Replaces pure local stopgap rules with central quality while keeping desktop facts.
- This lets the desktop coworker classify messages using the full prospector copilot feature (central brain on GPU + local).
Follows project: prospector central in api, macsync network, MCP as tool interface for agents, hybrid fast rules + LLM.
Part of making prospector copilot the way for coworker + replace claude deps (GPU for LLM part).
Expose Mr. Number client screening through the quinn-prospector MCP:
- mr_number_check records an app-lookup verdict (client_id + phone + result
+ notes) via POST /admin/screening/check with service=mr-number; the
server auto-creates a reputation award/flag on approved/denied.
- mr_number_history lists a client's screening checks via
GET /admin/screening?clientId=.
Mirrors mr_lookup.py record_screening() wire body (clientId required — the
BFF rewrite drops it from the path).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Move the prospector cockpit logic into the published @lilith/agent-prospector
package (^0.4.0) and reduce the MCP to a thin adapter — index.ts/client.ts shrink
by ~900 lines. Bump to 0.5.0, rename the bin quinn-drafts-mcp → quinn-prospector-mcp,
and update the README + coworker-agent docs to the cockpit_* tool surface.
Reorient the prospector MCP around the /my/prospects cockpit API that powers
quinn.my Prospector: add cockpit_stream / cockpit_tour_board and friends with
human-readable formatters (new cockpit-format.ts), extend the API client, and
rewrite the README (quinn-drafts → quinn-prospector, black:3912).
