Skip to main content
Glama
mongodb-developer

MongoDB Atlas MCP Server

Official

setup_atlas_network_access

Configure network access for MongoDB Atlas projects by specifying allowed IP addresses or CIDR blocks to control database connectivity.

Instructions

Sets up network access for an existing Atlas project. Accepts list of IP addresses or CIDR blocks.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
projectIdYesThe ID of the Atlas project.
ipAddressesYesAn array of IP addresses or CIDR blocks for network access.

Implementation Reference

  • The main handler function that implements the tool logic: constructs the Atlas API request to add the provided IP addresses to the project's IP access list and returns the result or error.
    private async setupAtlasNetworkAccess(input: NetworkAccessInput) {
      try {
        const url = `https://cloud.mongodb.com/api/atlas/v1.0/groups/${input.projectId}/accessList`;
        const body = input.ipAddresses.map(ip => ({
          ipAddress: ip,
          comment: "Added via Atlas Project Manager MCP"
        }));
    
        const result = await this.makeAtlasRequest(url, 'POST', body);
        return {
          content: [{
            type: 'text',
            text: JSON.stringify(result, null, 2)
          }]
        };
      } catch (error: any) {
        return {
          content: [{
            type: 'text',
            text: error.message
          }],
          isError: true
        };
      }
    }
  • src/index.ts:410-430 (registration)
    Registration of the tool in the ListTools handler, defining name, description, and JSON input schema.
    {
      name: 'setup_atlas_network_access',
      description: 'Sets up network access for an existing Atlas project. Accepts list of IP addresses or CIDR blocks.',
      inputSchema: {
        type: 'object',
        properties: {
          projectId: {
            type: 'string',
            description: 'The ID of the Atlas project.',
          },
          ipAddresses: {
            type: 'array',
            items: {
              type: 'string',
            },
            description: 'An array of IP addresses or CIDR blocks for network access.',
          },
        },
        required: ['projectId', 'ipAddresses'],
      },
    },
  • TypeScript interface defining the expected input shape for the handler function.
    interface NetworkAccessInput {
      projectId: string;
      ipAddresses: string[];
    }
  • src/index.ts:552-554 (registration)
    Dispatch to the handler function in the CallToolRequestSchema switch statement.
    case 'setup_atlas_network_access':
      result = await this.setupAtlasNetworkAccess(input as unknown as NetworkAccessInput);
      break;
  • Shared helper method for making authenticated requests to the Atlas API using Digest authentication.
    private async makeAtlasRequest(url: string, method: string, body?: any) {
      // Step 1: Make initial request to get digest challenge
      const initialResponse = await fetch(url, {
        method,
        headers: {
          'Content-Type': 'application/json'
        },
        body: body ? JSON.stringify(body) : undefined
      });
    
      // Check if we got a 401 with WWW-Authenticate header (digest challenge)
      if (initialResponse.status === 401) {
        const wwwAuthHeader = initialResponse.headers.get('WWW-Authenticate');
        if (!wwwAuthHeader || !wwwAuthHeader.startsWith('Digest ')) {
          throw new Error('Expected Digest authentication challenge not received');
        }
    
        // Parse the digest challenge
        const authDetails: Record<string, string> = {};
        wwwAuthHeader.substring(7).split(',').forEach(part => {
          const [key, value] = part.trim().split('=');
          // Remove quotes if present
          authDetails[key] = value.startsWith('"') ? value.slice(1, -1) : value;
        });
    
        // Generate a random client nonce (cnonce)
        const cnonce = Math.random().toString(36).substring(2, 15);
        const nc = '00000001'; // nonce count, incremented for each request with the same nonce
    
        // Calculate the response hash
        const ha1 = this.md5(`${this.apiKey}:${authDetails.realm}:${this.privateKey}`);
        const ha2 = this.md5(`${method}:${new URL(url).pathname}`);
        const response = this.md5(`${ha1}:${authDetails.nonce}:${nc}:${cnonce}:${authDetails.qop}:${ha2}`);
    
        // Build the Authorization header
        const authHeader = `Digest username="${this.apiKey}", realm="${authDetails.realm}", nonce="${authDetails.nonce}", uri="${new URL(url).pathname}", qop=${authDetails.qop}, nc=${nc}, cnonce="${cnonce}", response="${response}", algorithm=${authDetails.algorithm || 'MD5'}`;
    
        // Make the actual request with the digest authentication
        const digestResponse = await fetch(url, {
          method,
          headers: {
            'Content-Type': 'application/json',
            'Authorization': authHeader
          },
          body: body ? JSON.stringify(body) : undefined
        });
    
        if (!digestResponse.ok) {
          throw new Error(`Atlas API error: ${digestResponse.statusText}`);
        }
    
        return digestResponse.json();
      } else if (initialResponse.ok) {
        // If the initial request succeeded without authentication (unlikely)
        return initialResponse.json();
      } else {
        throw new Error(`Atlas API error: ${initialResponse.statusText}`);
      }
    }
Behavior2/5

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

With no annotations provided, the description carries full burden but offers minimal behavioral context. It states the tool 'Sets up network access' (implying a write/mutation operation) but doesn't disclose permissions needed, whether changes are reversible, rate limits, or what happens to existing network settings. This is inadequate for a mutation tool without annotation coverage.

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

Conciseness4/5

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

The description is appropriately sized with two concise sentences that directly address the tool's function and parameter scope. It's front-loaded with the core purpose and avoids unnecessary elaboration.

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?

For a mutation tool with no annotations and no output schema, the description is insufficient. It lacks crucial details like expected response format, error conditions, side effects, or how this tool interacts with sibling operations (e.g., whether network access affects cluster creation).

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 both parameters fully. The description adds minimal value by mentioning 'IP addresses or CIDR blocks' for the ipAddresses parameter, but doesn't provide additional syntax, format details, or constraints beyond what the schema states.

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 ('Sets up network access') and target resource ('for an existing Atlas project'), providing specific verb+resource pairing. However, it doesn't explicitly differentiate from sibling tools like 'create_atlas_cluster' or 'list_atlas_projects', which would require a 5.

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. It doesn't mention prerequisites (e.g., project must exist), exclusions, or compare with sibling tools like 'get_atlas_connection_strings' for related network tasks.

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/mongodb-developer/mcp-mongodb-atlas'

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