Agent Negotiation MCP
- Updated July 26, 2026
- CSOAI-ORG/agent-negotiation-mcp
Agent Negotiation MCP is a MCP server that adds negotiation tools so multiple AI agents can structuredly agree on tasks and handoffs.
About
Agent Negotiation MCP is a stdio Model Context Protocol server from MEOK AI Labs, published under CSOAI-ORG, that exposes negotiation-oriented tools for autonomous or semi-autonomous agents. developers stitching together Claude Code subagents, background workers, or vendor bots install it when handoffs need explicit propose–counter–accept style structure rather than one monolithic prompt that silently overrides priorities. The canonical Skillselion placement is build / agent-tooling, with a secondary operate / iterate path when production agents must renegotiate retries, SLAs, or task splits after failures. Repository metadata points to GitHub for deeper tool contracts than the registry blurb alone. It is an MCP integration layer, not a hosted marketplace or a planning methodology skill—pair it with orchestrator or router MCPs when your fleet grows. Intermediate complexity reflects protocol fluency and designing safe negotiation boundaries.
- MEOK AI Labs MCP server for agent-to-agent negotiation workflows
- Stdio MCP via PyPI package agent-negotiation-mcp v1.0.4
- GitHub source at CSOAI-ORG/agent-negotiation-mcp
- Fits multi-agent builds that need explicit bargain/commit steps instead of ad-hoc prompts
- Composable with other MEOK fleet servers via MCP router patterns
Agent Negotiation MCP by the numbers
- Data as of Aug 10, 2026 (Skillselion catalog sync)
claude mcp add agent-negotiation-mcp -- uvx agent-negotiation-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | agent-negotiation-mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | July 26, 2026 |
| Repository | CSOAI-ORG/agent-negotiation-mcp ↗ |
What it does
Give coding agents structured negotiation tools when multiple automated workers must agree on terms, tasks, or handoffs.
Who is it for?
Best when you're prototyping agent swarms, outsourced automation, or buyer–seller style agent flows on MEOK-compatible stacks.
Skip if: Single-agent apps with no peer agents and no need for structured deal or task negotiation.
What you get
After you add the server, agents can call dedicated negotiation MCP tools instead of improvising merges in free text.
- Negotiation MCP tools callable from agent sessions
- Documented stdio server wiring linked to CSOAI-ORG GitHub source
By the numbers
- Version 1.0.4 with stdio transport and GitHub repository CSOAI-ORG/agent-negotiation-mcp
README.md
Agent Negotiation MCP
Multi-agent negotiation framework
Multi-agent negotiation framework. Propose deals, evaluate offers, run auctions, and optimize outcomes. By MEOK AI Labs.
🚀 Quick Start
# Install via pip
pip install agent_negotiation_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install agent-negotiation-mcp --client claude
✨ Features
- Multi-agent deal negotiation
- Proposal generation
- Counter-offer handling
- Consensus detection
- Contract drafting
📖 Documentation
🛡️ Compliance
This MCP server is built with EU AI Act compliance built-in:
- ✅ Article 9 — Risk Management System
- ✅ Article 13 — Transparency & Instructions for Use
- ✅ Article 15 — Bias Detection & Testing
- ✅ Article 26 — FRIA Support (where applicable)
- ✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
🏢 Enterprise
Need custom development, SLA guarantees, or white-label deployment?
- Pro: $99/mo — Full MCP suite + EU AI Act tracking
- Enterprise: $499/mo — Custom dev + SLA + Dedicated support
View Pricing → | Contact Sales →
🤝 Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.
| Domain | Purpose |
|---|---|
| councilof.ai | EU AI Act compliance marketplace |
| safetyof.ai | AI safety & monitoring |
| meok.ai | Sovereign AI platform |
| cobolbridge.ai | Legacy modernization |
📜 License
MIT © CSOAI-ORG
Built with 💜 by MEOK AI Labs · UK Companies House 16939677
Each tier above the free self-host adds HMAC-signed attestations verifiable at `verify.meok.ai`. Linux Foundation governance on the A2A spine means EU regulated buyers can deploy without vendor-lock-in objections.💸 Try MEOK in 30 seconds — instant buy ladder
| Tier | Price | What you get | Stripe |
|---|---|---|---|
| Smoke test | £1 | Signed sample MCP-Hardening report + Article 50 PDF | https://buy.stripe.com/5kQ6oJ0xS3ce8sl7ew8k91j |
| Quick Kit | £9 | EU AI Act Article 50 implementation guide (C2PA + EU-Icon) | https://buy.stripe.com/5kQ6oJ0xS3ce8sl7ew8k91j |
| Founder Call | £29 | 30-min 1-on-1 with the founder | https://buy.stripe.com/5kQ6oJ0xS3ce8sl7ew8k91j |
Refundable. UK Stripe — VAT-clean. Builds on the 81-MCP MEOK fleet. Verify any signed report at https://meok.ai/verify.
Configuration
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"agent-negotiation-mcp": {
"command": "uvx",
"args": ["agent-negotiation-mcp"]
}
}
}
Or: pip install agent-negotiation-mcp then run the agent-negotiation-mcp command (stdio transport).
Examples
Once configured, ask your assistant, for example:
- "Use
propose_dealto …" - "Use
evaluate_offerto …" - "Use
counter_offerto …"
Recommended MCP Servers
0Latency Memory MCPPersistent memory layer for AI agents.
0nMCP — Universal AI API OrchestratorUniversal AI API Orchestrator — 1,554 tools, 96 services.
0xHumans Protocol MCPMCP for AI agents: financing, skills, lending on Base1k Patient MCP1k patient MCP server
1trippulse MCP1trip PULSE: 21-tool AI travel planner.
3D AI Agent Avatar MCP3D AI Agent Avatar — render any GLB, give it a Solana wallet, a voice, and pump.fun powers.90How it compares
Multi-agent negotiation MCP, not a human sales CRM or a generic brainstorming skill.
FAQ
Who is agent-negotiation-mcp for?
It is for developers running two or more cooperating agents who need MCP-exposed negotiation steps rather than unstructured chat between tools.
When should I use agent-negotiation-mcp?
Use it while building agent-tooling when tasks must be split, bid on, or agreed between agents, and again in operate when live runs need renegotiation after errors.
How do I add agent-negotiation-mcp to my agent?
Install agent-negotiation-mcp from PyPI, add the stdio MCP block in Claude Code or Cursor, and consult the GitHub repo for tool names and required environment variables.