Skip to main content
Glama
getgapup

@gapup/mcp-knowledge

by getgapup

competitor_intel

Read-onlyIdempotent

Generate a board-ready competitive-intelligence report analyzing competitor moves, pricing changes, and strategic signals, with quantified recommendations and a presenter script.

Instructions

Generate a board-ready competitive-intelligence report for a company against named competitors. Returns: recent competitor moves (product releases, pricing changes, hiring, funding) each with a severity score (critical/high/medium/low), prioritised signals, a pricing-radar comparison, 3-6 quantified recommendations (expected impact in € or %, over 7/30/90/180-day horizons), and an 8-12 slide presenter script. When to use this tool: the user wants to analyse, benchmark or track competitors, or needs a competitive briefing before a strategic decision. Inputs: the user's own company (name + one-paragraph pitch) and 1-10 competitors to analyse. Delivered by Manue, the AI CMO of the Gapup portfolio.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
selfCompanyYesYour company info
competitorsYes1-10 competitors to analyze
focusNoOptional — what the buyer wants to track first (e.g. pricing moves, hiring patterns)

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
executiveSummaryYesBoard-ready prose summary (120-400 chars)
competitorMovesYesRecent moves per competitor with severity rating
pricingRadarNoPricing comparison across competitors
recommendationsYes3-6 actionable strategic recommendations
presenterScriptYes8-12 slide board presenter script
kpisNo3-5 headline KPI bubbles
sourcesNoCited sources

Implementation Reference

  • The handler function for the competitor_intel tool. Delegates to callGapupEndpoint('competitor-intel', input, signal) to make an HTTP POST to the Gapup API.
    export async function handle(input: unknown, signal?: AbortSignal): Promise<unknown> {
      return callGapupEndpoint("competitor-intel", input, signal);
  • Full tool definition including name ('competitor_intel'), description, inputSchema (selfCompany, competitors, focus), outputSchema (executiveSummary, competitorMoves, pricingRadar, recommendations, presenterScript, kpis, sources), and annotations.
    export const tool = {
      name: "competitor_intel",
      description:
        "Generate a board-ready competitive-intelligence report for a company against named competitors. Returns: recent competitor moves (product releases, pricing changes, hiring, funding) each with a severity score (critical/high/medium/low), prioritised signals, a pricing-radar comparison, 3-6 quantified recommendations (expected impact in € or %, over 7/30/90/180-day horizons), and an 8-12 slide presenter script. When to use this tool: the user wants to analyse, benchmark or track competitors, or needs a competitive briefing before a strategic decision. Inputs: the user's own company (name + one-paragraph pitch) and 1-10 competitors to analyse. Delivered by Manue, the AI CMO of the Gapup portfolio.",
      inputSchema: {
        type: "object",
        properties: {
          selfCompany: {
            type: "object",
            description: "Your company info",
            properties: {
              name: { type: "string", minLength: 2, maxLength: 120 },
              url: { type: "string", format: "uri" },
              pitch: { type: "string", minLength: 10, maxLength: 400, description: "One-paragraph pitch" },
            },
            required: ["name", "pitch"],
          },
          competitors: {
            type: "array",
            description: "1-10 competitors to analyze",
            items: {
              type: "object",
              properties: {
                name: { type: "string", minLength: 2, maxLength: 120 },
                url: { type: "string", format: "uri" },
              },
              required: ["name", "url"],
            },
            minItems: 1,
            maxItems: 10,
          },
          focus: {
            type: "string",
            maxLength: 400,
            description: "Optional — what the buyer wants to track first (e.g. pricing moves, hiring patterns)",
          },
        },
        required: ["selfCompany", "competitors"],
      },
      outputSchema: {
        type: "object",
        properties: {
          executiveSummary: {
            type: "string",
            description: "Board-ready prose summary (120-400 chars)",
          },
          competitorMoves: {
            type: "array",
            description: "Recent moves per competitor with severity rating",
            items: {
              type: "object",
              properties: {
                competitor: { type: "string" },
                move: { type: "string" },
                severity: { type: "string", enum: ["critical", "high", "medium", "low"] },
                date: { type: "string" },
                source: { type: "string" },
              },
              required: ["competitor", "move", "severity"],
            },
          },
          pricingRadar: {
            type: "array",
            description: "Pricing comparison across competitors",
            items: {
              type: "object",
              properties: {
                competitor: { type: "string" },
                tier: { type: "string" },
                priceEur: { type: "number" },
                features: { type: "array", items: { type: "string" } },
              },
              required: ["competitor"],
            },
          },
          recommendations: {
            type: "array",
            description: "3-6 actionable strategic recommendations",
            items: {
              type: "object",
              properties: {
                action: { type: "string" },
                expectedImpact: { type: "string" },
                horizon: { type: "string", enum: ["7d", "30d", "90d", "180d"] },
                priority: { type: "string", enum: ["critical", "high", "medium", "low"] },
              },
              required: ["action", "expectedImpact", "horizon"],
            },
          },
          presenterScript: {
            type: "array",
            description: "8-12 slide board presenter script",
            items: {
              type: "object",
              properties: {
                slide: { type: "integer" },
                title: { type: "string" },
                keyPoints: { type: "array", items: { type: "string" } },
                speakerNote: { type: "string" },
                visualHint: { type: "string" },
              },
              required: ["slide", "title", "keyPoints", "speakerNote"],
            },
          },
          kpis: {
            type: "array",
            description: "3-5 headline KPI bubbles",
            items: {
              type: "object",
              properties: {
                label: { type: "string" },
                value: { type: "string" },
                trend: { type: "string", enum: ["up", "down", "stable"] },
              },
              required: ["label", "value"],
            },
          },
          sources: {
            type: "array",
            description: "Cited sources",
            items: {
              type: "object",
              properties: {
                url: { type: "string" },
                excerpt: { type: "string" },
              },
              required: ["url"],
            },
          },
        },
        required: ["executiveSummary", "competitorMoves", "recommendations", "presenterScript"],
      },
      annotations: {
        readOnlyHint: true,
        idempotentHint: true,
        destructiveHint: false,
        openWorldHint: true,
        title: "Competitor Intelligence Report",
      },
    } as const;
  • src/index.ts:21-21 (registration)
    Import of the tool definition and handler from the competitor-intel module.
    import { tool as competitorIntelTool, handle as competitorIntelHandle } from "./tools/competitor-intel.js";
  • src/index.ts:37-37 (registration)
    Registration of competitorIntelTool and competitorIntelHandle in the TOOLS array, linking the tool definition to its handler for the MCP server.
    { def: competitorIntelTool, handle: competitorIntelHandle },
  • The callGapupEndpoint helper function that performs the actual HTTP request. It POSTs to /api/agent/{slug} with the X-Api-Key header and handles errors (401, 402, 404, 429, and others).
    export async function callGapupEndpoint(
      slug: string,
      input: unknown,
      signal?: AbortSignal
    ): Promise<unknown> {
      const apiKey = process.env.GAPUP_API_KEY;
      if (!apiKey) {
        throw new GapupAuthError(
          "GAPUP_API_KEY environment variable required. Get a free tier key (100 calls/mo) at https://hub.gapup.io/agents-api/onboard"
        );
      }
    
