20659002550

Committed 02 Jan 2026 01:36PM UTC coverage: 79.432% (+0.03%) from 79.4%

Build # 20659002550

Build Type

Pull #819

github

Committed by

web-flow

Commit Message

Merge 85f3cdd9a into b5213e680

Pull Request Pull Request #819: feat: add transport metadata to all tools - MCP-348

Run Details

1478 of 1936 branches covered (76.34%)

Branch coverage included in aggregate %.

28 of 29 new or added lines in 4 files covered. (96.55%)

56 existing lines in 3 files now uncovered.

6802 of 8488 relevant lines covered (80.14%)

86.27 hits per line

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

60.61

/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";
import type { ConnectionMetadata, AutoEmbeddingsUsageMetadata } from "../../../telemetry/types.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>;
            }
        }
    }

    protected resolveTelemetryMetadata(
        args: ToolArgs<typeof this.argsShape>,
        { result }: { result: CallToolResult }
    ): ConnectionMetadata | AutoEmbeddingsUsageMetadata {
        if ("embeddingParameters" in args && this.config.voyageApiKey) {
            return {
                ...super.resolveTelemetryMetadata(args, { result }),
                embeddingsGeneratedBy: "mcp",
            };
        } else {
            return super.resolveTelemetryMetadata(args, { result });
        }
    }
}

