surreal-mcp

Execute one or more SurrealQL queries against the connected SurrealDB database.

This tool allows you to run any valid SurrealQL queries directly. Use this for complex queries that don't fit the other tool patterns, such as:

• Complex SELECT queries with JOINs, GROUP BY, or aggregations

• Custom DEFINE statements for schemas

• Transaction blocks with BEGIN/COMMIT

• Graph traversal queries

Queries are executed sequentially. If a query fails, execution continues with the remaining queries, and the error is captured in that query's result.

Args: queries: A list of SurrealQL queries to execute. Examples: - ["SELECT * FROM user WHERE age > 18"] - ["SELECT * FROM user", "SELECT * FROM product"] - ["CREATE user:alice SET name = 'Alice'", "CREATE user:bob SET name = 'Bob'"] namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if at least one query executed successfully - results: Array of per-query results, each containing: - success: Boolean indicating if this specific query succeeded - data: The query results (only present on success) - error: Error message (only present on failure) - total: Total number of queries executed - succeeded: Number of queries that succeeded - failed: Number of queries that failed

Example: >>> await query(["SELECT * FROM user", "SELECT * FROM product"]) { "success": true, "results": [ {"success": true, "data": [{"id": "user:1", "name": "Alice"}]}, {"success": true, "data": [{"id": "product:1", "name": "Laptop"}]} ], "total": 2, "succeeded": 2, "failed": 0 }

Select all records from a table or a specific record by ID.

This tool provides a simple way to retrieve data from SurrealDB tables. Use this when you need to:

• Fetch all records from a table

• Retrieve a specific record by its ID

• Get data for display or further processing

Args: table: The name of the table to select from (e.g., "user", "product", "order") id: Optional ID of a specific record to select. Can be: - Just the ID part (e.g., "john") - will be combined with table name - Full record ID (e.g., "user:john") - will be used as-is - None/omitted - selects all records from the table namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if the selection was successful - data: Array of records (even for single record selection) - count: Number of records returned - error: Error message if selection failed (only present on failure)

Examples: >>> await select("user") # Get all users {"success": true, "data": [...], "count": 42}

Create a new record in a SurrealDB table with the specified data.

This tool creates a new record with an auto-generated ID. The system will automatically:

• Generate a unique ID for the record

• Add created/updated timestamps

• Validate the data against any defined schema

Args: table: The name of the table to create the record in (e.g., "user", "product") data: A dictionary containing the field values for the new record. Examples: - {"name": "Alice", "email": "alice@example.com", "age": 30} - {"title": "Laptop", "price": 999.99, "category": "electronics"} namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if creation was successful - data: The created record including its generated ID and timestamps - id: The ID of the newly created record (convenience field) - error: Error message if creation failed (only present on failure)

Examples: >>> await create("user", {"name": "Alice", "email": "alice@example.com"}) { "success": true, "data": {"id": "user:ulid", "name": "Alice", "email": "alice@example.com", "created": "2024-01-01T10:00:00Z"}, "id": "user:ulid" }

Note: If you need to specify a custom ID, use the 'upsert' tool instead.

Update a specific record with new data, completely replacing its content.

This tool performs a full update, replacing all fields (except ID and timestamps) with the provided data. For partial updates that only modify specific fields, use 'merge' or 'patch' instead.

Args: thing: The full record ID to update in format "table:id" (e.g., "user:john", "product:laptop-123") data: Complete new data for the record. All existing fields will be replaced except: - The record ID (cannot be changed) - The 'created' timestamp (preserved from original) - The 'updated' timestamp (automatically set to current time) namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if update was successful - data: The updated record with all new values - error: Error message if update failed (only present on failure)

Examples: >>> await update("user:john", {"name": "John Smith", "email": "john.smith@example.com", "age": 31}) { "success": true, "data": {"id": "user:john", "name": "John Smith", "email": "john.smith@example.com", "age": 31, "updated": "2024-01-01T10:00:00Z"} }

Warning: This replaces ALL fields. If you only want to update specific fields, use 'merge' instead.

Delete a specific record from the database by its ID.

This tool permanently removes a record from the database. Use with caution as this operation cannot be undone. The deletion will also:

• Remove any graph edges (relations) connected to this record

• Trigger any defined deletion events/hooks

• Fail if the record is referenced by FOREIGN KEY constraints

Args: thing: The full record ID to delete in format "table:id" (e.g., "user:john", "product:laptop-123") namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if deletion was successful - deleted: The ID of the deleted record - data: The deleted record data (if available) - error: Error message if deletion failed (only present on failure)

Examples: >>> await delete("user:john") {"success": true, "deleted": "user:john", "data": {"id": "user:john", "name": "John Doe"}}

Note: This operation is irreversible. Consider using soft deletes (status fields) for recoverable deletions.

Merge data into a specific record, updating only the specified fields.

