MCP servers and agent tools for Neo4j
AgentSidekick indexes 15 DER agent products that mention Neo4j; 15 of them have a full profile and are listed below. The most-starred tools that are their own repository are NornicDB (933 stars), agent-memory (611 stars) and atlas-mcp-server (480 stars) SRC. Figures as of 2026-11-21.
Neo4j tools with a full profile
Search the directoryRanked by GitHub stars of the product's own repository. Products that live in a subfolder of a larger repository (marked “repo”) show that whole repository's stars and are ranked after them; products without a public repository come last.
| # | Product | Type | Hosting | Licence | Stars | Last push | Publisher | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | NornicDBNornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server. | MCP server | — | MIT | 933 | today | orneryd | |
| 2 | agent-memoryA graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j. | Infrastructure | — | Apache-2.0 | 611 | 2d ago | neo4j-labs | |
| 3 | atlas-mcp-serverA Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research. | MCP server | — | Apache-2.0 | 480 | 1y ago | cyanheads | |
| 4 | Neo4j GDS AgentNeo4j Graph Data Science MCP server | MCP server | Local | MIT | 100 | 3d ago | neo4j-contrib | |
| 5 | ReverieGraph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search | MCP server | Local | MIT | 67 | 15d ago | knowall.ai | |
| 6 | memwrightEmbedded memory for AI agents with SQLite, pgvector, and Neo4j graph search. | MCP server | Local | MIT | 14 | 2mo ago | bolnet | |
| 7 | mcp-graphql-enhancedGraphQL gateway for LLMs. Handles huge GitHub GraphQL & @neo4j/graphql schemas without crashing | MCP server | Local | MIT | 7 | today | letoribo | |
| 8 | neo4j-mcp-canaryNeo4j MCP Canary — The canary goes first so the rest of us know what's coming | MCP server | Local | — | 2 | 25d ago | neo4j-labs | |
| 9 | RationalBloksDeploy production REST and Neo4j Graph APIs from JSON schemas in seconds. | MCP server | Remote and local | — | 1 | 11d ago | rationalbloks.com | |
| 10 | mcp-neo4j-aura-managerMCP server for Neo4j Aura Database Instance Manager. | MCP server | Local | MIT | — | 2mo ago | neo4j-contrib | |
| 11 | mcp-neo4j-cypherA simple Neo4j MCP server that allows you to run Cypher queries against a Neo4j database. | MCP server | Local | MIT | — | 2mo ago | neo4j-contrib | |
| 12 | mcp-neo4j-data-modelingA simple Neo4j MCP server for creating graph data models. | MCP server | Local | MIT | — | 2mo ago | neo4j-contrib | |
| 13 | mcp-neo4j-memoryMCP Neo4j Knowledge Graph Memory Server | MCP server | Local | MIT | — | 2mo ago | neo4j-contrib | |
| 14 | toro4nDraw, shape, and edit Neo4j graph data models in toro4n with your AI assistant. | MCP server | Remote | — | — | — | toro4n.com | |
| 15 | wisdomgraphNeo4j-native DIKW memory for Claude Code — knowledge that compounds across sessions | MCP server | Local | MIT | — | 4mo ago | cklam12345 |
Hosting across all 15 profiled: 1 remote, 10 local, 1 both, 3 not declared. DER
Product-type mix
Which forms the tools take. Indexed covers every matching record; profiled only those with a page.
| Type | Indexed | Share | Profiled |
|---|---|---|---|
| MCP servers | 14 | 93.3% | 14 |
| Infrastructure | 1 | 6.7% | 1 |
What these tools do
Most common capabilities among the profiled tools, matched from their descriptions by keyword rules.
Capabilities of Neo4j toolsDER
Profiled products mentioning Neo4j, by capability, top 10. A product can have several. As of 2026-11-21.
Show the data as a table
| profiled products | |
|---|---|
| Knowledge Graphs | 15 |
| Graph Querying | 15 |
| API Tooling | 2 |
| GraphQL Tools | 2 |
| Vector Databases | 2 |
| Vector Storage | 2 |
| Agent Memory | 1 |
| Local & Open Models | 1 |
| Retrieval-Augmented Generation | 1 |
| Reranking | 1 |
Demand signal
How often developers discuss this integration alongside MCP in public GitHub issues.
938 SRC public GitHub issues contain the phrase Neo4j mcp
(search run 2026-11-21). Run the same search on GitHub.
This measures developer discussion, not buyers or revenue: an issue may be a bug report, a feature request or a passing mention. The count is GitHub's own estimate for the query "Neo4j mcp" in:title,body is:issue.
Segment statisticsDER
All 15 indexed products, not only profiled ones. Calculated 2026-11-21.
- Launches
- 3 in the last 90 days, 2 in the 90 days before (+50%)DER
- Products with a repository
- 9 of 15 have whole-repository star countsDER
- Combined stars
- 2,215DER
- Median stars
- 67DER
- Largest project's share
- 42% of all stars in the segmentDER
- Concentration (HHI)
- 0.303, as concentrated as about 3 equally starred projectsDER
- Open-source share
- 80%DER
- Label
- Lagging the catalogueDER
How the label is set: size is this integration's percentile among all 111 integrations by indexed products (80th or above is crowded, 30th or below is thin). Momentum compares the ratio of launches in the last 90 days to the 90 before with the same ratio for the whole catalogue, so a booming ecosystem does not make every segment look like it is accelerating; it needs at least 5 launches across both windows. A segment can launch more products than last quarter and still be labelled slowing if the catalogue grew faster.
Vendor API
Neo4j has a public API CUR. API docs (as recorded) The link has not been checked since it was recorded.
Neo4j is not recorded as primarily a paid business product.
Opportunity score
Better agent tooling for Neo4j scores 52.0 HEU of 100 (demand component 56, gap 64; competition high, confidence medium; calculated 2026-11-21). Scores rank integrations against each other; they do not predict revenue.
How products are matched, and the limits
A product is counted when its name, description or repository topics contain one of these aliases (case-insensitive, whole words): neo4j
, cypher query
, neo4j aura
. A product named exactly “Neo4j” is skipped, since it is the service itself.
Which alias matched, across the 15 indexed records: neo4j
15.
Keyword matching over-counts tools that only mention Neo4j in passing (for example as where their code is hosted) and misses tools that integrate with it without naming it. Treat the counts as an upper bound on dedicated tools and a lower bound on everything that touches Neo4j.
No profiled product's publisher, GitHub owner or repository owner matches Neo4j's own name, so this page does not split vendor tools from community ones.
Sources
- GitHub issue search: github.com (external)checked
- API documentation (as recorded, unverified): neo4j.com (external)check date not recorded
Product records come from the official MCP Registry, GitHub, Open VSX and plugin marketplaces; each profile lists its own sources. Methodology
Page data last updated .