neruva-mcp 0.5.0

Model Context Protocol server for Neruva — typed Records substrate (decisions, mistakes, llm_turns, tool_calls), KG, causal do-operator, analogy, and a Pinecone-compatible memory layer. Drop-in for any MCP host.

neruva-mcp

Model Context Protocol server for Neruva — text-embeddable Pinecone-compatible vector memory + HD-native substrate (knowledge graphs, analogy, causal do-operator). Drop-in for any MCP host. Same 22 tools as the TypeScript package, for Python-only hosts.

Install

pip install neruva-mcp
export NERUVA_API_KEY=...        # from https://app.neruva.io

Or zero-install via uvx:

uvx neruva-mcp

Use

Add to your MCP host's config. Example for Claude Code:

claude mcp add neruva -- uvx neruva-mcp -e NERUVA_API_KEY=YOUR_KEY

Or run directly:

NERUVA_API_KEY=YOUR_KEY neruva-mcp

The 4-layer mental model

• Memory = semantic recall (Pinecone-compatible drop-in)
• KG = mutable structured state (deploy state, project status, refactor tracking)
• Causal = "if I do X, what happens?" (Pearl do-operator)
• Analogy = pattern transfer in HD feature space (experimental, sub-ms)

Tools (22)

Memory

Tool	What it does
memory_embed	Encode texts to D=1024 vectors via the server-side static-MRL encoder. No BYOE.
memory_upsert_text	Embed and upsert text in one call -- the all-in-one for new users
memory_query_text	Embed a text query and search in one call
memory_create_index	Create a Pinecone-compatible vector index
memory_list_indexes	List your indexes
memory_describe_index	Describe one index
memory_stats	Per-namespace vector counts
memory_upsert	Insert/update raw vectors
memory_query	Cosine top-K search (raw vectors)
memory_fetch	Fetch vectors by id
memory_update	In-place edit values/metadata
memory_delete	Delete by id
memory_export	Portable .nmm export
memory_import	.nmm import
memory_bind_role	Bind a role atom for compound queries
memory_read_roles	Recover bound role atoms

HD-native substrate

Tool	What it does
hd_kg_add_fact	Add (subject, relation, object) to a KG (sharded K=16)
hd_kg_query	Query KG for object of (subject, relation)
hd_kg_delete_fact	Cancel a previously-added fact (mutable state)
hd_analogy	Four-term analogy in HD space (n_feat up to 20)
hd_causal_add_worlds	Add worlds to a structural causal model
hd_causal_query	Observational or interventional (Pearl do-operator)

Auto-record (opt-in, 0.4.0+)

Set NERUVA_AUTO_RECORD=<index>/<namespace> and every tool call the agent makes is auto-upserted into that namespace as a side-effect.

# single-agent
NERUVA_AUTO_RECORD=brain/main

# multi-agent: one namespace per agent
NERUVA_AUTO_RECORD=brain/support-bot
NERUVA_AUTO_RECORD=brain/research-agent

Each record carries metadata {kind: "tool_call", tool, latency_ms, ts}. memory_* tools are excluded to prevent loops. Fire-and-forget: never blocks or breaks the call. ~1.2 KB per tool call.

Env

Variable	Default
NERUVA_API_KEY	required
NERUVA_URL	https://api.neruva.io
NERUVA_AUTO_RECORD	optional <index>/<namespace> to enable auto-record

License

MIT — Clouthier Simulation Labs.