Skip to main content
Glama

RushDB MCP Server

Give your agent a memory layer. Via MCP.

Connect RushDB to any MCP-compatible AI client and your agent gains persistent, structured memory — semantically searchable and graph-traversable, without managing embeddings or schemas.

Works with ChatGPT, Claude.ai, Claude Desktop, Cursor, Windsurf, Gemini CLI, and any MCP-compatible tool.


Two ways to connect

Remote OAuth (no installation)

For ChatGPT, Claude.ai, and other web-based AI clients — connect directly without installing anything locally:

MCP endpoint: https://mcp.rushdb.com/mcp

Your client redirects to RushDB for OAuth sign-in and receives a scoped token. No API key setup required.

ChatGPT:

  1. Go to Settings → Connectors → Add connector

  2. Enter https://mcp.rushdb.com/mcp

  3. Sign in with your RushDB account

Claude.ai:

  1. Go to Settings → Integrations → Add integration

  2. Enter https://mcp.rushdb.com/mcp

  3. Authorize with your RushDB account


Local (RushDB Cloud API key)

For Claude Desktop, Cursor, Windsurf, VS Code, and other stdio MCP clients:

1. Get an API key at app.rushdb.com

2. Add to your MCP client config:

{
  "mcpServers": {
    "rushdb": {
      "command": "npx",
      "args": ["@rushdb/mcp-server"],
      "env": {
        "RUSHDB_API_KEY": "your-api-key-here"
      }
    }
  }
}

Place this in:

  • Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json

  • Cursor — MCP settings in the Cursor config panel

  • Windsurf — ~/.codeium/windsurf/mcp_config.json

3. That's it. The agent now has 43 tools for storing, querying, searching and traversing structured memory.

RUSHDB_API_URL is optional and defaults to https://api.rushdb.com/api/v1, the RushDB Cloud API.

Local standalone engine (no Cloud account)

Run the Rust engine, then point a local stdio MCP client at it. This mode calls the public engine protocol directly; it does not use a RushDB Cloud API key, dashboard, or OAuth.

RUSHDB_TOKEN=local-development-token rushdb up --data-dir ./rushdb-data
{
  "mcpServers": {
    "rushdb": {
      "command": "npx",
      "args": ["-y", "@rushdb/mcp-server"],
      "env": {
        "RUSHDB_MODE": "direct",
        "RUSHDB_ENGINE_URL": "http://127.0.0.1:3000",
        "RUSHDB_ENGINE_TOKEN": "local-development-token"
      }
    }
  }
}

Direct mode offers every tool whose work the engine does: schema discovery, record reads and writes (with ordering, projections and aggregations), relationships, labels and properties, bulk import and CSV export, text indexes and keyword search, and external vector indexes with vector search by a queryVector you supply. The RushDB Cloud tools are not listed and are refused if called: smartSearch (natural-language search), the relationship-pattern tools, and anything that needs managed embeddings (a text query for vector search, managed indexes). The MCP HTTP transport is unavailable in direct mode because its OAuth flow belongs to RushDB Cloud; run the server through stdio on the same machine as the client.


Related MCP server: Personal Neo4j Memory Server

What an agent can do

After connecting, ask Claude or your agent naturally:

"Remember that we decided to use Clerk for auth, replacing Auth0, on 2026-04-10."

The agent calls createRecord to store a structured memory. Later:

"What auth decisions have we made?"

The agent calls getSchemaMarkdown to learn what is stored, then findRecords, textSearch or vectorSearch.

"Show me everything related to our auth system."

The agent calls findRelationships and findRecords with relationship filters to traverse the graph of connected records.


Available tools

43 tools, named exactly as below. In direct mode the six RushDB Cloud tools are not listed. The full reference, with inputs and safety levels, is at docs.rushdb.com/3.x/learn/reference/mcp/tools.

Discovery and properties

Tool

What it does

getSchemaMarkdown

The whole graph schema as compact Markdown; call once at session start

getSchema

Structured schema JSON, with property IDs and vector indexes

findLabels

List or filter record labels and their counts

findProperties

Property names, types, IDs and record counts

findPropertyById

Metadata for one property

propertyValues

Numeric or date ranges, or distinct string and boolean values

deleteProperty

Remove a property and its values from all records

getSearchQuerySpec

The complete SearchQuery syntax reference

getQueryBuilderPrompt

The built-in query builder prompt (for clients without MCP Prompts support)

