// MCP TOOL REFERENCE

PYPI:CUBA MEMORYS TOOLS

13 tools from the Pypi:cuba Memorys MCP Server, categorised by risk level.

View the Pypi:cuba Memorys policy → Token cost: 1,824 tokens →

// ALL 13 PYPI:CUBA MEMORYS TOOLS

READ 10 tools

Read cuba_alarma Report errors immediately. Auto-detects patterns (≥3 similar = warning). Hebbian: similar errors get booste... Read cuba_alma CRUD knowledge graph entities (concepts, projects, technologies, patterns, people). Auto-boosts neighbors o... Read cuba_cronica Attach facts/lessons/decisions to entities. Auto-creates entity if not found. Dedup gate blocks near-duplic... Read cuba_decreto Record and query architecture/design decisions. Read cuba_eco RLHF feedback: positive boosts importance (Oja's rule), negative decreases, correct updates content. Read cuba_expediente Search past errors/solutions. Use 'proposed_action' as anti-repetition guard: warns if similar approach pre... Read cuba_faro Search memory BEFORE answering to ground responses. Returns grounding scores. Mode 'verify' checks claims a... Read cuba_jornada Track working sessions with goals and outcomes. Read cuba_remedio Mark an error as resolved with solution. Cross-references similar unresolved errors. Read cuba_vigia Knowledge graph analytics: summary (counts + token estimate), health (staleness, entropy, DB size), drift (...

WRITE 1 tools

Write cuba_puente Create edges between entities (uses, causes, implements, depends_on, related_to). 'traverse' explores conne...

DESTRUCTIVE 2 tools

Destructive cuba_forget GDPR Right to Erasure: cascading hard-delete of an entity and ALL references across observations, relations... Destructive cuba_zafra Memory maintenance: decay (exponential, halflife=30d), prune (remove low-importance), merge (deduplicate), ...

// FAQ

How many tools does the Pypi:cuba Memorys MCP server have? +

The Pypi:cuba Memorys MCP server exposes 13 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Pypi:cuba Memorys tools? +

Route the Pypi:cuba Memorys server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Pypi:cuba Memorys tools fall into? +

Pypi:cuba Memorys tools are categorised as Read (10), Write (1), Destructive (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.