io.github.LeandroPG19/cuba-memorys

io.github.LeandroPG19/cuba-memorysv0.20.0Memory & RAG

Persistent memory MCP server. 29 tools, BM25+MMR+OOD retrieval, CFR-21 audit, code graph.

In-path gate · all MCP tools

Using io.github.LeandroPG19/cuba-memorys in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire

Auditable install path →Watch it hold a drift →

Trust verdict · v1 advisory · method

REVIEWstatus: PARTIALfresh until 2026-08-28 23:03 UTC

screened 2026-07-29tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidence“No hidden actions”via static_description

Limits of this verdict

- Semantic screen only - the deterministic conformance probe has not run on this server
- Confidence is reported but not yet calibrated (v1)
- Screen reads the tool description, not the live behavior
- advisory
- registry description only no input schema

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-31).

Contracts can change after screening, with no version bump. The gate pins io.github.LeandroPG19/cuba-memorys’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown

[![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-leandropg19-cuba-memorys)](https://mcpindex.ai/server/io-github-leandropg19-cuba-memorys)

HTML

<a href="https://mcpindex.ai/server/io-github-leandropg19-cuba-memorys"><img src="https://mcpindex.ai/api/v1/badge/io-github-leandropg19-cuba-memorys" alt="mcpindex verdict" height="20" /></a>

Environment variables

DATABASE_URL

required

PostgreSQL connection URL (e.g. postgresql://user:pass@localhost:5432/brain)

CUBA_PROJECT_FILTER

Set to 'off' to disable v0.8 project scoping filters (admin/debug only).

CUBA_SYNC_DIR

Directory used by cuba_sync export/import (default ./.cuba-memorys/).

CUBA_JUDGE

cuba_juez backend selector: claude_cli | anthropic_api | heuristic | auto (default auto).

CUBA_JUEZ_CLI

Subprocess CLI used by ClaudeCodeJudge (default 'claude').

CUBA_JUEZ_MODEL

Model name passed to the judge backend (default 'claude-haiku-4-5').

ANTHROPIC_API_KEY

secret

API key for AnthropicApiJudge (only used when feature 'anthropic-api' is built in).

CUBA_REM_RELATION_BATCH

Isolated entities the REM cycle scans for relations per run (default 5, 0 disables).

CUBA_RERANKER_PATH

Directory holding the bge-reranker ONNX model; enables cross-encoder reranking (+93% nDCG on GPU).

CUBA_RERANK_FIXED_SHAPE

Pad reranker batches to a constant 512 tokens. Defaults on for GPU builds, off on CPU.

DATABASE_URL

required

PostgreSQL connection URL (e.g. postgresql://user:pass@localhost:5432/brain)

MCP quality score · maturity, not trust · methodology

freshness

completeness

installability

documentation

stability

Alternatives in Memory & RAG

Fodda Knowledge Graphs

ai.fodda/mcp-server

Expert-curated knowledge, brand, research & earnings intelligence — 31 tools, 220+ graphs.

Achriom

com.achriom/achriom

The media memory layer for AI agents and their humans. Books, movies, music, shows, and anime.

Lore Context

io.github.Lore-Context/lore-context-mcp

Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.

Install this server

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "cuba-memorys": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "cuba-memorys"
      ],
      "env": {
        "DATABASE_URL": "<database_url>",
        "CUBA_PROJECT_FILTER": "<cuba_project_filter>",
        "CUBA_SYNC_DIR": "<cuba_sync_dir>",
        "CUBA_JUDGE": "<cuba_judge>",
        "CUBA_JUEZ_CLI": "<cuba_juez_cli>",
        "CUBA_JUEZ_MODEL": "<cuba_juez_model>",
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "CUBA_REM_RELATION_BATCH": "<cuba_rem_relation_batch>",
        "CUBA_RERANKER_PATH": "<cuba_reranker_path>",
        "CUBA_RERANK_FIXED_SHAPE": "<cuba_rerank_fixed_shape>"
      }
    }
  }
}

Cursor (.cursor/mcp.json)

{
  "mcpServers": {
    "cuba-memorys": {
      "command": "npx",
      "args": [
        "-y",
        "--",
        "cuba-memorys"
      ],
      "env": {
        "DATABASE_URL": "<database_url>",
        "CUBA_PROJECT_FILTER": "<cuba_project_filter>",
        "CUBA_SYNC_DIR": "<cuba_sync_dir>",
        "CUBA_JUDGE": "<cuba_judge>",
        "CUBA_JUEZ_CLI": "<cuba_juez_cli>",
        "CUBA_JUEZ_MODEL": "<cuba_juez_model>",
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "CUBA_REM_RELATION_BATCH": "<cuba_rem_relation_batch>",
        "CUBA_RERANKER_PATH": "<cuba_reranker_path>",
        "CUBA_RERANK_FIXED_SHAPE": "<cuba_rerank_fixed_shape>"
      }
    }
  }
}

Cline (cline_mcp_settings.json)

npx -y -- cuba-memorys

Claude Code (claude mcp add)

claude mcp add --scope user cuba-memorys -- npx -y -- cuba-memorys

Gemini CLI (gemini mcp add)

gemini mcp add -s user cuba-memorys npx -y -- cuba-memorys

Claude Desktop (uvx)

{
  "mcpServers": {
    "cuba-memorys": {
      "command": "uvx",
      "args": [
        "--",
        "cuba-memorys"
      ],
      "env": {
        "DATABASE_URL": "<database_url>",
        "CUBA_PROJECT_FILTER": "<cuba_project_filter>",
        "CUBA_SYNC_DIR": "<cuba_sync_dir>",
        "CUBA_JUDGE": "<cuba_judge>",
        "CUBA_JUEZ_CLI": "<cuba_juez_cli>",
        "CUBA_JUEZ_MODEL": "<cuba_juez_model>",
        "ANTHROPIC_API_KEY": "<your-anthropic_api_key>",
        "CUBA_REM_RELATION_BATCH": "<cuba_rem_relation_batch>",
        "CUBA_RERANKER_PATH": "<cuba_reranker_path>",
        "CUBA_RERANK_FIXED_SHAPE": "<cuba_rerank_fixed_shape>"
      }
    }
  }
}

Verdict API

curl -s mcpindex.ai/api/v1/trust/server/io-github-leandropg19-cuba-memorys

Free-tier verdict as JSON: decision + dimensions + severity. Call it from your agent before it invokes a tool it just discovered.

Details

version: v0.20.0
category: Memory & RAG
verdict expires: 2026-08-28
quality: 80 / 100
operator: LeandroPG19

Listing

Listed from the official MCP registry. Unclaimed by its maintainer. Maintainer? Email us →

Provenance

Each verdict is bound to a hash of the exact description it judged, so a re-crawl that changes the text produces a new record rather than silently inheriting this one. Verdict history is hash-chained and anchored to Bitcoin via OpenTimestamps (latest confirmed at block 960,209). Verify it yourself.

Links

Repository →