
Zopaf
Exposes negotiation math as MCP tools: create a session, add issues with ranked options, record preferences, set your BATNA, then generate three iso-utility counteroffers or analyze deals against the Pareto frontier. Uses MILP optimization to infer counterpart priorities from their reactions and compute value splits based on leverage. Runs the math without burning LLM tokens on calculation. Your agent handles the conversation, Zopaf handles the optimization. Useful for job offers, term sheets, vendor contracts, or any multi-issue negotiation where you want efficient frontier analysis instead of guessing which concessions to make. Includes set_issue_range for numeric scoring, process_counterpart_response for revealed preference learning, and analyze_deal for post-hoc evaluation.
- tools
- 9
- transport
- HTTP
- last updated
- Apr 4, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
create_sessionCreate a new negotiation session. Returns a session_id used by all other tools.
Create a new negotiation session. Returns a session_id used by all other tools.
No parameter schema in public metadata yet.
add_issueAdd a negotiable issue/term with options ordered worst to best for the user.
Add a negotiable issue/term with options ordered worst to best for the user.
No parameter schema in public metadata yet.
set_issue_rangeSet the acceptable range for a numeric issue, enabling 0-100 scoring.
Set the acceptable range for a numeric issue, enabling 0-100 scoring.
No parameter schema in public metadata yet.
record_preferenceRecord that the user prioritizes some issues over others. Updates the weight model.
Record that the user prioritizes some issues over others. Updates the weight model.
No parameter schema in public metadata yet.
set_batnaRecord the user's alternatives if the deal falls through. Determines leverage.
Record the user's alternatives if the deal falls through. Determines leverage.
No parameter schema in public metadata yet.
generate_counteroffersGenerate 3 iso-utility counteroffers to present simultaneously.
Generate 3 iso-utility counteroffers to present simultaneously.
No parameter schema in public metadata yet.
process_counterpart_responseProcess the counterpart's reaction to infer their priorities and generate a round-2 offer.
Process the counterpart's reaction to infer their priorities and generate a round-2 offer.
No parameter schema in public metadata yet.
analyze_dealScore a specific deal against the Pareto frontier. Shows value captured and suggested trades.
Score a specific deal against the Pareto frontier. Shows value captured and suggested trades.
No parameter schema in public metadata yet.
get_negotiation_stateGet current model state: issues, weights, BATNA, frontier size, and recommended next step.
Get current model state: issues, weights, BATNA, frontier size, and recommended next step.
No parameter schema in public metadata yet.
Sponsors
Readme
Zopaf Negotiation Engine -- MCP Server
A negotiation math engine exposed as MCP tools that any AI agent can call. Zopaf computes Pareto frontiers, generates iso-utility counteroffers, and infers counterpart priorities from their reactions -- all through pure MILP optimization. Zero LLM tokens burned. The calling agent handles the conversation; Zopaf handles the math.
Quick Start
Claude Desktop
Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"zopaf": {
"type": "streamable-http",
"url": "https://zopaf-mcp-production.up.railway.app/mcp"
}
}
}
Claude Code
claude mcp add zopaf --transport streamable-http https://zopaf-mcp-production.up.railway.app/mcp
Generic MCP Client
Connect to the Streamable HTTP endpoint:
URL: https://zopaf-mcp-production.up.railway.app/mcp
Transport: Streamable HTTP
Tools Reference
Details
- Repository
- github.com/rjandino/zopaf
- Category
- AI & LLM Tools
- Transport
- HTTP
- Registry
- MCP registry, active