18342272475

Committed 08 Oct 2025 10:52AM UTC coverage: 82.531% (+0.03%) from 82.505%

Build # 18342272475

Build Type

Pull #621

github

Committed by

web-flow

Commit Message

Merge 33ba4d126 into 543301c2d

Pull Request Pull Request #621: feat: add ability to create vector search indexes MCP-234

Run Details

1101 of 1447 branches covered (76.09%)

Branch coverage included in aggregate %.

63 of 73 new or added lines in 1 file covered. (86.3%)

37 existing lines in 2 files now uncovered.

5362 of 6384 relevant lines covered (83.99%)

67.49 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

89.42

/src/tools/mongodb/create/createIndex.ts

import { z } from "zod";
import type { CallToolResult } from "@modelcontextprotocol/sdk/types.js";
import { DbOperationArgs, MongoDBToolBase } from "../mongodbTool.js";
import type { ToolArgs, OperationType } from "../../tool.js";
import type { IndexDirection } from "mongodb";

export class CreateIndexTool extends MongoDBToolBase {
    public name = "create-index";
    protected description = "Create an index for a collection";
    protected argsShape = {
        ...DbOperationArgs,
        name: z.string().optional().describe("The name of the index"),
        definition: z
            .discriminatedUnion("type", [
                z.object({
                    type: z.literal("classic"),
                    keys: z.object({}).catchall(z.custom<IndexDirection>()).describe("The index definition"),
                }),
                z.object({
                    type: z.literal("vectorSearch"),
                    fields: z
                        .array(
                            z.object({
                                type: z
                                    .enum(["vector", "filter"])
                                    .describe(
                                        "Field type to use to index fields for vector search. You must specify `vector` for fields that contain vector embeddings and `filter` for additional fields to filter on."
                                    ),
                                path: z
                                    .string()
                                    .describe(
                                        "Name of the field to index. For nested fields, use dot notation to specify path to embedded fields"
                                    ),
                                numDimensions: z
                                    .number()
                                    .min(1)
                                    .max(8192)
                                    .describe(
                                        "Number of vector dimensions that MongoDB Vector Search enforces at index-time and query-time"
                                    ),
                                similarity: z
                                    .enum(["cosine", "euclidean", "dotProduct"])
                                    .describe(
                                        "Vector similarity function to use to search for top K-nearest neighbors. You can set this field only for vector-type fields."
                                    ),
                                quantization: z
                                    .enum(["none", "scalar", "binary"])
                                    .optional()
                                    .default("none")
                                    .describe(
                                        "Type of automatic vector quantization for your vectors. Use this setting only if your embeddings are float or double vectors."
                                    ),
                            })
                        )
                        .describe(
                            "Definitions for the vector and filter fields to index, one definition per document. The fields array must contain at least one vector-type field definition."
                        ),
                }),
            ])
            .describe(
                "The index definition. Use 'classic' for standard indexes and 'vectorSearch' for vector search indexes"
            ),
    };

    public operationType: OperationType = "create";

    protected async execute({
        database,
        collection,
        name,
        definition,
    }: ToolArgs<typeof this.argsShape>): Promise<CallToolResult> {
        const provider = await this.ensureConnected();
        let indexes: string[] = [];
        switch (definition.type) {
            case "classic":
                indexes = await provider.createIndexes(database, collection, [
                    {
                        key: definition.keys,
                        name,
                    },
                ]);

                break;
            case "vectorSearch":
                indexes = await provider.createSearchIndexes(database, collection, [
                    {
                        name,
                        definition: {
                            fields: definition.fields,
                        },
                        type: "vectorSearch",
                    },
                ]);
                break;
        }

        return {
            content: [
                {
                    text: `Created the index "${indexes[0]}" on collection "${collection}" in database "${database}"`,
                    type: "text",
                },
            ],
        };
    }
}

