Neuromcp MCP server
Semantic memory for AI agents with hybrid search, knowledge graph, and consolidation
4 stars277 downloads/wk
Reviews
Write oneNobody has reviewed Neuromcp yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Neuromcp tools (46, 7 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
agent_conflictsFind conflicting knowledge between different agents on the same topic.
backfill_embeddingsRecompute embeddings for all memories missing from the vector store. Also syncs FTS index.
cite_memoriesAttach 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 actionRun k-means clustering on memories in a namespace. Groups semantically related memories into clusters. Returns cluster labels, sizes, and assignments.
compress_memoriesCompress old similar memories into digest memories. Reduces DB size while preserving knowledge. Hard-deletes ancient zero-access tombstones.
compute_centralitywrite actionRun 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 actionRun consolidation: merge near-duplicates, decay stale memories, prune low-value, sweep expired, purge old tombstones. Set commit=true to apply.
create_entitywrite actionCreate or update an entity in the knowledge graph. Entities represent concepts, people, tools, or any named thing.
create_relationwrite actionCreate a typed relation between two entities in the knowledge graph. Supports temporal validity.
end_episodeEnd an active episode. Optionally provide a summary, or one will be auto-generated from the most important memories in the episode.
export_memoriesExport memories as JSONL or JSON for backup or migration.
find_expertFind agents with expertise matching a query topic.
find_transferableFind memories in a source namespace that could be useful in a target namespace. Scores by transferability (universal vs project-specific).
forget_memoryTombstone (soft-delete) memories matching the given filters. At least one filter is required.
generate_reflectionSynthesise 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_memoriesGet all memories in a specific cluster, ordered by distance from centroid.
get_episodeGet details of a specific episode including memory count.
import_memoriesImport memories from JSONL or JSON data. Deduplicates by content hash.
init_reviewsInitialize spaced repetition for important memories that do not have a review schedule yet.
list_clustersList all clusters in a namespace with their labels and memory counts.
list_episodesList episodes in a namespace. Shows memory count per episode.
log_retrievalLog 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_statsGet statistics about stored memories: counts, categories, trust levels, importance, and database size.
memory_timelineTrack how knowledge about a topic evolved over time. Follows supersession chains and shows full revision history.
query_graphTraverse 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_answerAnswer 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_memoryRecall memories by ID, namespace, category, or tags without semantic search.
register_agentRegister or update an agent profile with expertise topics. Auto-counts memories.
review_memoryRecord a review of a memory. Quality 0-5 (SM-2 scale: 0=forgot, 5=perfect). Updates interval and schedules next review.
review_queueGet memories due for spaced repetition review. Returns overdue memories ordered by urgency + importance.
search_allUnified search across both extracted memories and verbatim text. Returns results with source labels and per-source quotas.
search_claimsSearch atomic claims extracted from memories. Claims are verifiable facts with subject-predicate-object structure.
search_memorySearch 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_verbatimSearch raw verbatim text using full-text search. Returns exact matches from stored conversations. Use for literal recall.
start_episodeStart 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_memoryStore 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_verbatimStore raw conversation text verbatim \u2014 no summarization, no consolidation, never pruned. Use for exact recall of what was said.
summarize_clusterGenerate an extractive summary of a cluster. Selects the most central, representative sentences from cluster memories using embedding centrality.
summarize_episodeGenerate an extractive summary of an episode. Selects the most central, representative sentences from episode memories.
transfer_memorieswrite actionCopy memories from source to target namespace. Optionally adapts content by stripping project-specific references.
update_importancewrite actionRecalculate 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_statsList 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_statsGet statistics about verbatim storage: total entries, size, and distribution by namespace.
wiki_briefingGenerate a structured briefing from the wiki: active projects, unprocessed sources, recent changelog entries, stale pages needing attention. Use for morning status checks.
wiki_ingestRead 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_lintScan 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.
Public scan report
scanner v0.1.8 · 2026-09-19 · same rubric, same numbers if you re-run it
- Code scan147 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 4 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Findings (2)
- mediumnpm install lifecycle script present
install.script - mediumnpm install lifecycle script present
install.scriptpackage.json: … eval/runner.ts --update-baseline", "postinstall": "node scripts/download-model.mjs || tru…
Grade history
- 2026-09-19restoreD → Bscore 77: npm install lifecycle script present; npm install lifecycle script present
Install directly
Runs npx -y neuromcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add neuromcp -- npx -y neuromcp
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, Claude Desktop or Cursor 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 4 days ago (2026-09-15). The latest release is v0.29.5.
- What can I use instead of Neuromcp?
- Servers from other publishers that do the same job: Octocode MCP server, Codeseeker MCP server and Junê MCP server. Compare all Neuromcp alternatives.
Alternatives to Neuromcp
Same job from other publishers: the closest match first, then the best rated.
- not reviewedEstablishedA
- CodeseekerGraph-powered code intelligence with semantic search and knowledge graph for AI assistantsnot reviewedGrowingC
- JunêShared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructionsnot reviewedGrowingB
- Better Code Review GraphToken-efficient code review knowledge graph: semantic search and call-graph resolution.not reviewedGrowingB
- SocraticodeMCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.not reviewedEstablishedB