Skip to main content
Glama
Octodet

octodet-elasticsearch-mcp

add_document

Insert or update documents into a specified Elasticsearch index, enabling structured data storage and retrieval for efficient search operations.

Instructions

Add a new document to a specific Elasticsearch index

Input Schema

NameRequiredDescriptionDefault
documentYesDocument body to index
idNoOptional document ID (if not provided, Elasticsearch will generate one)
indexYesName of the Elasticsearch index

Input Schema (JSON Schema)

{ "$schema": "http://json-schema.org/draft-07/schema#", "additionalProperties": false, "properties": { "document": { "additionalProperties": {}, "description": "Document body to index", "type": "object" }, "id": { "description": "Optional document ID (if not provided, Elasticsearch will generate one)", "type": "string" }, "index": { "description": "Name of the Elasticsearch index", "minLength": 1, "type": "string" } }, "required": [ "index", "document" ], "type": "object" }

Implementation Reference

  • The handler function for the 'add_document' MCP tool. It calls the Elasticsearch service to add the document and returns a formatted response or error message.
    async ({ index, id, document }) => { try { const response = await esService.addDocument(index, document, id); return { content: [ { type: "text", text: `Document added to index '${index}' with ID: ${response._id}`, }, ], }; } catch (error) { return { content: [ { type: "text", text: `Error adding document: ${ error instanceof Error ? error.message : String(error) }`, }, ], }; } }
  • Zod input schema defining parameters for the add_document tool: required index name, optional id, and document body.
    { index: z .string() .trim() .min(1, "Index name is required") .describe("Name of the Elasticsearch index"), id: z .string() .optional() .describe( "Optional document ID (if not provided, Elasticsearch will generate one)" ), document: z.record(z.any()).describe("Document body to index"), },
  • src/index.ts:416-457 (registration)
    Registration of the 'add_document' tool on the MCP server using server.tool, specifying name, description, input schema, and handler.
    server.tool( "add_document", "Add a new document to a specific Elasticsearch index", { index: z .string() .trim() .min(1, "Index name is required") .describe("Name of the Elasticsearch index"), id: z .string() .optional() .describe( "Optional document ID (if not provided, Elasticsearch will generate one)" ), document: z.record(z.any()).describe("Document body to index"), }, async ({ index, id, document }) => { try { const response = await esService.addDocument(index, document, id); return { content: [ { type: "text", text: `Document added to index '${index}' with ID: ${response._id}`, }, ], }; } catch (error) { return { content: [ { type: "text", text: `Error adding document: ${ error instanceof Error ? error.message : String(error) }`, }, ], }; } } );
  • Supporting helper method in ElasticsearchService class that performs the core Elasticsearch client.index operation to add the document.
    async addDocument(index: string, document: any, id?: string): Promise<any> { const params: any = { index, document }; if (id) params.id = id; return await this.client.index(params); }

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/Octodet/elasticsearch-mcp'

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