Skip to main content
Glama
Fund-z

FundzWatch MCP Server

get_scored_leads

Retrieve AI-scored sales leads tailored to your ideal customer profile. Filter by buyer intent score, buying stage, and industry to prioritize high-intent prospects with recommended outreach strategies.

Instructions

Get AI-scored sales leads based on your ICP (Ideal Customer Profile). Returns companies with recent business events scored by AI for buyer intent, buying stage, and recommended outreach strategy.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
min_scoreNoMinimum buyer intent score (0-100). Default: 0
max_resultsNoMax leads to return (1-50). Default: 25
buying_stagesNoFilter by buying stage: 'Active Evaluation', 'Decision', 'Research', 'Awareness'
industriesNoFilter by industry (e.g., ['SaaS', 'HealthTech', 'FinTech'])

Implementation Reference

  • The handler function for the 'get_scored_leads' tool. It calls the API endpoint /signals with parameters (min_score, max_results, buying_stages, industries), processes the response, and formats the results into a readable text output.
    case "get_scored_leads": {
      const data = await apiRequest("POST", "/signals", {
        min_score: (args as any).min_score ?? 0,
        max_results: (args as any).max_results ?? 25,
        buying_stages: (args as any).buying_stages,
        industries: (args as any).industries,
      });
      const leads = data.signals || [];
      if (leads.length === 0) {
        return textResult("No scored leads found for your current ICP. Leads are generated daily by the AI scoring engine.");
      }
      const summary = leads
        .map(
          (lead: any, i: number) =>
            `${i + 1}. **${lead.company_name}** (Score: ${lead.score}/100)\n` +
            `   Stage: ${lead.buying_stage} | Priority: ${lead.priority}\n` +
            `   Pain Point: ${lead.pain_point}\n` +
            `   Outreach: ${lead.outreach_angle}\n` +
            `   Action: ${lead.recommended_action}\n` +
            (lead.domain ? `   Domain: ${lead.domain}\n` : "") +
            (lead.industries?.length ? `   Industries: ${lead.industries.join(", ")}\n` : "")
        )
        .join("\n");
      return textResult(`Found ${data.signals_found} scored leads (showing ${leads.length}):\n\n${summary}`);
    }
  • Input schema for 'get_scored_leads' tool, defining parameters: min_score (number), max_results (number), buying_stages (array of strings), and industries (array of strings).
    inputSchema: {
      type: "object" as const,
      properties: {
        min_score: { type: "number", description: "Minimum buyer intent score (0-100). Default: 0" },
        max_results: { type: "number", description: "Max leads to return (1-50). Default: 25" },
        buying_stages: {
          type: "array",
          items: { type: "string" },
          description: "Filter by buying stage: 'Active Evaluation', 'Decision', 'Research', 'Awareness'",
        },
        industries: {
          type: "array",
          items: { type: "string" },
          description: "Filter by industry (e.g., ['SaaS', 'HealthTech', 'FinTech'])",
        },
      },
    },
  • src/index.ts:73-96 (registration)
    Registration of the 'get_scored_leads' tool within the ListToolsRequestSchema handler, including its name and description.
    {
      name: "get_scored_leads",
      description:
        "Get AI-scored sales leads based on your ICP (Ideal Customer Profile). " +
        "Returns companies with recent business events scored by AI for buyer intent, " +
        "buying stage, and recommended outreach strategy.",
      inputSchema: {
        type: "object" as const,
        properties: {
          min_score: { type: "number", description: "Minimum buyer intent score (0-100). Default: 0" },
          max_results: { type: "number", description: "Max leads to return (1-50). Default: 25" },
          buying_stages: {
            type: "array",
            items: { type: "string" },
            description: "Filter by buying stage: 'Active Evaluation', 'Decision', 'Research', 'Awareness'",
          },
          industries: {
            type: "array",
            items: { type: "string" },
            description: "Filter by industry (e.g., ['SaaS', 'HealthTech', 'FinTech'])",
          },
        },
      },
    },
  • The apiRequest helper function used by the handler to make authenticated HTTP requests, and the textResult helper used to format the output.
    async function apiRequest(
      method: string,
      path: string,
      params?: Record<string, any>
    ): Promise<any> {
      const apiKey = getApiKey();
      const url = new URL(`${API_BASE}${path}`);
    
      const options: RequestInit = {
        method,
        headers: {
          Authorization: `Bearer ${apiKey}`,
          "Content-Type": "application/json",
          "User-Agent": "fundzwatch-mcp/1.0.1",
        },
      };
    
      if (method === "GET" && params) {
        Object.entries(params).forEach(([key, value]) => {
          if (value !== undefined && value !== null) {
            url.searchParams.append(key, String(value));
          }
        });
      } else if (method !== "GET" && params) {
        options.body = JSON.stringify(params);
      }
    
      const response = await fetch(url.toString(), options);
    
      if (!response.ok) {
        const errBody: any = await response.json().catch(() => ({ message: response.statusText }));
        throw new Error(`API error ${response.status}: ${errBody.message || errBody.error || response.statusText}`);
      }
    
      return response.json();
    }
Behavior4/5

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

With no annotations, the description fully explains the read-only behavior: filtering by score, stage, industry. It discloses it returns pre-scored leads with recent business events, though it omits potential limitations like data freshness or rate limits.

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?

Two concise sentences front-loaded with purpose, then capability details. No filler or redundant phrasing.

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

Completeness3/5

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

No output schema, so the description partially addresses return values (companies with scored events), but lacks specifics on the result structure (e.g., fields per lead). Adequate for basic understanding but not fully self-contained.

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 coverage is 100%, so parameters are already well-described. The description provides no additional semantic detail beyond the schema's domain context (e.g., that scores are AI-generated). Baseline 3 is appropriate.

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 retrieves 'AI-scored sales leads' based on ICP, listing specific outputs (buyer intent, buying stage, outreach strategy). This verb+resource combination distinguishes it from siblings like get_events or get_market_brief.

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 implies use when needing scored leads, but does not specify when alternatives (e.g., get_events, get_market_pulse) are more appropriate. No explicit when-not-to-use or alternative references.

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/Fund-z/fundzwatch-mcp'

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