io.github.neo4j-labs/neo4j-mcp-canary
Officialby neo4j-labs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEO4J_URI | No | Neo4j connection URI (required) | |
| NEO4J_DATABASE | No | Database name | neo4j |
| NEO4J_PASSWORD | No | Database password (required in STDIO mode; must be unset in HTTP mode) | |
| NEO4J_USERNAME | No | Database username (required in STDIO mode; must be unset in HTTP mode) | |
| NEO4J_LOG_LEVEL | No | Log level: debug, info, notice, warning, error, critical, alert, emergency | info |
| NEO4J_READ_ONLY | No | When true, write-cypher tool is not registered | false |
| NEO4J_TELEMETRY | No | Enable/disable anonymous telemetry | true |
| NEO4J_LOG_FORMAT | No | Log format: text or json | text |
| NEO4J_MCP_HTTP_PORT | No | HTTP server port (default 443 with TLS, 80 without) | |
| NEO4J_CYPHER_TIMEOUT | No | Execution timeout in seconds; 0 disables | 30 |
| NEO4J_TRANSPORT_MODE | No | Transport mode: stdio or http | stdio |
| NEO4J_CYPHER_MAX_ROWS | No | Per-call row cap on read-cypher/write-cypher; 0 disables | 1000 |
| NEO4J_CYPHER_MAX_BYTES | No | Per-call byte cap on response envelope; 0 disables | 900000 |
| NEO4J_SCHEMA_SAMPLE_SIZE | No | Nodes per label APOC examines when inferring schema | 1000 |
| NEO4J_MCP_HTTP_TLS_ENABLED | No | Enable TLS/HTTPS | false |
| NEO4J_HTTP_AUTH_HEADER_NAME | No | Header name to read credentials from | Authorization |
| NEO4J_MCP_HTTP_TLS_KEY_FILE | No | Path to TLS private key (required when TLS enabled) | |
| NEO4J_MCP_HTTP_TLS_CERT_FILE | No | Path to TLS certificate (required when TLS enabled) | |
| NEO4J_CYPHER_MAX_ESTIMATED_ROWS | No | EXPLAIN-time planner estimate above which read-cypher refuses a query; 0 disables | 1000000 |
| NEO4J_HTTP_ALLOW_UNAUTHENTICATED_PING | No | Allow unauthenticated ping health checks | true |
| NEO4J_HTTP_ALLOW_UNAUTHENTICATED_INITIALIZE | No | Allow unauthenticated initialize | true |
| NEO4J_HTTP_ALLOW_UNAUTHENTICATED_TOOLS_LIST | No | Allow unauthenticated tool listing | true |
| NEO4J_HTTP_ALLOW_UNAUTHENTICATED_NOTIFICATIONS_INITIALIZE | No | Allow unauthenticated notifications/initialize | true |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/neo4j-labs/neo4j-mcp-canary'
If you have feedback or need assistance with the MCP directory API, please join our Discord server