AI CounselBLOCK
True deliberative consensus MCP server where AI models debate and refine positions across multiple rounds
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/skills?ns=blueman82&utmsource=github&utmmedium=badge)
True deliberative consensus MCP server where AI models debate and refine positions across multiple rounds.
🎬 See It In Action
Cloud Models Debate (Claude Sonnet, GPT-5.1 Codex, Gemini):
mcp__ai-counsel__deliberate({
question: "Should we use REST or GraphQL for our new API?",
participants: [
{cli: "claude", model: "claude-sonnet-4-5-20250929"},
{cli: "codex", model: "gpt-5.2-codex"},
{cli: "gemini", model: "gemini-2.5-pro"}
],
mode: "conference",
rounds: 3
})Result: Converged on hybrid architecture (0.82-0.95 confidence) • View full transcript
Local Models Debate (100% private, zero API costs):
mcp__ai-counsel__deliberate({
question: "Should we prioritize code quality or delivery speed?",
participants: [
{cli: "ollama", model: "llama3.1:8b"},
{cli: "ollama", model: "mistral:7b"},
{cli: "ollama", model: "deepseek-r1:8b"}
],
mode: "conference",
rounds: 2
})Result: 2 models switched positions after Round 1 debate • View full transcript
What Makes This Different
AI Counsel enables TRUE deliberative consensus where models see each other's responses and refine positions acr
a0df9a0d9bd4OBSERVED · 2026-10-06Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
list_models | read | Return the allowlisted model options for each adapter. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (14)
- Always load `.env` file first with `dotenv.load_dotenv()` in `load_config()`
# Add to your shell profile (~/.bashrc, ~/.zshrc, etc.)
{"path": "../../../etc", "working_directory": str(tmp_path)}base_url: "http://192.168.1.100:1234" # Remote server IP
base_url: "http://192.168.1.100:11434" # Remote server IP
mcp, pydantic, pyyaml, httpx, tenacity, vcrpy, scikit-learn, sentence-transformers
assets/ai-counsel.png
4. Permissions: Default (full access)
# Then load with: export $(cat .env | xargs)
3. **Add to PATH:**
# Add to PATH for easy access
# Add to ~/.bashrc or ~/.zshrc for persistence
# Permanent (add to ~/.bashrc or ~/.zshrc)
curl -fsSL https://ollama.com/install.sh | sh
Gates applied: no_behavioural_pass.
a0df9a0d9bd4full audit observations/trust-audit/mcp-server/blueman82__ai-counsel.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | a0df9a0d9bd4 | BLOCK | D | 69 | first audit |
Questions
What is the AI Counsel MCP server?
True deliberative consensus MCP server where AI models debate and refine positions across multiple rounds
What tools does AI Counsel expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is AI Counsel safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does AI Counsel need?
It reads TEST_API_KEY and TEST_OPENROUTER_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does AI Counsel run?
It speaks stdio, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (a0df9a0d9bd4), read on 2026-10-06. The repository is watched and re-audited when it changes.