Search Startups by Sector

Instructions

Implementation Reference

• src/server.ts:299-379 (registration)

  Registration of the 'search_startups_by_sector' tool in the TOOLS array, including its name, description, inputSchema (with sector slug enum), outputSchema, and annotations.

  {
    name: "search_startups_by_sector",
    title: "Search Startups by Sector",
    description: [
      "Return every tracked startup within one of 20 supported sectors, ranked by engineering acceleration for the current reporting period.",
      "",
      "WHEN TO USE:",
      "- The user names a specific vertical: 'show me AI/ML startups', 'who's moving in fintech?', 'cybersecurity deal flow', 'climate-tech picks'.",
      "- You need a focused list for a thesis-driven investor or a sector report.",
      "- You're comparing momentum inside a defined market before a sourcing cycle.",
      "",
      "DO NOT USE FOR:",
      "- Cross-sector discovery — call `get_trending_startups` for the top-20 across all sectors.",
      "- Looking up a named company — call `get_startup_signal(name)`.",
      "- Discovering which sectors exist or how many startups are tracked overall — call `get_signals_summary` (it returns live counts and URLs).",
      "- Multi-sector filtering — the tool accepts exactly one slug per call; issue parallel calls if you need several.",
      "",
      "BEHAVIOR:",
      "- Read-only, idempotent, no side effects.",
      "- Deterministic within a 7-day window: dataset refreshes every Monday ~09:00 UTC.",
      "- No authentication required. No rate limit enforced by this server.",
      "- Returns between 5 and 30 startups per sector depending on open-source density. Dense: ai-ml, developer-tools, data-infrastructure. Sparse: legal-tech, proptech, agtech.",
      "- On unknown sector slug: returns `isError: true` with the full list of valid slugs in `structuredContent.availableSectors` so the agent can retry with a correct value.",
      "- On upstream failure: returns `isError: true` with the HTTP status.",
      "- Open-world: the tracked universe changes week to week.",
      "",
      "PARAMETERS:",
      "- `sector` (required, string) — MUST be one of the 20 enumerated slugs in `inputSchema.properties.sector.enum`. Map fuzzy user input BEFORE calling: 'AI' / 'artificial intelligence' / 'ML' → 'ai-ml'; 'crypto' / 'blockchain' → 'web3'; 'cyber' / 'infosec' / 'security' → 'cybersecurity'; 'SaaS' → 'enterprise-saas'; 'devtools' / 'developer experience' → 'developer-tools'; 'climate' / 'clean energy' / 'cleantech' → 'climate-tech'; 'biotech' / 'health' / 'medtech' → 'healthcare'; 'data' / 'databases' → 'data-infrastructure'; 'real estate' → 'proptech'; 'agriculture' → 'agtech'; 'space' → 'space-tech'; 'games' → 'gaming'; 'community' / 'social' → 'social-community'; 'logistics' → 'supply-chain'; 'law' / 'legal' → 'legal-tech'; 'recruiting' / 'HR' → 'hr-tech'; 'learning' / 'education' → 'edtech'; 'commerce' / 'retail infra' → 'ecommerce-infrastructure'; 'hardware' / 'drones' → 'robotics'. If no mapping is clear, call `get_signals_summary` and ask the user to pick.",
      "",
      "RETURNS: `{ sector: {slug, name, description, url}, period, startupCount, startups[], citation }`. Each startup row contains rank, name, sector, stage, geography, commitVelocity14d, commitVelocityChange, contributors, contributorGrowth, newRepos, signalType, description, githubUrl, websiteUrl (when known), linkedinUrl (when known), profileUrl.",
      "",
      "TYPICAL WORKFLOW: `search_startups_by_sector('fintech')` → pick a name → `get_startup_signal(name)` → `get_methodology` if the user asks what the signal type means.",
      "",
      "LIMITATIONS: One sector slug per call; no free-text sector search. For cross-sector views use `get_trending_startups`. No historical series — each call is the latest weekly snapshot only.",
    ].join("\n"),
    inputSchema: {
      type: "object" as const,
      properties: {
        sector: {
          type: "string",
          description:
            "Sector slug. Must be one of the 20 supported values. Map fuzzy user input to the closest slug (e.g. 'AI' → 'ai-ml', 'crypto' → 'web3', 'cyber' → 'cybersecurity', 'SaaS' → 'enterprise-saas').",
          enum: [...SECTOR_SLUGS],
          examples: ["ai-ml", "fintech", "cybersecurity", "developer-tools"],
        },
      },
      required: ["sector"],
      additionalProperties: false,
    },
    outputSchema: {
      type: "object" as const,
      properties: {
        sector: {
          type: "object",
          properties: {
            slug: { type: "string" },
            name: { type: "string" },
            description: { type: "string" },
            url: { type: "string", format: "uri" },
          },
          required: ["slug", "name"],
        },
        period: { type: "string" },
        startupCount: { type: "integer" },
        startups: {
          type: "array",
          description: "Startups within the sector, ranked by engineering acceleration.",
          items: STARTUP_ITEM_SCHEMA,
        },
        citation: { type: "string" },
      },
      required: ["sector", "period", "startupCount", "startups", "citation"],
    },
    annotations: {
      title: "Search Startups by Sector",
      readOnlyHint: true,
      destructiveHint: false,
      idempotentHint: true,
      openWorldHint: true,
    },
  },

• src/server.ts:334-371 (schema)

  Input and output schema for search_startups_by_sector. Input requires a 'sector' string (one of 20 slugs). Output returns sector info, period, startupCount, startups array, and citation.

  inputSchema: {
    type: "object" as const,
    properties: {
      sector: {
        type: "string",
        description:
          "Sector slug. Must be one of the 20 supported values. Map fuzzy user input to the closest slug (e.g. 'AI' → 'ai-ml', 'crypto' → 'web3', 'cyber' → 'cybersecurity', 'SaaS' → 'enterprise-saas').",
        enum: [...SECTOR_SLUGS],
        examples: ["ai-ml", "fintech", "cybersecurity", "developer-tools"],
      },
    },
    required: ["sector"],
    additionalProperties: false,
  },
  outputSchema: {
    type: "object" as const,
    properties: {
      sector: {
        type: "object",
        properties: {
          slug: { type: "string" },
          name: { type: "string" },
          description: { type: "string" },
          url: { type: "string", format: "uri" },
        },
        required: ["slug", "name"],
      },
      period: { type: "string" },
      startupCount: { type: "integer" },
      startups: {
        type: "array",
        description: "Startups within the sector, ranked by engineering acceleration.",
        items: STARTUP_ITEM_SCHEMA,
      },
      citation: { type: "string" },
    },
    required: ["sector", "period", "startupCount", "startups", "citation"],
  },

• src/server.ts:1032-1101 (handler)

  Handler logic for 'search_startups_by_sector' inside the CallToolRequestSchema switch-case. Fetches /api/signals.json, finds the sector by slug, returns error if not found, otherwise maps startups with rank, name, sector, stage, geography, commit velocity, contributors, signalType, etc.

  case "search_startups_by_sector": {
    const sectorSlug = (args as { sector: string }).sector;
    const data = (await fetchJSON("/api/signals.json")) as unknown as SignalsData;
    const sector = data.sectors.find((s) => s.slug === sectorSlug);
    if (!sector) {
      const available = data.sectors.map((s) => s.slug).join(", ");
      return {
        content: [
          {
            type: "text" as const,
            text: `Sector "${sectorSlug}" not found. Available: ${available}`,
          },
        ],
        structuredContent: {
          sector: { slug: sectorSlug, name: "" },
          period: data.meta.period.name,
          startupCount: 0,
          startups: [],
          citation: data.meta.citation,
          error: `Sector "${sectorSlug}" not found.`,
          availableSectors: data.sectors.map((s) => s.slug),
        },
        isError: true,
      };
    }
  
    const structured = {
      sector: {
        slug: sector.slug,
        name: sector.name,
        description: sector.description,
        url: sector.url,
      },
      period: data.meta.period.name,
      startupCount: sector.startups.length,
      startups: sector.startups.map((s, i) => ({
        rank: i + 1,
        name: s.name,
        sector: sector.name,
        stage: s.stage,
        geography: s.geography,
        commitVelocity14d: s.commitVelocity14d,
        commitVelocityChange: s.commitVelocityChange,
        contributors: s.contributors,
        contributorGrowth: s.contributorGrowth,
        newRepos: s.newRepos,
        signalType: s.signalType,
        description: s.description,
        githubUrl: s.githubUrl,
        ...(s.websiteUrl ? { websiteUrl: s.websiteUrl } : {}),
        ...(s.linkedinUrl ? { linkedinUrl: s.linkedinUrl } : {}),
        profileUrl: s.profileUrl,
      })),
      citation: data.meta.citation,
    };
  
    const lines = sector.startups.map(
      (s, i) =>
        `${i + 1}. ${s.name} — ${s.commitVelocityChange} velocity change, ${s.contributors} contributors, signal: ${s.signalType}\n   ${s.description || "(no description)"}`
    );
    return {
      content: [
        {
          type: "text" as const,
          text: `${sector.name} Startups (${data.meta.period.name})\n${sector.description}\n${sector.startups.length} startups tracked\n\n${lines.join("\n\n")}\n\nSource: ${BASE_URL}/startups-to-watch/${sectorSlug}-q2-2026\nCitation: ${data.meta.citation}\n\n${FOOTER}`,
        },
      ],
      structuredContent: structured,
    };
  }

• src/server.ts:140-161 (helper)

  SECTOR_SLUGS constant array defining the 20 supported sector slugs used in the input schema enum and validation.

  const SECTOR_SLUGS = [
    "ai-ml",
    "fintech",
    "cybersecurity",
    "developer-tools",
    "healthcare",
    "climate-tech",
    "enterprise-saas",
    "data-infrastructure",
    "web3",
    "robotics",
    "edtech",
    "ecommerce-infrastructure",
    "supply-chain",
    "legal-tech",
    "hr-tech",
    "proptech",
    "agtech",
    "gaming",
    "space-tech",
    "social-community",
  ] as const;

• src/server.ts:99-123 (helper)

  Startup and Sector interfaces used as data structures for the handler logic.

  interface Startup {
    name: string;
    description: string;
    stage: string;
    geography: string;
    commitVelocity14d: number;
    commitVelocityChange: string;
    contributors: number;
    contributorGrowth: string;
    newRepos: number;
    signalType: string;
    githubUrl: string;
    websiteUrl?: string;
    linkedinUrl?: string;
    profileUrl?: string;
  }
  
  interface Sector {
    slug: string;
    name: string;
    description: string;
    startupCount: number;
    startups: Startup[];
    url: string;
  }