Skip to main content
Glama
LCV-Ideas-Software

ultrabrain-mcp

by LCV-Ideas-Software
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

ultrabrain-mcp

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 target: v01.02.11 (npm package 1.2.11). 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

v01.02.11

1.2.11

2026-08-05

Adds the read-only ultrabrain_server_info tool (cross-review server_info parity): identity, release, capabilities, tool/prompt/resource surface, persistence data_dir/config, session count, engine limits, and security policy.

v01.02.10

1.2.10

05/08/2026

Moves GitHub administration authority to a non-deploying protected environment, verifies canonical npm registry routing, and separates urgent CodeQL security updates from routine dependency batches.

v01.02.09

1.2.9

03/08/2026

Uses checksum-verified npm 12.0.2, accepts only documented 401/identity-concealing 404 in the negative OIDC probe, requires exact 201 in the positive probe, isolates the writer, and updates vulnerable dependencies.

v01.02.08

1.2.8

28/07/2026

Completes the provenance-bound 1.2.5/1.2.6 release recovery, preserves the ambiguous 1.2.4 drafts as audit evidence, bundles MCP SDK 1.30.0, removes Socket/StepSecurity integrations, and makes the SDK license regression version-aware.

v01.02.07

1.2.7

22/07/2026

Makes draft-release discovery eventual-consistency-safe by waiting for the exact server-issued release id before any asset upload.

v01.02.06

1.2.6

22/07/2026

Makes immutable release reconciliation preserve valid false boolean metadata at every release boundary.

v01.02.05

1.2.5

22/07/2026

Binds draft discovery, mutations, asset transfers, and final verification to the exact immutable release identity.

v01.02.04

1.2.4

22/07/2026

Corrects npm tarball publication and adds provenance-safe tag/release recovery while preserving the immutable audit trail.

v01.02.03

1.2.3

22/07/2026

Ships a self-contained MCP bundle, clean-consumer verification, and provenance-bound multi-registry publication.

v01.02.02

1.2.2

21/07/2026

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

17/07/2026

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

17/07/2026

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

15/05/2026

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

12/05/2026

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

12/05/2026

First LCV Ultrabrain MCP release: branded tool surface, session lifecycle, branching, merging, validation, analysis, prompts, resources, Pages, CI, and publish automation.

Related MCP server: mcp-llm-eval

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.

ultrabrain_server_info

Report server version, capabilities, tool surface, data dir, and limits.

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.

  • Third-party actions are pinned to reviewed immutable commit SHAs.

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

Links

License

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

Install Server
A
license - permissive license
A
quality
A
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
1wRelease cycle
13Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

View all tools

Related MCP Servers

View all related MCP servers

Related MCP Connectors

  • Reasoning Commons

    AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.

  • PlanWright

    Control plane for autonomous software labor. Agents claim objectives over MCP with audit trail.

  • copilotcliswitchgate-mcp

    Remote MCP for Copilot CLI switch gate MCP, structured receipts, audit logs, and reviewer-ready evid

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/LCV-Ideas-Software/ultrabrain-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server