Neuromcp MCP server

Read from the package source without running it. The installed server may list more.

• agent_conflicts

  Find conflicting knowledge between different agents on the same topic.

• backfill_embeddings

  Recompute embeddings for all memories missing from the vector store. Also syncs FTS index.

• cite_memories

  Attach a late verdict to a previously-logged retrieval event. Use when the agent answers first and a critic scores the answer afterward. Updates the memory_usefulness prior based on which retrieved memories were cited + outcome.

• cluster_memorieswrite action

  Run k-means clustering on memories in a namespace. Groups semantically related memories into clusters. Returns cluster labels, sizes, and assignments.

• compress_memories

  Compress old similar memories into digest memories. Reduces DB size while preserving knowledge. Hard-deletes ancient zero-access tombstones.

• compute_centralitywrite action

  Run weighted PageRank over the knowledge graph to compute entity centrality scores. Entities with more connections and higher-weight edges rank higher. Persists results for search boosting.

• consolidatewrite action

  Run consolidation: merge near-duplicates, decay stale memories, prune low-value, sweep expired, purge old tombstones. Set commit=true to apply.

• create_entitywrite action

  Create or update an entity in the knowledge graph. Entities represent concepts, people, tools, or any named thing.

• create_relationwrite action

  Create a typed relation between two entities in the knowledge graph. Supports temporal validity.

• end_episode

  End an active episode. Optionally provide a summary, or one will be auto-generated from the most important memories in the episode.

• export_memories

  Export memories as JSONL or JSON for backup or migration.

• find_expert

  Find agents with expertise matching a query topic.

• find_transferable

  Find memories in a source namespace that could be useful in a target namespace. Scores by transferability (universal vs project-specific).

• forget_memory

  Tombstone (soft-delete) memories matching the given filters. At least one filter is required.

• generate_reflection

  Synthesise a meta-reflection memory from memories that have been proven helpful (helpful_count >= min_helpful). Safeguarded: only touches memories with explicit positive critic signal \u2014 no speculation on unvalidated content. Stored as category=reflection so downstream searches can include or exclude meta-memories explicitly.

• get_cluster_memories

  Get all memories in a specific cluster, ordered by distance from centroid.

• get_episode

  Get details of a specific episode including memory count.

• import_memories

  Import memories from JSONL or JSON data. Deduplicates by content hash.

• init_reviews

  Initialize spaced repetition for important memories that do not have a review schedule yet.

• list_clusters

  List all clusters in a namespace with their labels and memory counts.

• list_episodes

  List episodes in a namespace. Shows memory count per episode.

• log_retrieval

  Log a retrieval event so future searches can learn which memories are actually helpful. Call right after search_memory. Pass retrieved_ids (all top-K), cited_ids (those actually used in the answer, if known), and an outcome label (helpful/neutral/harmful). Usefulness scores are applied as a prior in future rankings.

• memory_stats

  Get statistics about stored memories: counts, categories, trust levels, importance, and database size.

• memory_timeline

  Track how knowledge about a topic evolved over time. Follows supersession chains and shows full revision history.

• query_graph

  Traverse the knowledge graph starting from an entity. Returns connected nodes and edges up to max_depth hops. Supports temporal queries. Without entity_id/entity_name it returns an OVERVIEW: the top-N entities of the namespace ranked by number of relations (contradicts edges not counted), with the relations among them; internal memory_proxy entities that only back contradicts edges are excluded fr

• recall_answer

  Answer a question FROM memory: runs hybrid retrieval, then returns a synthesized, CITED extractive answer (every sentence traces to a stored memory id) PLUS an explicit gap-analysis \u2014 what memory does NOT cover and the freshness boundary (stale_since). Returns status "not_in_memory" instead of fabricating when nothing matches. Deterministic, no LLM. Prefer this over search_memory when you nee

• recall_memory

  Recall memories by ID, namespace, category, or tags without semantic search.

• register_agent

  Register or update an agent profile with expertise topics. Auto-counts memories.

