Provider REST API

9 actions

Connect Claude to Neo4j

Explore a Neo4j graph's labels, relationship types, properties, indexes and constraints, and run Cypher against it. Toolspoke puts 9 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: User and password
Actions exposed: 9
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Neo4j
Open the marketplace in your workspace, add Neo4j to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with user and password. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Neo4j shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Neo4j asks for

User and password. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

HTTPS endpointRequired: Aura: console.neo4j.io → Instances → your instance → Connection URI, with neo4j+s:// replaced by https://. Self-managed: the server's HTTP(S) connector, usually https://host:7473 or http://host:7474, reachable from the internet. No path.; https://abcd1234.databases.neo4j.io
User and passwordRequired: The database user and its password joined by a colon, sent as HTTP Basic. Aura gives you these when the instance is created. Use a user with a read-only role unless you mean to grant the write action.; neo4j:my-password
DatabaseOptional: The database to query. Aura instances have one, called neo4j.; neo4j

What Claude can do in Neo4j

9 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 8Reads
Writes: 0Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

server_info
Report the Neo4j version and edition. Call this first to confirm the connection, the credential and the database name all work.
list_labels
List every node label in the database.
list_relationship_types
List every relationship type in the database.
node_properties
List the properties found on each combination of node labels, with their types and whether every node has them. Use it to learn the graph's shape before writing a query. It samples the store, so it can be slow on a very large graph.
relationship_properties
List the properties found on each relationship type, with their types and whether every relationship has them.
list_indexes
List the database's indexes - name, type, the labels or types and properties they cover, and whether each is online.
list_constraints
List the database's constraints - uniqueness, existence and key rules - with the labels and properties they apply to.
run_read_query
Run one read-only Cypher statement and return the rows. Pass values as `parameters` and refer to them as $name in the statement - never paste values into the Cypher. Sent in Read access mode, so a statement that writes is refused by the server. Include your own LIMIT.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

run_write_query
Run one Cypher statement that may write: CREATE, MERGE, SET, DELETE, or a schema command. Destructive because DETACH DELETE and DROP remove data with no undo. Pass values as `parameters`, never pasted into the Cypher.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 9 actions above are the whole of it. A call to any other name is refused before it reaches Neo4j rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Neo4j of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Neo4j: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Neo4j. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Neo4j's own rate limits. A call that Neo4j refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Neo4j?

9 named actions: 8 that only read and 1 that delete or permanently alter something. They include server_info, list_labels and list_relationship_types. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Neo4j connector need?

User and password. The connector asks for https endpoint and user and password, and optionally database. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Neo4j connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 9 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Neo4j connector not do?

The 9 actions above are the whole of it. A call to any other name is refused before it reaches Neo4j rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Neo4j of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Neo4j. An agent has to ask. Toolspoke does not retry, queue or back off around Neo4j's own rate limits. A call that Neo4j refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Neo4j's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Neo4j?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More database connectors

Browse all of them