Skip to main content
Glama
manpreet2000

MCP Database Server

aggregate

Process MongoDB data by applying multiple operations like filtering, grouping, and sorting in a pipeline to transform and analyze database collections.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
collectionNameYes
pipelineYes
optionsNo

Implementation Reference

  • Handler function that executes MongoDB aggregation: connects to DB if needed, runs collection.aggregate(pipeline, options), returns JSON stringified result.
      async ({ collectionName, pipeline, options }) => {
        try {
          let db = mongodbConnection.getDb();
          if (!db) {
            await mongodbConnection.connect(this.MONGODB_URI);
            db = mongodbConnection.getDb();
            if (!db) throw new Error("Failed to connect to database");
          }
          const collection = db.collection(collectionName);
          const result = await collection
            .aggregate(pipeline, { maxTimeMS: 30000, ...options })
            .toArray();
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(result),
              },
            ],
          };
        } catch (error) {
          console.error(error);
          return {
            content: [{ type: "text", text: "Error: " + error }],
          };
        }
      }
    );
  • Zod input schema for aggregate tool: collectionName (string), pipeline (array of MongoDB aggregation stages with validation ensuring exactly one stage type per object), optional options.
    {
      collectionName: z.string(),
      pipeline: z.array(
        z
          .object({
            $match: z.record(z.any()).optional(),
            $group: z.record(z.any()).optional(),
            $project: z.record(z.any()).optional(),
            $sort: z.record(z.any()).optional(),
            $limit: z.number().optional(),
            $skip: z.number().optional(),
            $unwind: z.string().optional(),
            $lookup: z
              .object({
                from: z.string(),
                localField: z.string(),
                foreignField: z.string(),
                as: z.string(),
              })
              .optional(),
            $count: z.string().optional(),
            $addFields: z.record(z.any()).optional(),
            $replaceRoot: z.record(z.any()).optional(),
            $facet: z.record(z.any()).optional(),
            $bucket: z.record(z.any()).optional(),
            $geoNear: z.record(z.any()).optional(),
            $indexStats: z.record(z.any()).optional(),
            $listLocalSessions: z.record(z.any()).optional(),
            $listSessions: z.record(z.any()).optional(),
            $merge: z.record(z.any()).optional(),
            $out: z.string().optional(),
            $planCacheStats: z.record(z.any()).optional(),
            $redact: z.record(z.any()).optional(),
            $replaceWith: z.record(z.any()).optional(),
            $sample: z.object({ size: z.number() }).optional(),
            $search: z.record(z.any()).optional(),
            $searchMeta: z.record(z.any()).optional(),
            $set: z.record(z.any()).optional(),
            $setWindowFields: z.record(z.any()).optional(),
            $unionWith: z.record(z.any()).optional(),
            $unset: z.string().optional(),
          })
          .refine(
            (obj) => {
              // Count the number of defined fields
              const definedFields = Object.keys(obj).filter(
                (key) => obj[key as keyof typeof obj] !== undefined
              );
              return definedFields.length === 1;
            },
            {
              message: "Each pipeline stage must contain exactly one field",
            }
          )
      ),
      options: z.object({}).optional(),
    },
  • src/index.ts:151-237 (registration)
    Full registration of the 'aggregate' tool using this.mcpServer.tool(name, schema, handler), including inline schema and handler.
    this.mcpServer.tool(
      "aggregate",
      {
        collectionName: z.string(),
        pipeline: z.array(
          z
            .object({
              $match: z.record(z.any()).optional(),
              $group: z.record(z.any()).optional(),
              $project: z.record(z.any()).optional(),
              $sort: z.record(z.any()).optional(),
              $limit: z.number().optional(),
              $skip: z.number().optional(),
              $unwind: z.string().optional(),
              $lookup: z
                .object({
                  from: z.string(),
                  localField: z.string(),
                  foreignField: z.string(),
                  as: z.string(),
                })
                .optional(),
              $count: z.string().optional(),
              $addFields: z.record(z.any()).optional(),
              $replaceRoot: z.record(z.any()).optional(),
              $facet: z.record(z.any()).optional(),
              $bucket: z.record(z.any()).optional(),
              $geoNear: z.record(z.any()).optional(),
              $indexStats: z.record(z.any()).optional(),
              $listLocalSessions: z.record(z.any()).optional(),
              $listSessions: z.record(z.any()).optional(),
              $merge: z.record(z.any()).optional(),
              $out: z.string().optional(),
              $planCacheStats: z.record(z.any()).optional(),
              $redact: z.record(z.any()).optional(),
              $replaceWith: z.record(z.any()).optional(),
              $sample: z.object({ size: z.number() }).optional(),
              $search: z.record(z.any()).optional(),
              $searchMeta: z.record(z.any()).optional(),
              $set: z.record(z.any()).optional(),
              $setWindowFields: z.record(z.any()).optional(),
              $unionWith: z.record(z.any()).optional(),
              $unset: z.string().optional(),
            })
            .refine(
              (obj) => {
                // Count the number of defined fields
                const definedFields = Object.keys(obj).filter(
                  (key) => obj[key as keyof typeof obj] !== undefined
                );
                return definedFields.length === 1;
              },
              {
                message: "Each pipeline stage must contain exactly one field",
              }
            )
        ),
        options: z.object({}).optional(),
      },
      async ({ collectionName, pipeline, options }) => {
        try {
          let db = mongodbConnection.getDb();
          if (!db) {
            await mongodbConnection.connect(this.MONGODB_URI);
            db = mongodbConnection.getDb();
            if (!db) throw new Error("Failed to connect to database");
          }
          const collection = db.collection(collectionName);
          const result = await collection
            .aggregate(pipeline, { maxTimeMS: 30000, ...options })
            .toArray();
          return {
            content: [
              {
                type: "text",
                text: JSON.stringify(result),
              },
            ],
          };
        } catch (error) {
          console.error(error);
          return {
            content: [{ type: "text", text: "Error: " + error }],
          };
        }
      }
    );
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

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/manpreet2000/mcp-database-server'

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