• review_memory

  Record a review of a memory. Quality 0-5 (SM-2 scale: 0=forgot, 5=perfect). Updates interval and schedules next review.

• review_queue

  Get memories due for spaced repetition review. Returns overdue memories ordered by urgency + importance.

• search_all

  Unified search across both extracted memories and verbatim text. Returns results with source labels and per-source quotas.

• search_claims

  Search atomic claims extracted from memories. Claims are verifiable facts with subject-predicate-object structure.

• search_memory

  Search memories using hybrid vector + full-text search with RRF ranking, graph boost, and cognitive priming. Supports temporal queries (valid_at) to find what was true at a specific time.

• search_verbatim

  Search raw verbatim text using full-text search. Returns exact matches from stored conversations. Use for literal recall.

• start_episode

  Start a new episode (session/task context). Memories stored with this episode_id will be grouped together. Use to track what happened during a session.

• store_memory

  Store a new memory with semantic deduplication, contradiction detection, surprise scoring, and entity extraction. Returns the memory ID, contradictions found (resolution supersede/coexist are claim-backed and recorded as graph edges; flag is heuristic-only and reported here but never stored in the graph), surprise score, and extracted entities.

• store_verbatim

  Store raw conversation text verbatim \u2014 no summarization, no consolidation, never pruned. Use for exact recall of what was said.

• summarize_cluster

  Generate an extractive summary of a cluster. Selects the most central, representative sentences from cluster memories using embedding centrality.

• summarize_episode

  Generate an extractive summary of an episode. Selects the most central, representative sentences from episode memories.

• transfer_memorieswrite action

  Copy memories from source to target namespace. Optionally adapts content by stripping project-specific references.

• update_importancewrite action

  Recalculate adaptive importance for all memories in a namespace. Boosts frequently accessed, recently relevant, and graph-central memories. Run after clustering and PageRank for best results.

• usefulness_stats

  List memories ranked by observed usefulness (helpful vs harmful citation ratio). Use to inspect which memories the agent actually leans on, or to pick high-confidence source material for reflection.

• verbatim_stats

  Get statistics about verbatim storage: total entries, size, and distribution by namespace.

• wiki_briefing

  Generate a structured briefing from the wiki: active projects, unprocessed sources, recent changelog entries, stale pages needing attention. Use for morning status checks.

• wiki_ingest

  Read a file from the wiki raw-sources/ directory and extract structured metadata (title, type, key concepts, related pages). Returns analysis the LLM uses to decide which wiki pages to create or update. Does NOT write pages itself.

• wiki_lint

  Scan all wiki pages and check for health issues: missing frontmatter, pages not in index.md, stale pages (>30 days), thin pages (<5 lines), unprocessed raw sources, broken related links. Writes lint-report.md.

• Code scan150 source files scanned15/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Safety score

77/100

higher than 55% of 3,470 Web search servers

Tools

46

the typical Web search server has 5

Tools that change things

15%

typical: 0%. Fewer write tools means less an agent can break

GitHub stars

4

more than 75% of 1,786 Web search servers

Downloads a week

191

more than 70% of 827 Web search servers with a package

Grade history

• 2026-09-19restoreD → Bscore 77: npm install lifecycle script present; npm install lifecycle script present

Neuromcp: common questions

Is Neuromcp MCP server safe?

Mostly: it is graded B (77/100). Read the Neuromcp safety report

How do I install Neuromcp?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does Neuromcp need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Neuromcp maintained?

The last commit was 20 days ago (2026-10-15). The latest release is v0.30.2.

What can I use instead of Neuromcp?

Servers from other publishers that do the same job: Octocode MCP server, Crg MCP server and Shodh Memory MCP server. Compare all Neuromcp alternatives.

How does Neuromcp compare with other Web search MCP servers?

safety score 77/100 (higher than 55% of 3,470 Web search servers); tools 46 (the typical Web search server has 5); tools that change things 15% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.