Skip to main content
Glama
mzxrai

MCP OpenAI Server

by mzxrai

openai_chat

Send messages to OpenAI's chat completion API using models like GPT-4o, GPT-4o-mini, o1-preview, or o1-mini for AI-powered conversations and responses.

Instructions

Use this tool when a user specifically requests to use one of OpenAI's models (gpt-4o, gpt-4o-mini, o1-preview, o1-mini). This tool sends messages to OpenAI's chat completion API using the specified model.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messagesYesArray of messages to send to the API
modelNoModel to use for completion (gpt-4o, gpt-4o-mini, o1-preview, o1-mini)gpt-4o

Implementation Reference

  • index.ts:95-137 (handler)
    Handler for the 'openai_chat' tool: parses input, validates model, calls OpenAI chat.completions.create, returns response or error.
    case "openai_chat": {
        try {
            // Parse request arguments
            const { messages: rawMessages, model } = request.params.arguments as {
                messages: Array<{ role: string; content: string }>;
                model?: SupportedModel;
            };
    
            // Validate model
            if (!SUPPORTED_MODELS.includes(model!)) {
                throw new Error(`Unsupported model: ${model}. Must be one of: ${SUPPORTED_MODELS.join(", ")}`);
            }
    
            // Convert messages to OpenAI's expected format
            const messages: ChatCompletionMessageParam[] = rawMessages.map(msg => ({
                role: msg.role as "system" | "user" | "assistant",
                content: msg.content
            }));
    
            // Call OpenAI API with fixed temperature
            const completion = await openai.chat.completions.create({
                messages,
                model: model!
            });
    
            // Return the response
            return {
                content: [{
                    type: "text",
                    text: completion.choices[0]?.message?.content || "No response received"
                }]
            };
        } catch (error) {
            return {
                content: [{
                    type: "text",
                    text: `OpenAI API error: ${(error as Error).message}`
                }],
                isError: true
            };
        }
    }
    default:
  • Input schema for 'openai_chat' tool defining messages array (role/content) and optional model from supported list.
    inputSchema: {
        type: "object",
        properties: {
            messages: {
                type: "array",
                description: "Array of messages to send to the API",
                items: {
                    type: "object",
                    properties: {
                        role: {
                            type: "string",
                            enum: ["system", "user", "assistant"],
                            description: "Role of the message sender"
                        },
                        content: {
                            type: "string",
                            description: "Content of the message"
                        }
                    },
                    required: ["role", "content"]
                }
            },
            model: {
                type: "string",
                enum: SUPPORTED_MODELS,
                description: `Model to use for completion (${SUPPORTED_MODELS.join(", ")})`,
                default: DEFAULT_MODEL
            }
        },
        required: ["messages"]
    }
  • index.ts:33-69 (registration)
    Tool registration in TOOLS array used by ListToolsRequestHandler, including name, description, and inputSchema.
    const TOOLS: Tool[] = [
        {
            name: "openai_chat",
            description: `Use this tool when a user specifically requests to use one of OpenAI's models (${SUPPORTED_MODELS.join(", ")}). This tool sends messages to OpenAI's chat completion API using the specified model.`,
            inputSchema: {
                type: "object",
                properties: {
                    messages: {
                        type: "array",
                        description: "Array of messages to send to the API",
                        items: {
                            type: "object",
                            properties: {
                                role: {
                                    type: "string",
                                    enum: ["system", "user", "assistant"],
                                    description: "Role of the message sender"
                                },
                                content: {
                                    type: "string",
                                    description: "Content of the message"
                                }
                            },
                            required: ["role", "content"]
                        }
                    },
                    model: {
                        type: "string",
                        enum: SUPPORTED_MODELS,
                        description: `Model to use for completion (${SUPPORTED_MODELS.join(", ")})`,
                        default: DEFAULT_MODEL
                    }
                },
                required: ["messages"]
            }
        }
    ];
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 the action ('sends messages') but omits critical behavioral details like authentication requirements, rate limits, error handling, or response format. For a tool interacting with an external API, this is a significant gap in transparency.

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 concise with two sentences that directly address purpose and usage. It's front-loaded with the usage condition, though it could be slightly more structured. There's minimal waste, earning a high score.

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 the complexity of an API call tool with no annotations and no output schema, the description is incomplete. It lacks details on authentication, error cases, response structure, and operational constraints, which are crucial for effective tool 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 fully documents the parameters. The description adds no additional parameter semantics beyond what's in the schema (e.g., no examples or usage tips). This meets the baseline for high schema coverage.

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 tool's purpose: 'sends messages to OpenAI's chat completion API using the specified model.' It specifies the verb ('sends'), resource ('messages'), and target ('OpenAI's chat completion API'), though it doesn't need to distinguish from siblings since none exist. The mention of specific models adds precision.

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

Usage Guidelines3/5

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

The description provides some usage guidance: 'Use this tool when a user specifically requests to use one of OpenAI's models.' This implies context but lacks explicit when-not-to-use scenarios or alternatives. With no sibling tools, the guidance is adequate but not comprehensive.

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/mzxrai/mcp-openai'

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