mcpField
L
Lupin

Lupin

Local
qompass.aiBusiness & Marketing0Updated 1w ago
RepositoryVisit website

About Lupin

Lupin is an MCP server for tracking revenue opportunities and matching them against a capability registry. Its lane-scoped access separates Qompass and NTRanch entries, and it stores data in plain files rather than a database.

Key features

  1. 01Opportunity ledger and capability registry
  2. 02Lane-scoped access control
  3. 03Advisory keyword capability matching
  4. 04Candidate submission to scan inbox
  5. 05Pipeline counts and parse health

Use cases

  1. 01Review opportunities by status
  2. 02Check capability matches for a candidate
  3. 03Submit a candidate for scanning
  4. 04Inspect pipeline counts by lane

MCP support

Lupin communicates with MCP clients over stdio using NDJSON JSON-RPC. It exposes tools for listing capabilities and opportunities, matching text, submitting candidates, and viewing pipeline summaries.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
mcpblupin-mcp-0.1.0-linux-x64.mcpb

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Lupin

An MCP server for the Revenue Alignment Engine: an opportunity ledger and capability registry with lane-scoped access. Opportunities live in one of two lanes — Qompass (sfw) or NTRanch (nsfw) — and a caller scoped to one lane can never see the other lane's entries.

Lupin is a single Rust binary. It speaks MCP over stdio (NDJSON JSON-RPC) to the client and works on plain files under a data root — no database, no network listener. It is the ledger side of the estate's revenue pipeline; the research-feed server phaedrus drafts candidates into it.

How it runs

  • Data root (ledger, capability registry, scan inbox): --root <path> or the REVENUE_ROOT environment variable (default ~/workspace/revenue-alignment-20261019).
  • Lane scope: --lane-scope operator|sfw (default operator). The operator scope sees both lanes; an sfw-scoped caller can never see nsfw entries.
  • Read-mostly by design: the only write files a candidate into the scan inbox (opportunity_submit). The validated ledger is never written by this server, and capability_match is advisory only — it never auto-aligns an opportunity.

Tools

ToolWhat it returns
capability_listThe capability registry (the alignment vocabulary); lane scope enforced
capability_matchAdvisory keyword match of free text against capabilities; never auto-aligns
opportunity_getOne ledger entry by id, including its raw block
opportunity_listLedger opportunities, optionally filtered by status; lane scope enforced
opportunity_submitFile a candidate into the scan inbox; never writes the ledger
pipeline_summaryCounts by status/lane plus parse health — the value-demonstration view

Client config

{
  "mcpServers": {
    "lupin": {
      "command": "/path/to/lupin",
      "args": []
    }
  }
}

Registry

server.json in this repo is the MCP Registry record for ai.qompass/lupin. The server is distributed as an MCPB bundle attached to the GitHub releases (Linux x64).

License

Apache-2.0 — see LICENSE.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.