Records

Tool

What it does

findRecords

Search records; ordering, projections, grouping and aggregations

findOneRecord

The first matching record

findUniqRecord

Exactly one matching record; fails on zero or several

getRecord

One record by ID

getRecordsByIds

Several records by ID

createRecord

Insert or upsert one record

updateRecord

Update some fields of a record

setRecord

Replace all fields of a record

deleteRecord / deleteRecordById

Delete one record by ID

bulkCreateRecords

Insert or upsert many records with one label

bulkDeleteRecords

Delete the records matching a query

exportRecords

Export matching records as CSV

Relationships

Tool

What it does

findRelationships

Find relationships by type, properties or endpoint records

attachRelation

Create relationships between existing records

detachRelation

Remove relationships: every type unless relationType is given, both ways unless direction is

Tool

What it does

findEmbeddingIndexes

List embedding indexes and their status

createEmbeddingIndex

Create an embedding index (on a self-hosted engine, an external one with dimensions)

getEmbeddingIndexStats

How many records an index covers and has vectors for

upsertEmbeddingVectors

Write your own vectors to an external index

deleteEmbeddingIndex

Delete an embedding index and its vectors

vectorSearch

Rank records by vector similarity after exact filtering; add text for hybrid search

semanticSearch

Deprecated alias for vectorSearch

listTextIndexes

List text indexes and their status

createTextIndex

Declare a BM25 text index over one property, or * for every string

deleteTextIndex

Drop a text index

textSearch

Keyword (BM25) search after exact filtering

RushDB Cloud only

Tool

What it does

smartSearch

Turn a natural-language request into a SearchQuery and run it

listRelationshipPatterns

List inferred relationship patterns and analysis status

analyzeRelationshipPatterns

Queue schema analysis for relationship suggestions

approveRelationshipPattern

Approve and apply a suggested pattern

ignoreRelationshipPattern

Ignore a suggested pattern

deleteRelationshipPattern

Delete a pattern and optionally its materialized relationships

Utilities

Tool

What it does

helpAddToClient

Setup instructions for your MCP client

Writes accept an optional transactionId.


Built-in query builder prompt

RushDB exposes a system prompt via the MCP Prompts API that teaches the agent to query safely — discover labels and properties first, then construct queries.

How it works:

  1. Client calls prompts/list → finds rushdb.queryBuilder

  2. Client calls prompts/get → injects it as the session system message

  3. Agent now does discovery-first queries automatically

Most MCP clients handle this at session start. If your client doesn't support MCP Prompts, call getQueryBuilderPrompt and inject the result as your system message.


Environment variables

These apply to local (API key) mode. Remote OAuth connections do not use environment variables.

Variable

Required

Description

RUSHDB_API_KEY

yes

Your RushDB API key

RUSHDB_API_URL

no

API base URL (default: https://api.rushdb.com/api/v1)

For standalone direct mode, use these instead:

Variable

Required

Description

RUSHDB_MODE

yes

Set to direct.

RUSHDB_ENGINE_URL

yes

Standalone engine base URL, for example http://127.0.0.1:3000.

RUSHDB_ENGINE_TOKEN

yes

Token configured for the standalone engine.

RUSHDB_ENGINE_SCOPE

no

Tenant on an engine started with --multitenant.


Registry & autodiscovery

  • mcp.yaml at the repo root enables autodiscovery by MCP registries

  • glama.json at the repo root contains Glama metadata

  • Package: @rushdb/mcp-server, command: npx


Development

git clone https://github.com/rush-db/mcp-server
cd mcp-server
npm install
npm run build

Troubleshooting: rushdb-mcp: command not found / MCP error -32000

This only happens when the MCP client launches the server with a working directory inside this repo (e.g. an .mcp.json at the repo root used by Claude Code / Cursor). This repo is @rushdb/mcp-server, so an unversioned npx @rushdb/mcp-server (even with -p) can resolve to the local package, whose rushdb-mcp bin isn't linked in node_modules/.bin. The process exits before the MCP handshake, which the client reports as -32000.

The published package is unaffected — the config above works as-is outside the repo. To run from inside the repo, pin a version so npx fetches from the registry instead of resolving the local package:

{
  "mcpServers": {
    "rushdb": {
      "command": "npx",
      "args": ["-y", "-p", "@rushdb/mcp-server@latest", "rushdb-mcp"],
      "env": { "RUSHDB_API_KEY": "your-api-key-here" }
    }
  }
}

Alternatively, run the local build directly (uses your in-repo code, must be built first with npm run build):

{
  "mcpServers": {
    "rushdb": {
      "command": "node",
      "args": ["build/index.js"],
      "env": { "RUSHDB_API_KEY": "your-api-key-here" }
    }
  }
}

License

Apache 2.0

Available Tools

29 tools
AttachRelationC

Create a relationship between records (single or multiple targets)

Inputs: sourceId (required), targetId, targetIds, relationType, +2 more.

BulkCreateRecordsC

Create multiple records in a single operation

Inputs: label (required), data (required), transactionId.

BulkDeleteRecordsC

Delete multiple records matching a query

Inputs: where (required), labels, transactionId.

CreateRecordC

Create a new record in the database

Inputs: label (required), data (required), transactionId.

DeletePropertyC

Delete a property from the database

Inputs: propertyId (required).

DeleteRecordC

Delete a record from the database (alias of DeleteRecordById)

Inputs: recordId (required), transactionId.

DeleteRecordByIdC

Delete a record by its ID

Inputs: recordId (required), transactionId.

DetachRelationB

Remove a relationship between records (single or multiple targets)

Inputs: sourceId (required), targetId, targetIds, relationType, +2 more.

ExportRecordsC

Export records to CSV format

Inputs: labels, where, limit, orderBy.

FindLabelsB

Find / filter record labels (supports where, limit, skip, orderBy). Superset of GetLabels.

Inputs: where, limit, skip, orderBy.

FindOneRecordC

Find a single record that matches the given search criteria

Inputs: labels, where.

FindPropertiesC

Find properties in the database using a search query

Inputs: where, limit, skip, orderBy.

FindPropertyByIdC

Find a specific property by ID

Inputs: propertyId (required).

FindRecordsC

Find records in the database using a search query

Inputs: labels, where, limit, skip, +3 more.

FindRelationshipsC

Find relationships in the database

Inputs: where, limit, skip, orderBy.

FindUniqRecordC

Find a unique record that matches the given search criteria

Inputs: labels, where.

GetQueryBuilderPromptA

Return the RushDB Query Builder system prompt. Use this if your MCP client does not support Prompts API.

Inputs: no named parameters.

GetRecordB

Get a specific record by ID

Inputs: recordId (required).

GetRecordsByIdsC

Get multiple records by their IDs

Inputs: recordIds (required).

GetSettingsB

Get the current database settings and configuration

Inputs: no named parameters.

HelpAddToClientA

Help the user add the RushDB MCP server to their MCP client

Inputs: no named parameters.

OpenBrowserC

Open a web browser to a specific URL

Inputs: url (required).

PropertyValuesC

Get values for a specific property

Inputs: propertyId (required), query, orderBy, limit, +1 more.

SetRecordC

Replace all fields of a record with provided values

Inputs: recordId (required), label (required), data (required), transactionId.

TransactionBeginB

Begin a new database transaction

Inputs: ttl.

TransactionCommitC

Commit a database transaction

Inputs: transactionId (required).

TransactionGetC

Get information about a transaction

Inputs: transactionId (required).

TransactionRollbackC

Rollback a database transaction

Inputs: transactionId (required).

UpdateRecordC

Update an existing record (partial update)

Inputs: recordId (required), label (required), data (required), transactionId.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 29 tools

    Disambiguation4/5

    Most tools have distinct purposes with clear boundaries, such as CreateRecord vs. UpdateRecord vs. DeleteRecord. However, there is some overlap between DeleteRecord and DeleteRecordById (described as aliases), and FindOneRecord vs. FindUniqRecord could be confusing without careful reading of descriptions, though the latter emphasizes uniqueness.

    Naming Consistency4/5

    Tool names follow a consistent verb_noun pattern (e.g., CreateRecord, DeleteRecord, FindRecords) with clear action-object pairs. Minor deviations include GetQueryBuilderPrompt and HelpAddToClient, which are more descriptive but still maintain readability without disrupting the overall pattern.

    Tool Count3/5

    With 29 tools, the count feels heavy for a database server, potentially overwhelming for agents. While it covers many operations, it could be streamlined by merging redundant tools like DeleteRecord and DeleteRecordById, or consolidating some find operations to reduce complexity.

    Completeness5/5

    The tool set provides comprehensive coverage for database operations, including CRUD (CreateRecord, GetRecord, UpdateRecord, DeleteRecord), bulk operations, relationships (AttachRelation, DetachRelation), transactions, and utilities like export and settings. No obvious gaps exist for core database workflows.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI assistants with persistent, graph-based memory using Neo4j, enabling semantic search and complex relationship tracking. It features specialized Cloudflare Access support for secure remote connections and isolated multi-database management for different projects.
      7 npm
      MIT
    • A
      license
      Not graded
      quality
      Not graded
      maintenance
      A lightning-fast, self-hosted knowledge store and memory layer for AI agents
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides persistent knowledge graph memory for AI agents, enabling them to store, recall, and query facts about people, projects, and relationships across sessions.
      MIT