Stops agentic loops before they burn through your token budget. This runs a five-voter Byzantine Fault Tolerant council that evaluates whether an agent is making real progress or just spinning. You call `start_session` to begin tracking, `record_action` to log each step, and `council_vote` to get a thumbs-up or circuit-breaker signal. Designed to sit upstream of the token budget and audit logger in the MEOK A2A stack. MIT licensed, stdio or streamable HTTP transport. If you've ever watched Claude repeat the same operation twelve times because it couldn't detect its own stuck state, this is the guardrail that catches it. Part of the six-MCP compliance chain that maps to EU AI Act Articles 12 and 50.
mcp-name: io.github.CSOAI-ORG/bft-progress-council-mcp
BFT Progress Council MCP — 5-voter Byzantine council halts agentic loops when no real progress is...
BFT Progress Council MCP — 5-voter Byzantine council halts agentic loops when no real progress is happening. Stops tokens bleeding on infinite spins. MIT-licensed. Part of MEOK A2A Substrate.
# Install via pip
pip install bft_progress_council_mcp
# Or install via Smithery
npx -y @smithery/cli@latest install bft-progress-council-mcp --client claude
This MCP server is built with EU AI Act compliance built-in:
Need help getting compliant? Book a free 15-min diagnostic →
Need custom development, SLA guarantees, or white-label deployment?
View Pricing → | Contact Sales →
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 |
MIT © CSOAI-ORG
Built with 💜 by MEOK AI Labs · UK Companies House 16939677
- **Prompt Injection Firewall** → `uvx agent-prompt-injection-firewall-mcp` - **Audit Logger** → `uvx agent-audit-logger-mcp` - **Policy Enforcement** → `uvx agent-policy-enforcement-mcp` - **Rate Limiter** → `uvx agent-rate-limiter-mcp` - **Certified Handoff** → `uvx agent-handoff-certified-mcp` - **Identity + Trust** → `uvx agent-identity-trust-mcp`Full catalogue + Anthropic Registry verify links: meok.ai/anthropic-registry
| Option | Price | Best for |
|---|---|---|
| Self-host (this MCP) | £0 — MIT | Devs |
| This MCP Starter | £29/mo | One-MCP teams |
| Universal PAYG | £29/mo + £0.0002/call | Spiky usage |
| A2A Substrate | £499/mo | A whole pack |
| Universe | £1,499/mo | All 48 MCPs |
Every other MEOK MCP makes you do something. This one tells you when to stop. It's the cheapest insurance policy in the catalogue — and it sits alongside the agent-rate-limiter and agent-audit-logger as the third guardrail in the A2A Substrate.
This MCP is step 1 of 6 in the MEOK chain that turns one agent action into a fully signed compliance event. See meok.ai/mcp-stack for the 6-MCP chain:
Output: ONE auditor-defensible evidence event mapped to EU AI Act Articles 12 + 50, DORA Article 17, ISO 42001 clause 9 — plus a public verify URL.
MIT. By MEOK AI Labs (CSOAI LTD, UK Companies House 16939677). Founder: Nicholas Templeman.
| 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.
Add to your claude_desktop_config.json (Claude Desktop) or your MCP client config:
{
"mcpServers": {
"bft-progress-council-mcp": {
"command": "uvx",
"args": ["bft-progress-council-mcp"]
}
}
}
Or: pip install bft-progress-council-mcp then run the bft-progress-council-mcp command (stdio transport).
Once configured, ask your assistant, for example:
start_session to …"record_action to …"council_vote to …"io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent