MCP100 Assessment

Editorial verdict

Recommended for graph exploration when database credentials are least-privilege, write operations are constrained, and production graph changes remain supervised.

Reviewed July 30, 2026

Task Fit

Mapped

Working with structured data

Trust

Reviewed

A dated editorial review is published on the MCP detail page.

Maintenance

Activity observed

A dated repository or package update is available; editorial maintenance review is still pending.

Popularity

Signals available

Visible usage signals are shown for discovery only, not as proof of safety.

Best for

Graph-database exploration, modeling, and query workflows against Neo4j.

Not ideal for

Teams outside the publisher ecosystem or without least-privilege credentials

Avoid if

The connected identity is broader than the task requires
Tool calls cannot be reviewed before consequential mutations

Trade-offs

Cypher queries can disclose connected data or become expensive; production credentials should be read-only by default.

Evidence scope

Evidence

Current source snapshot

Popularity

295 MCP repository stars

No MCP-specific package metric is stored

Repository identity: neo4j/mcp

Package identity: neo4j-mcp-server

Stars observed September 24, 2026 · Downloads observation date unavailable

Exact reviewed repository identity; current GitHub repository stars are eligible as repository-level adoption evidence.

No exact MCP-specific package metric was sufficiently verified in this snapshot; preserve existing Not measured/unknown rather than guessing.

Maintenance

Publisher activity observed September 23, 2026

Current source snapshot

Trust review

Source relationship: First-party MCP

Reviewed July 30, 2026

Sources

GitHub repository ↗

Evidence-backed setup

Install & Agents

Choose your MCP client. A client connects to the MCP server; the language model is selected inside that client. Only stored, source-backed configurations are shown.

Claude Code

Local stdio

MCP100 logic checked

claude mcp add neo4j -e NEO4J_URI="bolt://localhost:7687" -e NEO4J_USERNAME="neo4j" -e NEO4J_PASSWORD="YOUR_NEO4J_PASSWORD" -e NEO4J_DATABASE="neo4j" -e NEO4J_READ_ONLY="true" -e NEO4J_TELEMETRY="false" -e NEO4J_LOG_LEVEL="info" -e NEO4J_LOG_FORMAT="text" -e NEO4J_SCHEMA_SAMPLE_SIZE="100" -- python "-m" "neo4j_mcp_server"

The publisher connection details were combined with this client's official MCP transport configuration; installation was not executed by MCP100.

Verify safely: Restart Claude Code, confirm neo4j tools are listed, and perform one read-only test with non-sensitive data.

Uninstall and revoke

Remove neo4j from Claude Code, restart the client, remove any separately installed package, and revoke dedicated credentials if used.

Evidence & methodology

Publisher-documented setup is not the same as MCP100 execution testing. “MCP100 logic checked” means the stored configuration shape was reviewed, not that third-party MCP software was run.

Evidence checked 2026-08-12

Evidence 1 ↗Evidence 2 ↗

Read additional publisher installation details

From the publisher README

Publisher installation details

Original client setup and configuration retained from the publisher documentation.

View original README ↗

Publisher-documented clients

VS Code

These names appear in the publisher's installation documentation. MCP100-verified configurations are shown separately above when available.

Installation

Install with PyPI:

pip install neo4j-mcp-server

Otherwise see MCP documentation -> Installation.

Server configuration (VSCode)

Create / edit mcp.json:

{
  "servers": {
    "neo4j": {
      "type": "stdio",
      "command": "python",
      "args": ["-m", "neo4j_mcp_server"],
      "env": {
        "NEO4J_MCP_URI": "bolt://localhost:7687",
        "NEO4J_MCP_USERNAME": "neo4j",
        "NEO4J_MCP_PASSWORD": "password",
        "NEO4J_MCP_DATABASE": "neo4j",
        "NEO4J_MCP_READ_ONLY": "true",
        "NEO4J_MCP_TELEMETRY": "false",
        "NEO4J_MCP_LOG_LEVEL": "info",
        "NEO4J_MCP_LOG_FORMAT": "text",
        "NEO4J_MCP_SCHEMA_SAMPLE_SIZE": "100"
      }
    }
  }
}

See MCP documentation > Configuration for more details.

Loading optional publisher installation details…

Capability

What it does

Explore Neo4j schemas and graph data and run governed Cypher workflows.

Data & DatabasesSoftware & Technology

Representative uses

Graph-database exploration, modeling, and query workflows against Neo4j.

Important limits

Teams outside the publisher ecosystem or without least-privilege credentials

Tools4 toolsView tools

get-schema
Inspect Neo4j node labels, relationship types, and property keys so an agent can understand the graph schema before querying it.
read-cypher
Execute read-only Cypher queries against Neo4j to retrieve graph data without modifying the database.
write-cypher
Execute Cypher statements that can modify Neo4j data; this tool is not exposed when read-only mode is enabled.
list-gds-procedures
List Graph Data Science procedures available in the connected Neo4j instance so an agent can discover supported graph algorithms.

Context Footprint

~800 estimated schema tokens

Context impact: Low

Estimated token footprint of the MCP tool schemas exposed to the agent.

Approx. estimate

Whole-profile rough estimate only. Do not synthesize per-tool token values from this heuristic.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: The official server uses configured Neo4j URI and database credentials.
Permissions: Neo4j database users and roles control graph visibility and Cypher authority; read-only operation is documented.
Data handling: Authorized service data and tool results pass through the MCP server to the connected AI client. Review the publisher and client data policies before using sensitive data & databases information.
Cost: The MCP integration has no separately verified MCP100 price conclusion. Publisher subscriptions, API usage, compute, storage, and AI-client charges may apply.
Risk and cautions: Cypher queries can disclose connected data or become expensive; production credentials should be read-only by default. Use a test environment where practical, least-privilege credentials, narrowly enabled tools, and explicit confirmation for mutations. MCP100 did not execute third-party server code during this documentation review.

Related reviewed MCPs

Other options

Google MCP Toolbox for Databases

MCP100 Recommended

Connect MCP clients to enterprise databases with prebuilt or explicitly defined tools.

Choose this instead if

Choose Google MCP Toolbox for Databases instead if schema exploration and database-aware coding in development environments.

Connect MCP clients to enterprise databases with prebuilt or explicitly defined tools.

Compare with neo4j View Google MCP Toolbox for Databases details

Redis MCP

MCP100 Recommended

Manage and search Redis data through Redis's MCP server.

Choose this instead if

Choose Redis MCP instead if inspecting and manipulating Redis strings, hashes, lists, sets, sorted sets, streams, JSON, and search indexes.

Manage and search Redis data through Redis's MCP server.

Compare with neo4j View Redis MCP details

Supabase MCP

MCP100 Recommended

Connect AI tools to Supabase projects and development workflows.

Choose this instead if

Choose Supabase MCP instead if inspecting one Supabase project's schema, logs, advisors, and docs.

Connect AI tools to Supabase projects and development workflows.

Compare with neo4j View Supabase MCP details

Read publisher documentation

Publisher documentation

Publisher README

Original product, capability, tool, and usage documentation from the MCP publisher. Installation sections appear under Install & Agents.

View original README ↗

Neo4j MCP

Neo4j MCP gives AI assistants and LLM-powered tools direct, structured access to your Neo4j graph database. By implementing the Model Context Protocol (MCP), it acts as a bridge between any MCP-compatible client, such as Claude, Cursor, or VS Code with MCP support, and your Neo4j instance.

Features

Explore your graph schema - discover node labels, relationship types, and property keys
Let AI reason on your data model without prior knowledge
Run Cypher queries - execute, read, and write queries against your database in response to natural language prompts
Inspect and analyze data - retrieve nodes, relationships, and paths to answer questions, generate summaries, or feed data to other workflows

Tools

get-schema — introspect labels, relationship types, property keys
read-cypher — execute read-only Cypher queries that do not modify database data, enforced via EXPLAIN and Neo4j's query-type classification. Note: custom procedures or functions incorrectly classified as read-only by Neo4j may bypass this check; ensuring correct classification is the responsibility of the procedure/function maintainer.
write-cypher — execute write Cypher queries (disabled if NEO4J_MCP_READ_ONLY=true)
list-gds-procedures — list available GDS procedures

Links

Documentation: The official Neo4j MCP documentation.
Discord: The Neo4j discord channel.
Contributing Guide: Contribution workflow, development environment, mocks and testing.

For issues and feedback, you can also create a GitHub issue with reproduction details (omit sensitive data).

Loading optional publisher documentation…

FAQ

What can Neo4j MCP do?

Explore Neo4j schemas and graph data and run governed Cypher workflows.

Can Neo4j MCP inspect graph schemas and run Cypher queries?

Yes. The reviewed Neo4j MCP surface includes graph/schema inspection and Cypher query execution against the configured Neo4j database, subject to the database user's permissions.

Does Neo4j MCP work with Claude Code?

Yes. MCP100 reviewed an evidence-backed setup for Claude Code, but has not independently verified it with a live runtime test.

How does Neo4j MCP authenticate?

The official server uses configured Neo4j URI and database credentials.

Is Neo4j MCP safe to use with a production graph database?

Cypher queries can disclose connected data or become expensive; production credentials should be read-only by default. Use a test environment where practical, least-privilege credentials, narrowly enabled tools, and explicit confirmation for mutations. MCP100 did not execute third-party server code during this documentation review.

Is this an official MCP?

ecosystem:neo4j is listed as First-party MCP in MCP100’s current evidence.

Current official resources:

Publisher documentation ↗