      const res = await fetch(`${HUB_BASE_URL}/api/agent/${slug}`, {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
          "X-Api-Key": apiKey,
          "Accept": "application/json",
          "User-Agent": "@gapup/mcp-knowledge/0.1.0",
        },
        body: JSON.stringify(input),
        signal,
      });
    
      if (res.status === 401) {
        throw new GapupAuthError(
          "Invalid or missing GAPUP_API_KEY. Verify your key at https://hub.gapup.io/agents-api/onboard"
        );
      }
    
      if (res.status === 402) {
        const body = await res.text().catch(() => "");
        throw new GapupAuthError(
          `Free tier quota exhausted or paid auth required. Upgrade at https://hub.gapup.io/agents-api (received 402: ${body.slice(0, 120)})`
        );
      }
    
      if (res.status === 404) {
        throw new GapupApiError(
          404,
          `Endpoint '${slug}' not found — check GAPUP_API_BASE_URL or update the package (npm update @gapup/mcp-knowledge)`
        );
      }
    
      if (res.status === 429) {
        const retryAfter = res.headers.get("Retry-After");
        const retryMsg = retryAfter ? ` Retry after ${retryAfter} seconds.` : "";
        const body = await res.text().catch(() => "");
        throw new GapupApiError(
          429,
          `Rate limit exceeded.${retryMsg} Upgrade your plan at https://hub.gapup.io/agents-api (received: ${body.slice(0, 100)})`
        );
      }
    
      if (!res.ok) {
        const body = await res.text().catch(() => "");
        throw new GapupApiError(res.status, body);
      }
    
      return res.json();
    }
Behavior4/5

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral context such as generating a report with specific components (e.g., severity scores, quantified recommendations) and the fact that it is delivered by an AI CMO. However, it does not disclose any potential delays or data freshness concerns.

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 a single paragraph that efficiently conveys the tool's purpose, outputs, usage context, and inputs. It is front-loaded with the core output description. While clear, it could be slightly more structured (e.g., bullet points) for easier scanning, but it is appropriately sized.

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

Completeness5/5

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

Given the complexity (nested objects, optional focus, array of competitors) and the presence of an output schema, the description is complete. It covers inputs, specific outputs, use cases, and even the authoring persona (Manue, the AI CMO). No additional information seems necessary for an AI agent to use this tool correctly.

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

Parameters5/5

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

Schema description coverage is 100% with clear descriptions for selfCompany, competitors, and focus. The description reinforces these inputs, adding detail such as requiring a one-paragraph pitch and a URL for competitors, and noting that focus is optional. This adds value beyond the schema.

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

Purpose5/5

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

The description specifies the tool generates a board-ready competitive intelligence report with specific outputs like recent competitor moves, severity scores, pricing radar, recommendations, and a presenter script. This clearly differentiates it from sibling tools (e.g., carbon_footprint_calculator, trend_watcher).

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

Usage Guidelines4/5

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

The description explicitly states when to use the tool: 'when the user wants to analyse, benchmark or track competitors, or needs a competitive briefing before a strategic decision.' It provides clear context but lacks explicit guidance on when not to use it or mention of alternatives.

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/getgapup/gapup-mcp'

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