Skip to main content
Glama

delete

Remove data from APIs by making DELETE HTTP requests to specified URLs with optional headers and authentication.

Instructions

Make a DELETE HTTP request

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesThe URL to make the DELETE request to
headersNoOptional headers to include in the request
authNoOptional auth configuration to load a stored bearer token

Implementation Reference

  • Handler for the 'delete' tool: extracts URL and optional headers/auth, applies authentication if provided, validates required URL, performs DELETE request via makeHttpRequest helper, and returns a formatted text response with status and body.
    case "delete": {
      const url = String(args?.url || '');
      const auth = args?.auth as AuthConfig | undefined;
      const headers = applyAuthHeader(args?.headers as Record<string, string> || {}, auth);
      
      if (!url) {
        throw new Error("URL is required for DELETE request");
      }
    
      const result = await makeHttpRequest('DELETE', { url, headers });
      
      return {
        content: [{
          type: "text",
          text: `DELETE ${url}\nStatus: ${result.status} ${result.statusText}\nResponse: ${JSON.stringify(result.data, null, 2)}`
        }]
      };
    }
  • src/index.ts:200-234 (registration)
    Registration of the 'delete' tool in the listTools response, defining its name, description, and input schema for URL, optional headers, and auth.
    {
      name: "delete",
      description: "Make a DELETE HTTP request",
      inputSchema: {
        type: "object",
        properties: {
          url: {
            type: "string",
            description: "The URL to make the DELETE request to"
          },
          headers: {
            type: "object",
            description: "Optional headers to include in the request",
            additionalProperties: {
              type: "string"
            }
          },
          auth: {
            type: "object",
            description: "Optional auth configuration to load a stored bearer token",
            properties: {
              folder: {
                type: "string",
                description: "Folder where tokens are stored (tokens.json)"
              },
              user_title: {
                type: "string",
                description: "User title to pick the token from storage (default: 'default')"
              }
            }
          }
        },
        required: ["url"]
      }
    },
  • Shared helper function that executes the actual HTTP request for all tools, including DELETE. Handles logging, options preparation, fetch call, response parsing, and error handling.
    async function makeHttpRequest(method: string, config: HttpRequestConfig) {
      try {
        server.sendLoggingMessage({
          level: "info",
          data: `Starting ${method.toUpperCase()} request to: ${config.url}`,
        });
    
        const options: NodeRequestInit = {
          method: method.toUpperCase(),
          headers: {
            ...config.headers,
          },
        };
    
        if (config.body && (method === 'POST' || method === 'PUT')) {
          if (config.requestType === 'form-data') {
            server.sendLoggingMessage({
              level: "info",
              data: `Using form-data request type with fieldFiles: ${JSON.stringify(config.fieldFiles)}`,
            });
            
            // Use FormData for form-data requests
            const formData = await createFormData(config.body, config.fieldFiles);
            options.body = formData as any; // Cast to any to handle type incompatibility
            
            server.sendLoggingMessage({
              level: "info",
              data: `FormData prepared, not setting Content-Type header (will be auto-set with boundary)`,
            });
            // Don't set Content-Type header for FormData, let the system set it with boundary
          } else {
            server.sendLoggingMessage({
              level: "info",
              data: `Using JSON request type`,
            });
            
            // Use JSON for regular requests
            options.headers = {
              'Content-Type': 'application/json',
              ...options.headers,
            };
            options.body = typeof config.body === 'string' ? config.body : JSON.stringify(config.body);
            
            server.sendLoggingMessage({
              level: "info",
              data: `JSON body prepared: ${options.body}`,
            });
          }
        } else if (!config.body && method !== 'GET' && method !== 'DELETE') {
          // Set default Content-Type for POST/PUT without body
          options.headers = {
            'Content-Type': 'application/json',
            ...options.headers,
          };
        }
    
        server.sendLoggingMessage({
          level: "info",
          data: `Request headers: ${JSON.stringify(options.headers)}`,
        });
    
        server.sendLoggingMessage({
          level: "info",
          data: `Making HTTP request...`,
        });
    
        const response = await fetch(config.url, options);
        
        server.sendLoggingMessage({
          level: "info",
          data: `Response received: ${response.status} ${response.statusText}`,
        });
    
        const responseText = await response.text();
        
        server.sendLoggingMessage({
          level: "info",
          data: `Response body: ${responseText}`,
        });
        
        // Try to parse as JSON, fallback to text
        let responseData;
        try {
          responseData = JSON.parse(responseText);
        } catch {
          responseData = responseText;
        }
    
        // Store in history
        requestHistory.push({
          method: method.toUpperCase(),
          config,
          timestamp: new Date()
        });
    
        return {
          status: response.status,
          statusText: response.statusText,
          headers: Object.fromEntries(response.headers.entries()),
          data: responseData
        };
      } catch (error) {
        server.sendLoggingMessage({
          level: "error",
          data: `HTTP ${method.toUpperCase()} request failed: ${error instanceof Error ? error.message : String(error)}`,
        });
        throw new Error(`HTTP ${method.toUpperCase()} request failed: ${error instanceof Error ? error.message : String(error)}`);
      }
    }
  • Helper function to apply stored bearer token Authorization header based on auth config (folder and user_title), used by delete handler.
    function applyAuthHeader(headers: Record<string, string>, auth?: AuthConfig): Record<string, string> {
      if (!auth) {
        return headers;
      }
    
      const folder = auth.folder;
      if (!folder) {
        throw new Error("auth.folder is required when using auth configuration");
      }
    
      if (headers.Authorization) {
        return headers;
      }
    
      const userTitle = auth.user_title || 'default';
      const tokens = loadStoredTokens(folder);
      const tokenEntry = tokens.find((entry) => entry.user_title_name === userTitle);
    
      if (!tokenEntry) {
        throw new Error(`No token found for user_title '${userTitle}' in folder '${folder}'`);
      }
    
      return {
        ...headers,
        Authorization: `Bearer ${tokenEntry.token}`,
      };
    }
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 only states the basic action without disclosing behavioral traits. It doesn't mention potential destructive effects (DELETE typically removes resources), authentication requirements beyond the optional auth parameter, rate limits, error handling, or response format. This leaves significant gaps for a mutation tool.

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 extremely concise with a single sentence that directly states the tool's function. It's front-loaded with no wasted words, making it easy to parse quickly. Every word earns its place.

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 this is a mutation tool (DELETE) with no annotations, no output schema, and complex parameters including nested objects, the description is incomplete. It fails to address critical aspects like what the tool returns, error conditions, or the implications of making a DELETE request, leaving the agent with insufficient context for safe and 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 three parameters thoroughly. The description adds no additional meaning beyond what's in the schema, such as explaining parameter interactions or 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 ('Make a DELETE HTTP request') which is specific and unambiguous. It distinguishes from siblings like 'get', 'post', and 'put' by specifying the HTTP method. However, it doesn't explicitly mention what resource it operates on beyond the URL parameter.

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 like 'post' or 'put', nor does it mention any prerequisites or context for making DELETE requests. It lacks explicit when/when-not instructions or references to sibling tools for different operations.

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/vilasone455/api-mcp'

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