19925638108

Committed 04 Dec 2025 10:23AM UTC coverage: 80.575% (-0.03%) from 80.607%

Build # 19925638108

Build Type

Pull #779

github

Committed by

web-flow

Commit Message

Merge 1e90969c7 into e12068a03

Pull Request Pull Request #779: chore: bump mcp SDK, refactor tool arguments

Run Details

1469 of 1905 branches covered (77.11%)

Branch coverage included in aggregate %.

49 of 66 new or added lines in 12 files covered. (74.24%)

2 existing lines in 2 files now uncovered.

6736 of 8278 relevant lines covered (81.37%)

78.78 hits per line

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

60.4

/src/tools/mongodb/create/insertMany.ts

import { z } from "zod";
import type { CallToolResult } from "@modelcontextprotocol/sdk/types.js";
import { DbOperationArgs, MongoDBToolBase } from "../mongodbTool.js";
import { type ToolArgs, type OperationType, formatUntrustedData } from "../../tool.js";
import { zEJSON } from "../../args.js";
import { type Document } from "bson";
import { zSupportedEmbeddingParameters } from "../mongodbSchemas.js";
import { ErrorCodes, MongoDBError } from "../../../common/errors.js";

const zSupportedEmbeddingParametersWithInput = zSupportedEmbeddingParameters.extend({
    input: z
        .array(z.object({}).passthrough())
        .describe(
            "Array of objects with vector search index fields as keys (in dot notation) and the raw text values to generate embeddings for as values. The index of each object corresponds to the index of the document in the documents array."
        ),
});

const commonArgs = {
    ...DbOperationArgs,
    documents: z
        .array(zEJSON().describe("An individual MongoDB document"))
        .describe(
            "The array of documents to insert, matching the syntax of the document argument of db.collection.insertMany()."
        ),
} as const;

export class InsertManyTool extends MongoDBToolBase {
    public name = "insert-many";
    protected description = "Insert an array of documents into a MongoDB collection";
    protected argsShape = this.isFeatureEnabled("search")
        ? {
              ...commonArgs,
              embeddingParameters: zSupportedEmbeddingParametersWithInput
                  .optional()
                  .describe(
                      "The embedding model and its parameters to use to generate embeddings for fields with vector search indexes. Note to LLM: If unsure which embedding model to use, ask the user before providing one."
                  ),
          }
        : commonArgs;
    static operationType: OperationType = "create";

    protected async execute({
        database,
        collection,
        documents,
        ...conditionalArgs
    }: ToolArgs<typeof this.argsShape>): Promise<CallToolResult> {
        const provider = await this.ensureConnected();

        let embeddingParameters: z.infer<typeof zSupportedEmbeddingParametersWithInput> | undefined;
        if ("embeddingParameters" in conditionalArgs) {
            embeddingParameters = conditionalArgs.embeddingParameters;
        }

        // Process documents to replace raw string values with generated embeddings
        documents = await this.replaceRawValuesWithEmbeddingsIfNecessary({
            database,
            collection,
            documents,
            embeddingParameters,
        });

        await this.session.vectorSearchEmbeddingsManager.assertFieldsHaveCorrectEmbeddings(
            { database, collection },
            documents
        );

        const result = await provider.insertMany(database, collection, documents);
        const content = formatUntrustedData(
            "Documents were inserted successfully.",
            `Inserted \`${result.insertedCount}\` document(s) into ${database}.${collection}.`,
            `Inserted IDs: ${Object.values(result.insertedIds).join(", ")}`
        );
        return {
            content,
        };
    }

    private async replaceRawValuesWithEmbeddingsIfNecessary({
        database,
        collection,
        documents,
        embeddingParameters,
    }: {
        database: string;
        collection: string;
        documents: Document[];
        embeddingParameters?: z.infer<typeof zSupportedEmbeddingParametersWithInput>;
    }): Promise<Document[]> {
        // If no embedding parameters or no input specified, return documents as-is
        if (!embeddingParameters?.input || embeddingParameters.input.length === 0) {
            return documents;
        }

        // Get vector search indexes for the collection
        const vectorIndexes = await this.session.vectorSearchEmbeddingsManager.embeddingsForNamespace({
            database,
            collection,
        });

        // Ensure for inputted fields, the vector search index exists.
        for (const input of embeddingParameters.input) {
            for (const fieldPath of Object.keys(input)) {
                if (!vectorIndexes.some((index) => index.path === fieldPath)) {
                    throw new MongoDBError(
                        ErrorCodes.AtlasVectorSearchInvalidQuery,
                        `Field '${fieldPath}' does not have a vector search index in collection ${database}.${collection}. Only fields with vector search indexes can have embeddings generated.`
                    );
                }
            }
        }

