Skip to main content
Glama
ricleedo

MCP Server Boilerplate

by ricleedo

mongo-aggregate

Execute aggregation pipelines on MongoDB collections to process and analyze data through multi-stage operations.

Instructions

Execute aggregation pipeline on a MongoDB collection

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
databaseYesDatabase name
collectionYesCollection name
pipelineYesAggregation pipeline as array of stage objects

Implementation Reference

  • Handler function that executes the MongoDB aggregation pipeline on the specified collection, formats the results, and returns them in the MCP response format.
    async ({ database: dbName, collection: collectionName, pipeline }) => {
      try {
        const db = await ensureConnection(dbName);
        const collection: Collection = db.collection(collectionName);
        
        const documents = await collection.aggregate(pipeline).toArray();
        
        const formattedOutput = formatJsonOutput(documents);
        
        return {
          content: [
            {
              type: "text",
              text: `Aggregation returned ${documents.length} document(s):\n\n${formattedOutput}`,
            },
          ],
        };
      } catch (error) {
        throw new Error(`Failed to execute aggregation: ${error instanceof Error ? error.message : 'Unknown error'}`);
      }
    }
  • Input schema using Zod for validating database name, collection name, and aggregation pipeline array.
    {
      database: z.string().describe("Database name"),
      collection: z.string().describe("Collection name"),
      pipeline: z.array(z.record(z.any())).describe("Aggregation pipeline as array of stage objects"),
    },
  • src/index.ts:233-262 (registration)
    Registration of the 'mongo-aggregate' tool using server.tool(), including name, description, schema, and inline handler.
    server.tool(
      "mongo-aggregate",
      "Execute aggregation pipeline on a MongoDB collection",
      {
        database: z.string().describe("Database name"),
        collection: z.string().describe("Collection name"),
        pipeline: z.array(z.record(z.any())).describe("Aggregation pipeline as array of stage objects"),
      },
      async ({ database: dbName, collection: collectionName, pipeline }) => {
        try {
          const db = await ensureConnection(dbName);
          const collection: Collection = db.collection(collectionName);
          
          const documents = await collection.aggregate(pipeline).toArray();
          
          const formattedOutput = formatJsonOutput(documents);
          
          return {
            content: [
              {
                type: "text",
                text: `Aggregation returned ${documents.length} document(s):\n\n${formattedOutput}`,
              },
            ],
          };
        } catch (error) {
          throw new Error(`Failed to execute aggregation: ${error instanceof Error ? error.message : 'Unknown error'}`);
        }
      }
    );
  • Helper function to ensure MongoDB client connection and return the database instance, used by all tools including mongo-aggregate.
    async function ensureConnection(dbName: string): Promise<Db> {
      if (!mongoClient) {
        const uri = getMongoUri();
        mongoClient = new MongoClient(uri);
        await mongoClient.connect();
      }
      
      if (!databases.has(dbName)) {
        databases.set(dbName, mongoClient.db(dbName));
      }
      
      return databases.get(dbName)!;
    }
  • Helper function to format and truncate large JSON outputs for tool responses, called by the handler.
    function formatJsonOutput(data: unknown): string {
      const truncatedData = truncateForOutput(data);
      let outputText = JSON.stringify(truncatedData, null, 2);
      
      outputText = outputText.replace(
        /"\.\.\.(\d+) more items"/g,
        "...$1 more items"
      );
      outputText = outputText.replace(
        /"\.\.\.(\d+) more properties": "\.\.\.?"/g,
        "...$1 more properties"
      );
      
      return outputText;
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.0.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
  2. First observed

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions 'Execute aggregation pipeline' which implies a read operation, but doesn't disclose if it's read-only, has side effects, requires specific permissions, or handles errors. For a tool with no annotations, this leaves critical behavioral traits unspecified.

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

Conciseness5/5

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

The description is a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, making it easy to parse quickly. Every word earns its place without redundancy.

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

Completeness2/5

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

Given no annotations, no output schema, and a tool that performs complex database operations, the description is incomplete. It doesn't explain return values, error handling, or performance implications. For a tool with 3 parameters and significant behavioral complexity, this minimal description leaves too many gaps for effective use.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all parameters (database, collection, pipeline). The description adds no additional meaning beyond what's in the schema, such as explaining what an aggregation pipeline is or providing usage examples. Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the action ('Execute aggregation pipeline') and resource ('on a MongoDB collection'), making the purpose understandable. However, it doesn't differentiate from sibling tools like mongo-find-documents or mongo-count-documents, which also operate on collections but with different query methods.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. With siblings like mongo-find-documents for simple queries and mongo-count-documents for counting, there's no indication that this tool is for complex data transformations or analytics, leaving the agent to guess based on the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.