LocalNest MCP

Return runtime status and active configuration summary for this MCP server.

Return a compact runtime health summary for fast smoke checks.

Return concise best-practice guidance for users and AI agents using this MCP.

Check npm for the latest localnest-mcp version on the selected channel (cached, default every 120 minutes).

Update localnest-mcp globally via npm and sync bundled skill. Supports stable, beta, or explicit version targets. Requires explicit user approval.

Bundle runtime status, memory state, and relevant recall for a non-trivial task in one call.

Return local memory feature status, consent state, and backend compatibility.

Recall the most relevant local memories for a task or query.

Capture a meaningful task outcome into the memory event pipeline with a simpler payload.

List stored memories with optional scope and kind filters.

Fetch one stored memory with revision history.

Store a durable local memory entry.

Update a stored memory entry and append a revision.

Delete a stored memory entry and all of its revisions.

Ingest a background work event and auto-promote meaningful events into durable memory.

List recently captured memory events and whether they were promoted into durable memory.

Find semantically similar memory entries that could be linked to a given memory. Uses dense embeddings (all-MiniLM-L6-v2) when available, falls back to token overlap. Returns candidates ranked by similarity without creating any relations — use localnest_memory_add_relation to confirm.

Link two memory entries with a named relation. Use to build a traversable knowledge graph (e.g. "depends_on", "contradicts", "supersedes", "related").

Remove a relation between two memory entries.

Return all memory entries linked to a given memory ID, traversing the knowledge graph one hop in both directions.

List configured local roots available to this MCP server.

List first-level project directories under a root.

Return a compact tree of files/directories for a project path.

Return local semantic index status and metadata.

Return active embedding backend/model status and vector-search readiness.

Build or refresh semantic index for a project or across all roots.

Search file paths and names matching a query. Use this first when looking for a module, feature, or component by name (e.g. "sso", "payment", "auth"). Much faster than content search for module discovery, and handles cases where the keyword only appears in file/directory names.

Search text across files under a project/root and return matching lines. Best for exact symbol names, imports, or known identifiers. Use use_regex=true for patterns (e.g. "async\s+function\s+get\w+"). Use context_lines to include surrounding lines with each match.

Run lexical + semantic retrieval and return RRF-ranked results.

Look up symbol definitions/exports by name using fast regex search.

Find call sites and import usages of a symbol by name.

Read a bounded chunk of a file with line numbers.

Return a high-level summary of a project directory.