Skip to main content
Glama
avarant

Typesense MCP Server

create_document

Add a new document to a specified collection in Typesense, ensuring it includes required fields like 'id' unless using auto-schema. Simplify document creation for structured data storage and retrieval.

Instructions

Creates a single new document in a specific collection.

Args:
    ctx (Context): The MCP context.
    collection_name (str): The name of the collection.
    document (dict): The document data to create (must include an 'id' field unless auto-schema).

Returns:
    dict | str: The created document dictionary or an error message string.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
collection_nameYes
documentYes

Implementation Reference

  • main.py:574-611 (handler)
    Handler function for the 'create_document' tool. It creates a new document in a Typesense collection using the provided client from the context. Includes error handling for common Typesense exceptions.
    @mcp.tool()
    async def create_document(ctx: Context, collection_name: str, document: dict) -> dict | str:
        """
        Creates a single new document in a specific collection.
    
        Args:
            ctx (Context): The MCP context.
            collection_name (str): The name of the collection.
            document (dict): The document data to create (must include an 'id' field unless auto-schema).
    
        Returns:
            dict | str: The created document dictionary or an error message string.
        """
        if not collection_name:
            return "Error: collection_name parameter is required."
        if not isinstance(document, dict):
            return "Error: document parameter must be a dictionary."
        # Consider adding check for 'id' field if not using auto-id generation
    
        try:
            print(f"Creating document in collection '{collection_name}' with ID: {document.get('id', 'N/A')}")
            client: typesense.Client = ctx.request_context.lifespan_context.client
            # NOTE: Assuming create is *sync* based on observed pattern
            created_doc = client.collections[collection_name].documents.create(document)
            return created_doc
        except typesense.exceptions.ObjectNotFound:
            return f"Error: Collection '{collection_name}' not found."
        except typesense.exceptions.ObjectAlreadyExists as e:
             # Occurs if document ID already exists
             return f"Error: Document with ID '{document.get('id', 'N/A')}' already exists in collection '{collection_name}'. Use upsert to update. Details: {e}"
        except typesense.exceptions.RequestMalformed as e:
             return f"Error: Malformed create document request for collection '{collection_name}'. Check document structure against schema. Details: {e}"
        except typesense.exceptions.TypesenseClientError as e:
            print(f"Error creating document in '{collection_name}': {e}")
            return f"Error creating document in '{collection_name}': {e}"
        except Exception as e:
            print(f"An unexpected error occurred while creating document in '{collection_name}': {e}")
            return f"An unexpected error occurred: {e}"
  • main.py:574-574 (registration)
    The @mcp.tool() decorator registers the create_document function as an MCP tool.
    @mcp.tool()
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a document and mentions an 'id' field requirement, but fails to cover critical aspects like permissions needed, error handling, whether it's idempotent, or mutation effects. This leaves significant gaps for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence, followed by structured parameter and return details. It avoids unnecessary fluff, but the Args/Returns formatting could be more integrated into natural language, slightly affecting flow.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a mutation tool with no annotations, no output schema, and 0% schema coverage, the description is incomplete. It lacks details on error cases, return value structure beyond 'dict | str', and behavioral traits like idempotency or side effects, making it inadequate for safe agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains that 'collection_name' specifies the target collection and 'document' includes data with an 'id' field requirement, adding some semantic context beyond the bare schema. However, it doesn't detail format constraints or examples, keeping it at a baseline level.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('creates') and resource ('single new document in a specific collection'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like 'index_multiple_documents' or 'upsert_document', which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'upsert_document' or 'index_multiple_documents'. The description mentions the tool's function but lacks context about prerequisites, constraints, or comparisons with siblings, leaving the agent without usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

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/avarant/typesense-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server