        // We make one call to generate embeddings for all documents at once to avoid making too many API calls.
        const flattenedEmbeddingsInput = embeddingParameters.input.flatMap((documentInput, index) =>
            Object.entries(documentInput).map(([fieldPath, rawTextValue]) => ({
                fieldPath,
                rawTextValue,
                documentIndex: index,
            }))
        );

        const generatedEmbeddings = await this.session.vectorSearchEmbeddingsManager.generateEmbeddings({
            rawValues: flattenedEmbeddingsInput.map(({ rawTextValue }) => rawTextValue) as string[],
            embeddingParameters,
            inputType: "document",
        });

        const processedDocuments: Document[] = [...documents];

        for (const [index, { fieldPath, documentIndex }] of flattenedEmbeddingsInput.entries()) {
            if (!processedDocuments[documentIndex]) {
                throw new MongoDBError(ErrorCodes.Unexpected, `Document at index ${documentIndex} does not exist.`);
            }
            // Ensure no nested fields are present in the field path.
            this.deleteFieldPath(processedDocuments[documentIndex], fieldPath);
            processedDocuments[documentIndex][fieldPath] = generatedEmbeddings[index];
        }

        return processedDocuments;
    }

    // Delete a specified field path from a document using dot notation.
    private deleteFieldPath(document: Record<string, unknown>, fieldPath: string): void {
        const parts = fieldPath.split(".");
        let current: Record<string, unknown> = document;
        for (let i = 0; i < parts.length; i++) {
            const part = parts[i];
            const key = part as keyof typeof current;
            if (!current[key]) {
                return;
            } else if (i === parts.length - 1) {
                delete current[key];
            } else {
                current = current[key] as Record<string, unknown>;
            }
        }
    }
}