This tool performs a partial update, only modifying the fields provided in the data parameter. All other fields remain unchanged. This is useful when you want to:

• Update specific fields without affecting others

• Add new fields to an existing record

• Modify nested properties without replacing the entire object

Args: thing: The full record ID to merge data into in format "table:id" (e.g., "user:john") data: Dictionary containing only the fields to update. Examples: - {"email": "newemail@example.com"} - updates only email - {"profile": {"bio": "New bio"}} - updates nested field - {"tags": ["python", "mcp"]} - replaces the tags array namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if merge was successful - data: The complete record after merging, with all fields - modified_fields: List of field names that were modified - error: Error message if merge failed (only present on failure)

Examples: >>> await merge("user:john", {"email": "john.new@example.com", "verified": true}) { "success": true, "data": {"id": "user:john", "name": "John Doe", "email": "john.new@example.com", "verified": true, "age": 30}, "modified_fields": ["email", "verified"] }

Note: This is equivalent to the 'patch' tool but uses object merging syntax instead of JSON Patch.

Apply JSON Patch operations to a specific record (RFC 6902).

This tool applies a sequence of patch operations to modify a record. However, since SurrealDB doesn't natively support JSON Patch, this implementation converts patches to a merge operation. Supported operations:

• add: Add a new field or array element

• remove: Remove a field (limited support)

• replace: Replace a field value

Args: thing: The full record ID to patch in format "table:id" (e.g., "user:john") patches: Array of patch operations. Each operation should have: - op: The operation type ("add", "remove", "replace", "move", "copy", "test") - path: The field path (e.g., "/email", "/profile/bio") - value: The value for add/replace operations namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if patch was successful - data: The complete record after applying patches - applied_patches: Number of patch operations applied - error: Error message if patch failed (only present on failure)

Examples: >>> await patch("user:john", [ ... {"op": "replace", "path": "/email", "value": "john@newdomain.com"}, ... {"op": "add", "path": "/verified", "value": true} ... ]) { "success": true, "data": {"id": "user:john", "email": "john@newdomain.com", "verified": true, ...}, "applied_patches": 2 }

Note: This provides compatibility with JSON Patch but internally uses SurrealDB's merge. Complex operations like "move" or "test" are not fully supported.

Upsert a record: create if it doesn't exist, merge/update if it does.

This tool is perfect when you want to ensure a record exists with specific data, regardless of whether it already exists. It will:

• Create a new record with the specified ID if it doesn't exist

• Merge the provided data into the existing record if it does exist

• Always succeed (unless there's a database error)

Args: thing: The full record ID in format "table:id" (e.g., "user:john", "settings:global") data: The data for the record. If record exists, this will be merged with existing data namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if upsert was successful - data: The record after upserting - created: Boolean indicating if a new record was created (vs updated) - error: Error message if upsert failed (only present on failure)

Examples: >>> await upsert("user:john", {"name": "John Doe", "email": "john@example.com"}) {"success": true, "data": {"id": "user:john", "name": "John Doe", ...}, "created": true}

Insert multiple records into a table in a single operation.

This tool is optimized for bulk inserts when you need to create many records at once. It's more efficient than calling 'create' multiple times. Each record will get:

• An auto-generated unique ID

• Automatic created/updated timestamps

• Schema validation (if defined)

Args: table: The name of the table to insert records into (e.g., "user", "product") data: Array of dictionaries, each representing a record to insert. Example: [ {"name": "Alice", "email": "alice@example.com"}, {"name": "Bob", "email": "bob@example.com"}, {"name": "Charlie", "email": "charlie@example.com"} ] namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if insertion was successful - data: Array of all inserted records with their generated IDs - count: Number of records successfully inserted - error: Error message if insertion failed (only present on failure)

Examples: >>> await insert("user", [ ... {"name": "Alice", "role": "admin"}, ... {"name": "Bob", "role": "user"} ... ]) { "success": true, "data": [ {"id": "user:ulid1", "name": "Alice", "role": "admin", "created": "..."}, {"id": "user:ulid2", "name": "Bob", "role": "user", "created": "..."} ], "count": 2 }

Note: For single record creation, use the 'create' tool instead.

Create a graph relation (edge) between two records in SurrealDB.

This tool creates relationships in SurrealDB's graph structure, allowing you to:

• Connect records with named relationships

• Store data on the relationship itself

• Build complex graph queries later

• Model many-to-many relationships efficiently

Args: from_thing: The source record ID in format "table:id" (e.g., "user:john") relation_name: The name of the relation/edge table (e.g., "likes", "follows", "purchased") to_thing: The destination record ID in format "table:id" (e.g., "product:laptop-123") data: Optional dictionary containing data to store on the relation itself. Examples: - {"rating": 5, "review": "Great product!"} - {"quantity": 2, "price": 99.99} - {"since": "2024-01-01", "type": "friend"} namespace: Optional SurrealDB namespace override. If not provided, uses SURREAL_NAMESPACE env var. database: Optional SurrealDB database override. If not provided, uses SURREAL_DATABASE env var.

Returns: A dictionary containing: - success: Boolean indicating if relation was created successfully - data: The created relation record(s) - relation_id: The ID of the created relation - error: Error message if creation failed (only present on failure)

Examples: >>> await relate("user:john", "likes", "product:laptop-123", {"rating": 5}) { "success": true, "data": [{"id": "likes:xyz", "in": "user:john", "out": "product:laptop-123", "rating": 5}], "relation_id": "likes:xyz" }

Note: You can query these relations later using graph syntax: SELECT * FROM user:john->likes->product SELECT * FROM user:alice->follows->user