1.2.2 • Published 12m agoCLI

@lcv-ideas-software/ultrabrain-mcp

Licence

Apache-2.0

Version

1.2.2

Deps

Size

226 kB

Vulns

Weekly

Summary Dependency Versions

ultrabrain-mcp

LCV's local MCP reasoning gate for structured engineering thought.

Install. npm install -g @lcv-ideas-software/ultrabrain-mcp from npmjs.com, or npm install -g @lcv-ideas-software/ultrabrain-mcp --registry=https://npm.pkg.github.com from the GitHub Packages mirror.

Status. Stable. Current release: v01.02.02 (npm package 1.2.2). See CHANGELOG.md for the full release history.

First publication started at v01.00.00. Public GitHub tags use the LCV display convention v00.00.00; npm keeps normal SemVer.

Change History

The version history at a glance:

Release	Package	Date	Notes
`v01.02.02`	`1.2.2`	2026-07-21	Security patch: updates transitive `body-parser` to 2.3.0, restoring request-size enforcement for invalid limit values (GHSA-v422-hmwv-36x6 / CVE-2026-12590).
`v01.02.01`	`1.2.1`	2026-07-17	Retro cross-review follow-up: `export` json+limit filters branches to the retained thoughts (latent leak, not tool-reachable), with a regression test.
`v01.02.00`	`1.2.0`	2026-07-17	Audit remediation: correctness cluster (persistence, state machine, validation, protocol), a `vitest` unit-test layer, and Tier-1 features (mermaid review, template coverage, related thoughts, structuredContent).
`v01.01.01`	`1.1.1`	2026-05-15	4-gate quality directive compliance: added Biome, aligned CI, applied cosmetic source cleanup, and synchronized SERVER_VERSION to `1.1.1`.
`v01.01.00`	`1.1.0`	2026-05-12	Refinements for depth enforcement, active thought-reference validation, update record returns, real markdown merge output, optional file persistence, and expanded smoke coverage.
`v01.00.00`	`1.0.0`	2026-05-12	First LCV Ultrabrain MCP release: branded tool surface, session lifecycle, branching, merging, validation, analysis, prompts, resources, Pages, CI, publish, and StepSecurity baseline.

What It Does

ultrabrain-mcp is an LCV-created MCP server for local, structured reasoning before engineering work is closed. It gives agents a single branded gate for:

step-by-step reasoning with branches and revisions;
quality metrics, confidence, budget mode, and meta checkpoints;
bias detection and counterexample prompts;
explicit evidence, assumptions, alternatives, risks, and next actions;
session review, validation, metrics, export, prompts, and resources.

The server does not call external LLM APIs. It is a local MCP reasoning scratchpad and quality gate, so source code and private task context stay inside the active MCP host.

Tools

Tool	Purpose
`ultrabrain_start`	Create a reasoning session and optionally seed the first thought.
`ultrabrain_think`	Append the canonical Ultrabrain reasoning step.
`ultrabrain_update`	Strengthen an existing thought with evidence, risks, confidence, or metrics.
`ultrabrain_branch`	Create or continue an alternative reasoning path.
`ultrabrain_merge`	Merge branch insights into a synthesis, best-evidence path, or decision.
`ultrabrain_validate`	Check evidence, alternatives, verification, bias, and closure gaps.
`ultrabrain_analyze`	Summarize quality, confidence, labels, bias counts, and recommendations.
`ultrabrain_review`	Render a session as summary, linear chain, tree, markdown, JSON, or Mermaid.
`ultrabrain_status`	Show session state, thought count, branches, and latest quality score.
`ultrabrain_history`	Return recent thought records.
`ultrabrain_export`	Export a session as markdown, text, or JSON.
`ultrabrain_metrics`	Return aggregate session and reasoning metrics.
`ultrabrain_templates`	List built-in LCV engineering reasoning templates.
`ultrabrain_reset`	Clear one session, or all sessions, removing their persisted files too.

Canonical Example

{
  "thought": "Map the failure, list evidence, compare alternatives, and choose the next verification step.",
  "thought_number": 1,
  "total_thoughts": 4,
  "next_thought_needed": true,
  "mode": "hybrid",
  "step_type": "analysis",
  "evidence": ["The failing behavior was reproduced locally."],
  "alternatives": ["patch the caller", "patch the shared parser"],
  "risks": ["a shared parser change can affect unrelated hosts"],
  "next_actions": ["run the focused test", "inspect the shared call path"],
  "quality_metrics": {
    "logical_consistency": 4,
    "completeness": 4,
    "objectivity": 4,
    "practicality": 5,
    "clarity": 5
  },
  "response_format": "json"
}

MCP Configuration

Global npm installation target in the LCV Windows environment:

C:\npm-global\node_modules\@lcv-ideas-software\ultrabrain-mcp

Use the MCP server name ultrabrain in host configs:

{
  "mcpServers": {
    "ultrabrain": {
      "command": "ultrabrain-mcp",
      "args": []
    }
  }
}

Development checkout and global installation are intentionally separate. Do not create a junction or symlink from C:\npm-global\node_modules\@lcv-ideas-software\ultrabrain-mcp to the workspace checkout.

Optional local persistence can be enabled per host with ULTRABRAIN_STATE_DIR or ULTRABRAIN_PERSIST_DIR. When unset, sessions remain process-local.

Development

npm install
npm test
npm run format:public:check
npm pack --dry-run

The smoke test starts the built MCP server over stdio, lists tools, verifies the branded ultrabrain_* surface, exercises session start, thought, branch, merge, validation, status, export, prompts, and resources.

Release Automation

This repository follows the LCV package baseline:

CI runs on main pull requests and pushes.
Dependabot tracks npm and GitHub Actions updates.
Pages deploys the static site from site/ using ultrabrain-mcp.lcv.dev.
Auto-tagging derives padded public tags from package.json version.
Publish workflow releases to npmjs.com, GitHub Packages, and GitHub Releases.
StepSecurity Harden-Runner is enabled on workflows.

Research

See docs/research-matrix.md. Ultrabrain imports ideas only at the architecture level. It does not copy third-party code, text, branding, non-English localization strings, or external model/API behavior.

Repository conventions

License: Apache-2.0. See NOTICE and THIRDPARTY.
Security disclosure: see SECURITY.md.
Code of conduct: see CODE_OF_CONDUCT.md.
Changelog: CHANGELOG.md.
Contributing: see CONTRIBUTING.md.
Sponsorship: see the repo's Sponsor button or central sponsor page.
Action pinning: all GitHub Actions are pinned by full SHA per supply-chain hardening baseline.
Code owners: .github/CODEOWNERS.

License

Apache-2.0. See LICENSE, NOTICE, and THIRDPARTY.

Copyright 2026 LCV Ideas & Software
_{LEONARDO CARDOZO VARGAS TECNOLOGIA DA INFORMACAO LTDA
Rua Pais Leme, 215 Conj 1713 - Pinheiros
São Paulo - SP - CEP 05424-150
CNPJ: 66.584.678/0001-77 - IM: 3039854}

Keywords

mcp model-context-protocol reasoning ultrabrain quality-gate engineering lcv