Skip to content

mercurialsolo/counsel-mcp

v0.2.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 4mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Adds Multi-Criteria Decision Analysis, Deep Research Mode, and consultation management tools.

Full changelog

Features

Multi-Criteria Decision Analysis (MCDA)

  • New enable_mcda parameter for structured decision scoring
  • criteria_weights for custom weighting (e.g., {'reliability': 0.3, 'cost': 0.25})
  • stake_level enforcement: 'fast', 'standard', 'high'
  • evidence_policy for freshness, coverage, and source requirements

Deep Research Mode

  • New 'research' mode for evidence-only analysis (no debate)
  • Enhanced multi-provider synthesis (ChatGPT, Gemini, Claude, Grok, Kimi, DeepSeek)

Consultation Management

  • New tool: manage_consultation - Intervene in running analyses
    • Actions: pause, resume, abort, steer, add_sources

Advisor Improvements

  • Enhanced consult_advisor with proper session management
  • New tool: get_advisor_profile - Retrieve learned user profiles

Upgrade Notes

This is a minor version bump (0.1.6 → 0.2.0) with new features. Existing tool calls remain compatible.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track mercurialsolo/counsel-mcp

Get notified when new releases ship.

Sign up free

About mercurialsolo/counsel-mcp

Connect AI agents to the Counsel API for strategic reasoning, multi-perspective debate analysis, and interactive advisory sessions.

All releases →

Related context

Beta — feedback welcome: [email protected]