1	import { z } from "zod";	3✔
2	import type { CallToolResult } from "@modelcontextprotocol/sdk/types.js";
3	import { DbOperationArgs, MongoDBToolBase } from "../mongodbTool.js";	3✔
4	import { type ToolArgs, type OperationType, formatUntrustedData } from "../../tool.js";	3✔
5	import { zEJSON } from "../../args.js";	3✔
6	import { type Document } from "bson";
7	import { zSupportedEmbeddingParameters } from "../mongodbSchemas.js";	3✔
8	import { ErrorCodes, MongoDBError } from "../../../common/errors.js";	3✔
9
10	const zSupportedEmbeddingParametersWithInput = zSupportedEmbeddingParameters.extend({	3✔
11	input: z	3✔
12	.array(z.object({}).passthrough())	3✔
13	.describe(	3✔
14	"Array of objects with vector search index fields as keys (in dot notation) and the raw text values to generate embeddings for as values. The index of each object corresponds to the index of the document in the documents array."	3✔
15	),	3✔
16	});	3✔
17
18	const commonArgs = {	3✔
19	...DbOperationArgs,	3✔
20	documents: z	3✔
21	.array(zEJSON().describe("An individual MongoDB document"))	3✔
22	.describe(	3✔
23	"The array of documents to insert, matching the syntax of the document argument of db.collection.insertMany()."	3✔
24	),	3✔
25	} as const;	3✔
26
27	export class InsertManyTool extends MongoDBToolBase {	3✔
28	public name = "insert-many";	118✔
29	protected description = "Insert an array of documents into a MongoDB collection";	118✔
30	protected argsShape = this.isFeatureEnabled("search")	118✔
31	? {	15✔
32	...commonArgs,	15✔
33	embeddingParameters: zSupportedEmbeddingParametersWithInput	15✔
34	.optional()	15✔
35	.describe(	15✔
36	"The embedding model and its parameters to use to generate embeddings for fields with vector search indexes. Note to LLM: If unsure which embedding model to use, ask the user before providing one."	15✔
37	),	15✔
38	}	15✔
39	: commonArgs;	103✔
40	static operationType: OperationType = "create";	3✔
41
42	protected async execute({	3✔
43	database,	7✔
44	collection,	7✔
45	documents,	7✔
46	...conditionalArgs	7✔
47	}: ToolArgs<typeof this.argsShape>): Promise<CallToolResult> {	7✔
48	const provider = await this.ensureConnected();	7✔
49
50	let embeddingParameters: z.infer<typeof zSupportedEmbeddingParametersWithInput> \| undefined;	6✔
51	if ("embeddingParameters" in conditionalArgs) {	7!
NEW 52	embeddingParameters = conditionalArgs.embeddingParameters;	×
NEW 53	}	✔
54
55	// Process documents to replace raw string values with generated embeddings
56	documents = await this.replaceRawValuesWithEmbeddingsIfNecessary({	6✔
57	database,	6✔
58	collection,	6✔
59	documents,	6✔
60	embeddingParameters,	6✔
61	});	6✔
62
63	await this.session.vectorSearchEmbeddingsManager.assertFieldsHaveCorrectEmbeddings(	6✔
64	{ database, collection },	6✔
65	documents	6✔
66	);	6✔
67
68	const result = await provider.insertMany(database, collection, documents);	5✔
69	const content = formatUntrustedData(	4✔
70	"Documents were inserted successfully.",	4✔
71	`Inserted \`${result.insertedCount}\` document(s) into ${database}.${collection}.`,	4✔
72	`Inserted IDs: ${Object.values(result.insertedIds).join(", ")}`	4✔
73	);	4✔
74	return {	4✔
75	content,	4✔
76	};	4✔
77	}	7✔
78
79	private async replaceRawValuesWithEmbeddingsIfNecessary({	3✔
80	database,	6✔
81	collection,	6✔
82	documents,	6✔
83	embeddingParameters,	6✔
84	}: {	6✔
85	database: string;
86	collection: string;
87	documents: Document[];
88	embeddingParameters?: z.infer<typeof zSupportedEmbeddingParametersWithInput>;
89	}): Promise<Document[]> {	6✔
90	// If no embedding parameters or no input specified, return documents as-is
91	if (!embeddingParameters?.input \|\| embeddingParameters.input.length === 0) {	6!
92	return documents;	6✔
93	}	6!
94
95	// Get vector search indexes for the collection
96	const vectorIndexes = await this.session.vectorSearchEmbeddingsManager.embeddingsForNamespace({	×
97	database,	×
98	collection,	×
99	});	×
100
101	// Ensure for inputted fields, the vector search index exists.
102	for (const input of embeddingParameters.input) {	×
103	for (const fieldPath of Object.keys(input)) {	×
104	if (!vectorIndexes.some((index) => index.path === fieldPath)) {	×
105	throw new MongoDBError(	×
106	ErrorCodes.AtlasVectorSearchInvalidQuery,	×
107	`Field '${fieldPath}' does not have a vector search index in collection ${database}.${collection}. Only fields with vector search indexes can have embeddings generated.`	×
108	);	×
109	}	×
110	}	×
111	}	×
112
113	// We make one call to generate embeddings for all documents at once to avoid making too many API calls.
114	const flattenedEmbeddingsInput = embeddingParameters.input.flatMap((documentInput, index) =>	×
115	Object.entries(documentInput).map(([fieldPath, rawTextValue]) => ({	×
116	fieldPath,	×
117	rawTextValue,	×
118	documentIndex: index,	×
119	}))	×
120	);	×
121
122	const generatedEmbeddings = await this.session.vectorSearchEmbeddingsManager.generateEmbeddings({	×
123	rawValues: flattenedEmbeddingsInput.map(({ rawTextValue }) => rawTextValue) as string[],	×
124	embeddingParameters,	×
125	inputType: "document",	×
126	});	×
127
128	const processedDocuments: Document[] = [...documents];	×
129
130	for (const [index, { fieldPath, documentIndex }] of flattenedEmbeddingsInput.entries()) {	×
131	if (!processedDocuments[documentIndex]) {	×
132	throw new MongoDBError(ErrorCodes.Unexpected, `Document at index ${documentIndex} does not exist.`);	×
133	}	×
134	// Ensure no nested fields are present in the field path.
135	this.deleteFieldPath(processedDocuments[documentIndex], fieldPath);	×
136	processedDocuments[documentIndex][fieldPath] = generatedEmbeddings[index];	×
137	}	×
138
139	return processedDocuments;	×
140	}	6✔
141
142	// Delete a specified field path from a document using dot notation.
143	private deleteFieldPath(document: Record<string, unknown>, fieldPath: string): void {	3✔
144	const parts = fieldPath.split(".");	×
145	let current: Record<string, unknown> = document;	×
146	for (let i = 0; i < parts.length; i++) {	×
147	const part = parts[i];	×
148	const key = part as keyof typeof current;	×
149	if (!current[key]) {	×
150	return;	×
151	} else if (i === parts.length - 1) {	×
152	delete current[key];	×
153	} else {	×
154	current = current[key] as Record<string, unknown>;	×
155	}	×
156	}	×
157	}	×
158	}	3✔

mongodb-js / mongodb-mcp-server / 19925638108

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