Skip to content
Agentmart
Submit a tool

OpenClaw Consensus

9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.

Connector by MICONNM · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/miconnm-openclaw-consensus-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

9-LLM consensus + disagreement scoring + cheapest-route picks to fight hallucinations.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
3 read · 0 write · 0 deleteRead-only
Secrets
1 (API keys, tokens or passwords)
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 3

Read from the source code; the running server may list different tools.

Read 3 · Look things up without changing anything.

  • cheapest_route
  • consensus
  • disagreement_score

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

  • RAPIDAPI_KEY

Tools (3)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • cheapest_route

    Recommend the cheapest model combination that meets a quality bar. Args: prompt: The user prompt to route. target_quality: Minimum acceptable quality, 0..1. Default 0.85. Returns: ``{"models": [...], "estimated_cost_usd": float, "estimated_quality": float}``.

  • consensus

    Get a 9-LLM consensus answer. Args: prompt: The user question or instruction. mode: ``deep`` (9 models), ``balanced`` (5), or ``fast`` (3). Returns: A dict with ``answer``, ``confidence`` (0..1), ``models_used`` (list), and ``disagreement`` (0..1, higher = riskier hallucination signal).

  • disagreement_score

    Score how much the 9 models disagree on a prompt (0..1). A high score is a useful hallucination warning: when frontier models disagree, single-model answers are more likely to be wrong. Returns: ``{"score": float, "per_model": {model: answer_summary}}``.

Signals

Stars
0
Forks
0
Open issues
0
Weekly downloads
24
Last commit
Jun 1, 2026 (5 months ago)
Last release
Apr 30, 2026 (6 months ago)
Last package publish
Apr 30, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.MICONNM/openclaw-consensus-mcp
Version
0.1.1
Auth
API key
Packages
pypi openclaw-consensus-mcp
License
MIT
Repository
github.com/MICONNM/openclaw-consensus-mcp
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

OpenClaw Consensus MCP server. Agent Mart. https://agentmart.dev/connectors/miconnm-openclaw-consensus-mcp (last updated 2026-10-24)