Skip to main content
Glama

chat_history

Retrieve conversation history for Pickaxe agents to analyze interactions, identify knowledge gaps, and review performance metrics.

Instructions

Fetch conversation history for a Pickaxe agent. Use to analyze user questions, identify KB gaps, and review agent performance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
studioNoStudio name to use. Available: STAGING, MAIN, DEV, PRODUCTION. Default: PRODUCTION
pickaxeIdYesThe Pickaxe agent ID (from the agent URL or config)
skipNoNumber of conversations to skip (for pagination). Default: 0
limitNoMaximum conversations to return. Default: 10, Max: 100
formatNoOutput format. 'messages' is human-readable, 'raw' includes metadata. Default: messages

Implementation Reference

  • The execution handler for the 'chat_history' tool. It makes a POST request to the Pickaxe API '/studio/pickaxe/history' endpoint with parameters pickaxeId, skip, limit, and format, then returns the JSON-formatted result.
    case "chat_history": {
      const result = await pickaxeRequest("/studio/pickaxe/history", "POST", {
        pickaxeId: args.pickaxeId,
        skip: args.skip ?? 0,
        limit: args.limit ?? 10,
        format: args.format ?? "messages",
      }, studio);
      return JSON.stringify(result, null, 2);
    }
  • Input schema definition for the 'chat_history' tool, specifying parameters like studio, pickaxeId (required), skip, limit, and format.
    inputSchema: {
      type: "object",
      properties: {
        studio: studioParam,
        pickaxeId: {
          type: "string",
          description: "The Pickaxe agent ID (from the agent URL or config)",
        },
        skip: {
          type: "number",
          description: "Number of conversations to skip (for pagination). Default: 0",
        },
        limit: {
          type: "number",
          description: "Maximum conversations to return. Default: 10, Max: 100",
        },
        format: {
          type: "string",
          enum: ["messages", "raw"],
          description: "Output format. 'messages' is human-readable, 'raw' includes metadata. Default: messages",
        },
      },
      required: ["pickaxeId"],
    },
  • src/index.ts:120-146 (registration)
    Registration of the 'chat_history' tool in the tools array, including name, description, and input schema. This array is used by the ListToolsRequestHandler.
      name: "chat_history",
      description: "Fetch conversation history for a Pickaxe agent. Use to analyze user questions, identify KB gaps, and review agent performance.",
      inputSchema: {
        type: "object",
        properties: {
          studio: studioParam,
          pickaxeId: {
            type: "string",
            description: "The Pickaxe agent ID (from the agent URL or config)",
          },
          skip: {
            type: "number",
            description: "Number of conversations to skip (for pagination). Default: 0",
          },
          limit: {
            type: "number",
            description: "Maximum conversations to return. Default: 10, Max: 100",
          },
          format: {
            type: "string",
            enum: ["messages", "raw"],
            description: "Output format. 'messages' is human-readable, 'raw' includes metadata. Default: messages",
          },
        },
        required: ["pickaxeId"],
      },
    },

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/aplaceforallmystuff/mcp-pickaxe'

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