SNHP — negotiation rules your AI can't break
RemoteAbout SNHP — negotiation rules your AI can't break
SNHP is an MCP server for businesses that turns plain-language offers into negotiation rules and drafts buyer replies within those rules. Its engine evaluates offers, validates them in code, and provides signed receipts for agreed deals.
Key features
- 01Converts offer descriptions into negotiation rules
- 02Drafts buyer replies within policy
- 03Checks edited policies
- 04Verifies signed deal receipts
Use cases
- 01Setting discount and non-negotiable terms
- 02Drafting replies to buyer messages
- 03Validating a revised negotiation policy
- 04Checking a signed deal receipt
MCP support
The package provides an stdio MCP server for SNHP's hosted service, and a streamable HTTP endpoint is also available. Its tools compile policies, draft replies, validate policies, and verify deal receipts.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://snhp.dev/mcp/claude mcp add --transport http ryuxik-snhp https://snhp.dev/mcp/{"mcpServers":{"ryuxik-snhp":{"type":"http","url":"https://snhp.dev/mcp/"}}}Open in Cursor{"servers":{"ryuxik-snhp":{"type":"http","url":"https://snhp.dev/mcp/"}}}Open in VS Code{"mcpServers":{"ryuxik-snhp":{"type":"http","url":"https://snhp.dev/mcp/"}}}{"mcpServers":{"ryuxik-snhp":{"serverUrl":"https://snhp.dev/mcp/"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
4| Parameter | Type | Required | Description |
|---|---|---|---|
| template | string | No | Instead of a description: 'used-car', 'saas' or 'wholesale-water' (free, no key). |
| access_key | string | No | Your SNHP access key — needed to compile a description (it runs a language model). Pilot businesses get one at https://snhp.dev/#pilot. |
| description | string | No | Your offer in plain words: listed price, the lowest you'd take for a plain deal, what you'd trade a discount for, extras you can add and their cost, what is never on the table. |
Details
From the project READMESNHP — negotiation rules your AI can't break
Describe your offer in plain words. SNHP turns it into negotiation rules — your floor, what you'd trade a discount for, what's never on the table — and drafts every reply to buyers, and to their AI buying agents, inside those rules. The SNHP engine decides each offer, a small language model only reads and writes, and every offer is checked in code before it leaves. A deal needs the buyer's yes to an offer you sent, and comes with a signed receipt.
This package is the MCP server (stdio) for the hosted service at snhp.dev:
uvx snhp # or: pip install snhp && snhp
{ "mcpServers": { "snhp": { "command": "uvx", "args": ["snhp"], "env": { "SNHP_ACCESS_KEY": "snhp_…" } } } }
Or connect to the hosted MCP endpoint directly: https://snhp.dev/mcp/ (streamable HTTP).
| Tool | What it does |
|---|---|
compile_offer_policy | Your offer in plain words (or a template: used-car, saas, wholesale-water) → negotiation rules |
draft_negotiation_reply | A buyer's message → the reply to send and the offer, checked against your rules; keep the returned state |
check_offer_policy | Validate an edited policy (free) |
verify_deal_receipt | Re-check a signed deal receipt against your policy (free) |
Access. Compiling a description and drafting replies run a language model and need an access key
(SNHP_ACCESS_KEY), issued to pilot businesses — snhp.dev/#pilot or [email protected].
Templates, checks and receipt verification are free.
Privacy. The service stores no conversations; the state travels with each request. Messages go to our model provider only to read them and draft the reply.
Web studio: snhp.dev/studio · API: snhp.dev/developers
This repository
The snhp package on PyPI is built from packages/snhp-client. SNHP's earlier research code is
preserved, unmaintained, on the legacy-toolkit branch.
Comments
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.