SNHP — free negotiation math + agent memory
SNHP runs a live, hosted, streamable-HTTP MCP server with TWO doors on the same application: the CORE door at https://snhp.dev/mcp/ (15 "hero-first" tools) and the PRO door at https://snhp.dev/mcp/pro/ (54 tools — the same 15 plus 39 legacy gt_* names, the verified-peer A2A flow, first-strike attestation, auction design/simulation, the offer-graph engine and "pondering" sessions). Both completed the initialize handshake (protocolVersion 2025-06-18, serverInfo gametheory / gametheory-pro, version 1.28.1) with no credentials, answered tools/list cold — no session id required — with real tools carrying inputSchema and (core door) annotations, and a read-only tools/call of store_catalog succeeded anonymously. resources/list and prompts/list are empty. The identical server also answers on api.snhp.dev/mcp/ (the host the official MCP registry names), www.snhp.dev and snhp.fly.dev. A stdio twin ships on PyPI as `snhp` (`uvx snhp`), listed on Smithery and Glama, so the deployment mode is BOTH.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Endpoint
Hosted endpoint · transport streamable-http
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
negotiate— Your math-optimal next move in any price negotiation — free, no account or key needed.negotiate_bundle— Negotiate several linked issues at once by logrolling — free.score_deal— Score a deal against the Pareto frontier (the certificate test's oracle as a callable tool).auction_bid— Optimal auction bid (first-price, Vickrey, English).auction_reserve— Revenue-optimal reserve price (Myerson).clearance_price— Clearance price and markdown schedule (Gallego-van Ryzin posted price).stable_match— Stable matching (Gale-Shapley deferred acceptance).memory_save— Save agent memory (blind locker) — flat park fee from the prepaid wallet; retrieval free.memory_load— Load agent memory by ticket.session_open— Open a $2 receipted, deterministic negotiation session (cap 10 moves, 7 days).session_advise— Next single-price move inside a receipted session (no extra charge).session_bundle— Multi-issue logrolled move inside a receipted session.session_close— Close the session and get the signed summary receipt.store_catalog— Store catalog and wallet balance.store_request— File a capability request in the demand box, or check a filing by request_id.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.