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	import type { ConnectionMetadata, AutoEmbeddingsUsageMetadata } from "../../../telemetry/types.js";
10
11	const zSupportedEmbeddingParametersWithInput = zSupportedEmbeddingParameters.extend({	3✔
12	input: z	3✔
13	.array(z.object({}).passthrough())	3✔
14	.describe(	3✔
15	"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✔
16	),	3✔
17	});	3✔
18
19	const commonArgs = {	3✔
20	...DbOperationArgs,	3✔
21	documents: z	3✔
22	.array(zEJSON().describe("An individual MongoDB document"))	3✔
23	.describe(	3✔
24	"The array of documents to insert, matching the syntax of the document argument of db.collection.insertMany()."	3✔
25	),	3✔
26	} as const;	3✔
27
28	export class InsertManyTool extends MongoDBToolBase {	3✔
29	public name = "insert-many";	118✔
30	protected description = "Insert an array of documents into a MongoDB collection";	118✔
31	protected argsShape = this.isFeatureEnabled("search")	118✔
32	? {	15✔
33	...commonArgs,	15✔
34	embeddingParameters: zSupportedEmbeddingParametersWithInput	15✔
35	.optional()	15✔
36	.describe(	15✔
37	"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✔
38	),	15✔
39	}	15✔
40	: commonArgs;	103✔
41	static operationType: OperationType = "create";	3✔
42
43	protected async execute({	3✔
44	database,	8✔
45	collection,	8✔
46	documents,	8✔
47	...conditionalArgs	8✔
48	}: ToolArgs<typeof this.argsShape>): Promise<CallToolResult> {	8✔
49	const provider = await this.ensureConnected();	8✔
50
51	let embeddingParameters: z.infer<typeof zSupportedEmbeddingParametersWithInput> \| undefined;	7✔
52	if ("embeddingParameters" in conditionalArgs) {	8!
UNCOV 53	embeddingParameters = conditionalArgs.embeddingParameters;	×
54	}	✔
55
56	// Process documents to replace raw string values with generated embeddings
57	documents = await this.replaceRawValuesWithEmbeddingsIfNecessary({	7✔
58	database,	7✔
59	collection,	7✔
60	documents,	7✔
61	embeddingParameters,	7✔
62	});	7✔
63
64	await this.session.vectorSearchEmbeddingsManager.assertFieldsHaveCorrectEmbeddings(	7✔
65	{ database, collection },	7✔
66	documents	7✔
67	);	7✔
68
69	const result = await provider.insertMany(database, collection, documents);	6✔
70	const content = formatUntrustedData(	5✔
71	"Documents were inserted successfully.",	5✔
72	`Inserted \`${result.insertedCount}\` document(s) into ${database}.${collection}.`,	5✔
73	`Inserted IDs: ${Object.values(result.insertedIds).join(", ")}`	5✔
74	);	5✔
75	return {	5✔
76	content,	5✔
77	};	5✔
78	}	8✔
79
80	private async replaceRawValuesWithEmbeddingsIfNecessary({	3✔
81	database,	7✔
82	collection,	7✔
83	documents,	7✔
84	embeddingParameters,	7✔
85	}: {	7✔
86	database: string;
87	collection: string;
88	documents: Document[];
89	embeddingParameters?: z.infer<typeof zSupportedEmbeddingParametersWithInput>;
90	}): Promise<Document[]> {	7✔
91	// If no embedding parameters or no input specified, return documents as-is
92	if (!embeddingParameters?.input \|\| embeddingParameters.input.length === 0) {	7!
93	return documents;	7✔
94	}	7!
95
96	// Get vector search indexes for the collection
UNCOV 97	const vectorIndexes = await this.session.vectorSearchEmbeddingsManager.embeddingsForNamespace({	×
98	database,	×
99	collection,	×
100	});	×
101
102	// Ensure for inputted fields, the vector search index exists.
UNCOV 103	for (const input of embeddingParameters.input) {	×
104	for (const fieldPath of Object.keys(input)) {	×
105	if (!vectorIndexes.some((index) => index.path === fieldPath)) {	×
106	throw new MongoDBError(	×
107	ErrorCodes.AtlasVectorSearchInvalidQuery,	×
108	`Field '${fieldPath}' does not have a vector search index in collection ${database}.${collection}. Only fields with vector search indexes can have embeddings generated.`	×
109	);	×
110	}	×
111	}	×
112	}	×
113
114	// We make one call to generate embeddings for all documents at once to avoid making too many API calls.
UNCOV 115	const flattenedEmbeddingsInput = embeddingParameters.input.flatMap((documentInput, index) =>	×
116	Object.entries(documentInput).map(([fieldPath, rawTextValue]) => ({	×
117	fieldPath,	×
118	rawTextValue,	×
119	documentIndex: index,	×
120	}))	×
121	);	×
122
UNCOV 123	const generatedEmbeddings = await this.session.vectorSearchEmbeddingsManager.generateEmbeddings({	×
124	rawValues: flattenedEmbeddingsInput.map(({ rawTextValue }) => rawTextValue) as string[],	×
125	embeddingParameters,	×
126	inputType: "document",	×
127	});	×
128
UNCOV 129	const processedDocuments: Document[] = [...documents];	×
130
UNCOV 131	for (const [index, { fieldPath, documentIndex }] of flattenedEmbeddingsInput.entries()) {	×
132	if (!processedDocuments[documentIndex]) {	×
133	throw new MongoDBError(ErrorCodes.Unexpected, `Document at index ${documentIndex} does not exist.`);	×
134	}	×
135	// Ensure no nested fields are present in the field path.
UNCOV 136	this.deleteFieldPath(processedDocuments[documentIndex], fieldPath);	×
137	processedDocuments[documentIndex][fieldPath] = generatedEmbeddings[index];	×
138	}	×
139
UNCOV 140	return processedDocuments;	×
141	}	7✔
142
143	// Delete a specified field path from a document using dot notation.
144	private deleteFieldPath(document: Record<string, unknown>, fieldPath: string): void {	3✔
UNCOV 145	const parts = fieldPath.split(".");	×
146	let current: Record<string, unknown> = document;	×
147	for (let i = 0; i < parts.length; i++) {	×
148	const part = parts[i];	×
149	const key = part as keyof typeof current;	×
150	if (!current[key]) {	×
151	return;	×
152	} else if (i === parts.length - 1) {	×
153	delete current[key];	×
154	} else {	×
155	current = current[key] as Record<string, unknown>;	×
156	}	×
157	}	×
158	}	×
159
160	protected resolveTelemetryMetadata(	3✔
161	args: ToolArgs<typeof this.argsShape>,	3✔
162	{ result }: { result: CallToolResult }	3✔
163	): ConnectionMetadata \| AutoEmbeddingsUsageMetadata {	3✔
164	if ("embeddingParameters" in args && this.config.voyageApiKey) {	3!
UNCOV 165	return {	×
166	...super.resolveTelemetryMetadata(args, { result }),	×
167	embeddingsGeneratedBy: "mcp",	×
168	};	×
169	} else {	3✔
170	return super.resolveTelemetryMetadata(args, { result });	3✔
171	}	3✔
172	}	3✔
173	}	3✔

mongodb-js / mongodb-mcp-server / 20659002550

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