1	import { z } from "zod";	2✔
2	import type { CallToolResult } from "@modelcontextprotocol/sdk/types.js";
3	import { DbOperationArgs, MongoDBToolBase } from "../mongodbTool.js";	2✔
4	import type { ToolArgs, OperationType } from "../../tool.js";
5	import type { IndexDirection } from "mongodb";
6
7	export class CreateIndexTool extends MongoDBToolBase {	2✔
8	public name = "create-index";	77✔
9	protected description = "Create an index for a collection";	77✔
10	protected argsShape = {	77✔
11	...DbOperationArgs,	77✔
12	name: z.string().optional().describe("The name of the index"),	77✔
13	definition: z	77✔
14	.discriminatedUnion("type", [	77✔
15	z.object({	77✔
16	type: z.literal("classic"),	77✔
17	keys: z.object({}).catchall(z.custom<IndexDirection>()).describe("The index definition"),	77✔
18	}),	77✔
19	z.object({	77✔
20	type: z.literal("vectorSearch"),	77✔
21	fields: z	77✔
22	.array(	77✔
23	z.object({	77✔
24	type: z	77✔
25	.enum(["vector", "filter"])	77✔
26	.describe(	77✔
27	"Field type to use to index fields for vector search. You must specify `vector` for fields that contain vector embeddings and `filter` for additional fields to filter on."	77✔
28	),	77✔
29	path: z	77✔
30	.string()	77✔
31	.describe(	77✔
32	"Name of the field to index. For nested fields, use dot notation to specify path to embedded fields"	77✔
33	),	77✔
34	numDimensions: z	77✔
35	.number()	77✔
36	.min(1)	77✔
37	.max(8192)	77✔
38	.describe(	77✔
39	"Number of vector dimensions that MongoDB Vector Search enforces at index-time and query-time"	77✔
40	),	77✔
41	similarity: z	77✔
42	.enum(["cosine", "euclidean", "dotProduct"])	77✔
43	.describe(	77✔
44	"Vector similarity function to use to search for top K-nearest neighbors. You can set this field only for vector-type fields."	77✔
45	),	77✔
46	quantization: z	77✔
47	.enum(["none", "scalar", "binary"])	77✔
48	.optional()	77✔
49	.default("none")	77✔
50	.describe(	77✔
51	"Type of automatic vector quantization for your vectors. Use this setting only if your embeddings are float or double vectors."	77✔
52	),	77✔
53	})	77✔
54	)	77✔
55	.describe(	77✔
56	"Definitions for the vector and filter fields to index, one definition per document. The fields array must contain at least one vector-type field definition."	77✔
57	),	77✔
58	}),	77✔
59	])	77✔
60	.describe(	77✔
61	"The index definition. Use 'classic' for standard indexes and 'vectorSearch' for vector search indexes"	77✔
62	),	77✔
63	};	77✔
64
65	public operationType: OperationType = "create";	77✔
66
67	protected async execute({	2✔
68	database,	16✔
69	collection,	16✔
70	name,	16✔
71	definition,	16✔
72	}: ToolArgs<typeof this.argsShape>): Promise<CallToolResult> {	16✔
73	const provider = await this.ensureConnected();	16✔
74	let indexes: string[] = [];	15✔
75	switch (definition.type) {	15✔
76	case "classic":	15✔
77	indexes = await provider.createIndexes(database, collection, [	15✔
78	{	15✔
79	key: definition.keys,	15✔
80	name,	15✔
81	},	15✔
82	]);	15✔
83
84	break;	15✔
85	case "vectorSearch":	16!
NEW 86	indexes = await provider.createSearchIndexes(database, collection, [	×
NEW 87	{	×
NEW 88	name,	×
NEW 89	definition: {	×
NEW 90	fields: definition.fields,	×
NEW 91	},	×
NEW 92	type: "vectorSearch",	×
NEW 93	},	×
NEW 94	]);	×
NEW 95	break;	×
96	}	16✔
97
98	return {	15✔
99	content: [	15✔
100	{	15✔
101	text: `Created the index "${indexes[0]}" on collection "${collection}" in database "${database}"`,	15✔
102	type: "text",	15✔
103	},	15✔
104	],	15✔
105	};	15✔
106	}	16✔
107	}	2✔

mongodb-js / mongodb-mcp-server / 18342272475

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous