Skip to main content
Glama
kindrat86

mcp-deal-flow-signal

by kindrat86
OverviewSchemaRelated ServersScoreDiscussions(2)
JavaScript
Remote

Get Deep Signal (paid)

get_deep_signal
Read-onlyIdempotent

Generate a deep-dive signal on a startup with scored growth, velocity, novelty, sector percentile, comparable companies, and an investment thesis.

Instructions

PAID per-request tool — costs 1 credit per match. Returns a deeply enriched signal profile for a single tracked startup, beyond what the free get_startup_signal returns: scored breakdown (velocity / growth / novelty / composite), in-sector rank and percentile, comparable startups, multi-period history, and a plain-English investment thesis.

PRICING:

  • 100 credits = €19 one-time (€0.19 per call). Buy at https://signals.gitdealflow.com/agents/credits

  • 1 credit consumed only on a successful match. found: false is FREE.

  • Credits never expire.

AUTHENTICATION:

  • Set environment variable GITDEALFLOW_API_KEY to the v2 key delivered in the credit-pack welcome email (format: gdf_v2.cus_xxx.<hmac>). The server reads it once on each call.

  • Without a key, this tool returns an error pointing at the purchase URL — the other 6 free tools are unaffected.

WHEN TO USE (vs free get_startup_signal):

  • You already know the startup name and need scored / percentile / comparables / thesis output for a memo.

  • The agent's principal will read or quote the thesis line.

  • You're processing a watchlist programmatically and need a numeric composite score for ranking.

DO NOT USE FOR:

  • Discovery — call free get_trending_startups or search_startups_by_sector first.

  • Bulk scoring an unknown universe — that's not yet shipped; submit feedback via signal@gitdealflow.com.

  • Methodology questions — call free get_methodology.

PARAMETERS: name (required, string, 1-100 chars) — Startup display name OR GitHub org name. Case-insensitive matching, same as the free lookup.

RETURNS: { found: boolean, name, sector, stage, geography, signalType, scores: { velocity, growth, novelty, composite }, rank: { inSector, sectorTotal, sectorPercentile }, thesis, comparables[], history[], links, balance, charged, citation }. balance is the remaining credit count after this call. charged is 0 (miss) or 1 (hit).

ERRORS: 401 = invalid/missing key; 402 = insufficient credits (top up at the purchase URL); 400 = malformed request.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesStartup name or GitHub org name. Case-insensitive; punctuation and whitespace are ignored.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
foundYes
nameNo
sectorNo
stageNo
geographyNo
signalTypeNo
scoresNo
rankNo
thesisNo
comparablesNo
balanceNo
chargedNo
citationNo

Implementation Reference

  • src/server.ts:618-716 (registration)
    Registration of the 'get_deep_signal' tool in the TOOLS array, with input/output schemas, description (paid tool), and annotations.
    {
  name: "get_deep_signal",
  title: "Get Deep Signal (paid)",
  description: [
    "PAID per-request tool — costs 1 credit per match. Returns a deeply enriched signal profile for a single tracked startup, beyond what the free `get_startup_signal` returns: scored breakdown (velocity / growth / novelty / composite), in-sector rank and percentile, comparable startups, multi-period history, and a plain-English investment thesis.",
    "",
    "PRICING:",
    "- 100 credits = €19 one-time (€0.19 per call). Buy at " +
      CREDITS_PURCHASE_URL,
    "- 1 credit consumed only on a successful match. `found: false` is FREE.",
    "- Credits never expire.",
    "",
    "AUTHENTICATION:",
    "- Set environment variable `GITDEALFLOW_API_KEY` to the v2 key delivered in the credit-pack welcome email (format: `gdf_v2.cus_xxx.<hmac>`). The server reads it once on each call.",
    "- Without a key, this tool returns an error pointing at the purchase URL — the other 6 free tools are unaffected.",
    "",
    "WHEN TO USE (vs free `get_startup_signal`):",
    "- You already know the startup name and need scored / percentile / comparables / thesis output for a memo.",
    "- The agent's principal will read or quote the thesis line.",
    "- You're processing a watchlist programmatically and need a numeric composite score for ranking.",
    "",
    "DO NOT USE FOR:",
    "- Discovery — call free `get_trending_startups` or `search_startups_by_sector` first.",
    "- Bulk scoring an unknown universe — that's not yet shipped; submit feedback via signal@gitdealflow.com.",
    "- Methodology questions — call free `get_methodology`.",
    "",
    "PARAMETERS: `name` (required, string, 1-100 chars) — Startup display name OR GitHub org name. Case-insensitive matching, same as the free lookup.",
    "",
    "RETURNS: `{ found: boolean, name, sector, stage, geography, signalType, scores: { velocity, growth, novelty, composite }, rank: { inSector, sectorTotal, sectorPercentile }, thesis, comparables[], history[], links, balance, charged, citation }`. `balance` is the remaining credit count after this call. `charged` is 0 (miss) or 1 (hit).",
    "",
    "ERRORS: 401 = invalid/missing key; 402 = insufficient credits (top up at the purchase URL); 400 = malformed request.",
  ].join("\n"),
  inputSchema: {
    type: "object" as const,
    properties: {
      name: {
        type: "string",
        description:
          "Startup name or GitHub org name. Case-insensitive; punctuation and whitespace are ignored.",
        minLength: 1,
        maxLength: 100,
        examples: ["Roboflow", "SkyPilot", "Supabase"],
      },
    },
    required: ["name"],
    additionalProperties: false,
  },
  outputSchema: {
    type: "object" as const,
    properties: {
      found: { type: "boolean" },
      name: { type: "string" },
      sector: { type: "string" },
      stage: { type: "string" },
      geography: { type: "string" },
      signalType: { type: "string" },
      scores: {
        type: "object",
        properties: {
          velocity: { type: "integer", minimum: 0, maximum: 100 },
          growth: { type: "integer", minimum: 0, maximum: 100 },
          novelty: { type: "integer", minimum: 0, maximum: 100 },
          composite: { type: "integer", minimum: 0, maximum: 100 },
        },
      },
      rank: {
        type: "object",
        properties: {
          inSector: { type: "integer" },
          sectorTotal: { type: "integer" },
          sectorPercentile: { type: "integer", minimum: 0, maximum: 100 },
        },
      },
      thesis: { type: "string" },
      comparables: {
        type: "array",
        items: {
          type: "object",
          properties: {
            name: { type: "string" },
            commitVelocityChange: { type: "string" },
            signalType: { type: "string" },
          },
        },
      },
      balance: { type: "integer", minimum: 0 },
      charged: { type: "integer", minimum: 0, maximum: 1 },
      citation: { type: "string" },
    },
    required: ["found"],
  },
  annotations: {
    title: "Get Deep Signal (paid)",
    readOnlyHint: true,
    destructiveHint: false,
    idempotentHint: true,
    openWorldHint: true,
  },
},
  • src/server.ts:650-715 (schema)
    Input schema (requires 'name' string) and output schema (found, scores, rank, thesis, comparables, balance, charged, citation) for get_deep_signal.
    inputSchema: {
  type: "object" as const,
  properties: {
    name: {
      type: "string",
      description:
        "Startup name or GitHub org name. Case-insensitive; punctuation and whitespace are ignored.",
      minLength: 1,
      maxLength: 100,
      examples: ["Roboflow", "SkyPilot", "Supabase"],
    },
  },
  required: ["name"],
  additionalProperties: false,
},
outputSchema: {
  type: "object" as const,
  properties: {
    found: { type: "boolean" },
    name: { type: "string" },
    sector: { type: "string" },
    stage: { type: "string" },
    geography: { type: "string" },
    signalType: { type: "string" },
    scores: {
      type: "object",
      properties: {
        velocity: { type: "integer", minimum: 0, maximum: 100 },
        growth: { type: "integer", minimum: 0, maximum: 100 },
        novelty: { type: "integer", minimum: 0, maximum: 100 },
        composite: { type: "integer", minimum: 0, maximum: 100 },
      },
    },
    rank: {
      type: "object",
      properties: {
        inSector: { type: "integer" },
        sectorTotal: { type: "integer" },
        sectorPercentile: { type: "integer", minimum: 0, maximum: 100 },
      },
    },
    thesis: { type: "string" },
    comparables: {
      type: "array",
      items: {
        type: "object",
        properties: {
          name: { type: "string" },
          commitVelocityChange: { type: "string" },
          signalType: { type: "string" },
        },
      },
    },
    balance: { type: "integer", minimum: 0 },
    charged: { type: "integer", minimum: 0, maximum: 1 },
    citation: { type: "string" },
  },
  required: ["found"],
},
annotations: {
  title: "Get Deep Signal (paid)",
  readOnlyHint: true,
  destructiveHint: false,
  idempotentHint: true,
  openWorldHint: true,
},
  • src/server.ts:1338-1467 (handler)
    Handler for get_deep_signal: validates name, checks GITDEALFLOW_API_KEY env var, POSTs to /api/agent/deep-signal with Bearer auth, handles 401/402/not-found errors, formats response with scores, thesis, comparables, and credit balance.
    case "get_deep_signal": {
  const inputName = String(
    (request.params.arguments as Record<string, unknown> | undefined)?.name ?? ""
  ).trim();
  if (!inputName || inputName.length > 100) {
    throw new Error("Invalid name. Must be 1-100 chars.");
  }
  const apiKey = process.env.GITDEALFLOW_API_KEY?.trim();
  if (!apiKey) {
    return {
      content: [
        {
          type: "text" as const,
          text: [
            `get_deep_signal is paid (€0.19/call, 100 credits = €19).`,
            ``,
            `Set the GITDEALFLOW_API_KEY environment variable to the key from your credit-pack welcome email.`,
            ``,
            `Buy credits: ${CREDITS_PURCHASE_URL}`,
            ``,
            `The 6 free tools (get_trending_startups, search_startups_by_sector, get_startup_signal, get_signals_summary, get_scout_receipts, get_methodology) are unaffected.`,
          ].join("\n"),
        },
      ],
      structuredContent: {
        found: false,
        error: "missing_api_key",
        purchaseUrl: CREDITS_PURCHASE_URL,
      },
      isError: true,
    };
  }

  const res = await fetch(`${BASE_URL}/api/agent/deep-signal`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "User-Agent": UA,
      Authorization: `Bearer ${apiKey}`,
    },
    body: JSON.stringify({ name: inputName }),
  });

  const data = (await res.json().catch(() => ({}))) as Record<string, unknown>;

  if (res.status === 401) {
    return {
      content: [
        {
          type: "text" as const,
          text: `API key did not validate. Re-check GITDEALFLOW_API_KEY against the welcome email, or buy a fresh key at ${CREDITS_PURCHASE_URL}.`,
        },
      ],
      structuredContent: data,
      isError: true,
    };
  }
  if (res.status === 402) {
    const balance = typeof data.balance === "number" ? data.balance : 0;
    return {
      content: [
        {
          type: "text" as const,
          text: `Out of credits (balance: ${balance}). Buy 100 more for €19 at ${CREDITS_PURCHASE_URL}.`,
        },
      ],
      structuredContent: data,
      isError: true,
    };
  }
  if (!res.ok) {
    throw new Error(`HTTP ${res.status} from /api/agent/deep-signal`);
  }

  if (data.found === false) {
    const suggestion =
      typeof data.suggestion === "string"
        ? data.suggestion
        : "Try the GitHub org name exactly, or call get_trending_startups to browse.";
    return {
      content: [
        {
          type: "text" as const,
          text: `"${inputName}" is not in the tracked universe. ${suggestion}\n\n(0 credits charged for misses.)`,
        },
      ],
      structuredContent: data,
    };
  }

  const text = (() => {
    const lines: string[] = [];
    lines.push(`${data.name as string} — Deep Signal (paid)`);
    lines.push("");
    const scores = data.scores as Record<string, number> | undefined;
    const rank = data.rank as Record<string, number> | undefined;
    if (scores) {
      lines.push(
        `Composite score: ${scores.composite}/100  ·  Velocity ${scores.velocity}  ·  Growth ${scores.growth}  ·  Novelty ${scores.novelty}`
      );
    }
    if (rank) {
      lines.push(
        `Sector rank: #${rank.inSector} of ${rank.sectorTotal} (${rank.sectorPercentile}th percentile in ${data.sector})`
      );
    }
    lines.push("");
    if (typeof data.thesis === "string") lines.push(`Thesis: ${data.thesis}`);
    const comps = data.comparables as Array<Record<string, unknown>> | undefined;
    if (comps && comps.length > 0) {
      lines.push("");
      lines.push("Comparables in sector:");
      for (const c of comps) {
        lines.push(`  - ${c.name} (${c.commitVelocityChange}, ${c.signalType})`);
      }
    }
    lines.push("");
    lines.push(`Credits remaining: ${data.balance ?? "?"}  ·  Charged: ${data.charged ?? 1}`);
    lines.push("");
    if (typeof data.citation === "string") lines.push(`Citation: ${data.citation}`);
    lines.push("");
    lines.push(FOOTER);
    return lines.join("\n");
  })();

  return {
    content: [{ type: "text" as const, text }],
    structuredContent: data,
  };
}

Tool Definition Quality

A4.7/5.0
Behavior5/5

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

Description adds significant behavioral context beyond annotations: pricing, credit consumption only on success, authentication requirements, error codes, and free vs paid behavior (found: false is free). No contradiction with annotations.

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?

Well-organized with clear sections (PRICING, AUTHENTICATION, WHEN TO USE, etc.). Front-loaded with core purpose. Every sentence is informative and non-redundant.

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?

Comprehensive for a paid tool with complex behavior. Covers pricing, authentication, return fields (despite output schema existing), error handling, and usage guidelines. Leaves no critical gaps.

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?

Input schema already covers the parameter fully with description, constraints, and examples (100% coverage). Description only reiterates case-insensitivity and matching logic, adding marginal value.

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 clearly states the tool returns a deeply enriched signal profile beyond the free `get_startup_signal`, listing specific outputs (score, rank, comparables, thesis). It distinguishes itself from siblings by name and scope.

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

Usage Guidelines5/5

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

Explicitly provides 'WHEN TO USE' and 'DO NOT USE FOR' sections with concrete alternatives (e.g., free tools for discovery, methodology). Guides the agent on appropriate invocation context.

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/kindrat86/mcp-deal-flow-signal'

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