Skip to main content
Glama
phxdev1

People Data Labs MCP Server

search_skills

Search for skills using SQL-like queries to match specific criteria and retrieve targeted results, with support for specifying the number of outputs (up to 100).

Instructions

Search for skills matching specific criteria

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesSQL-like query to search for skills
sizeNoNumber of results to return (max 100)

Implementation Reference

  • Core handler function for search_skills (and other search tools). Validates input, makes API call to People Data Labs `/skill/search` endpoint with SQL query, and returns the JSON response.
    private async handleSearch(dataType: string, args: any) {
      if (!isValidSearchArgs(args)) {
        throw new McpError(
          ErrorCode.InvalidParams,
          `Invalid search parameters. Must provide a query string.`
        );
      }
    
      const params: Record<string, any> = {
        sql: args.query,
        size: args.size || 10,
      };
    
      const response = await pdlApi.get(`/${dataType}/search`, { params });
    
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify(response.data, null, 2),
          },
        ],
      };
    }
  • JSON Schema definition and tool metadata for the search_skills tool, registered in the MCP tools list.
    {
      name: 'search_skills',
      description: 'Search for skills matching specific criteria',
      inputSchema: {
        type: 'object',
        properties: {
          query: {
            type: 'string',
            description: 'SQL-like query to search for skills',
          },
          size: {
            type: 'number',
            description: 'Number of results to return (max 100)',
            minimum: 1,
            maximum: 100,
          },
        },
        required: ['query'],
      },
    },
  • src/index.ts:421-423 (registration)
    Switch case registration/dispatch for handling incoming calls to the search_skills tool by invoking handleSearch with dataType 'skill'.
    // Skill API handlers
    case 'search_skills':
      return await this.handleSearch('skill', request.params.arguments);
  • Runtime input validation type guard for search tool arguments, including search_skills.
    const isValidSearchArgs = (args: any): args is {
      query: string;
      size?: number;
    } => {
      return typeof args === 'object' &&
             args !== null &&
             typeof args.query === 'string' &&
             (args.size === undefined || (typeof args.size === 'number' && args.size > 0 && args.size <= 100));
    };
  • MCP server setup that registers all tools, including search_skills, via ListToolsRequestSchema handler.
    this.server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        // Person API tools
        {
          name: 'enrich_person',
          description: 'Enrich a person profile with additional data from People Data Labs',
          inputSchema: {
            type: 'object',
            properties: {
              email: {
                type: 'string',
                description: 'Email address of the person',
              },
              phone: {
                type: 'string',
                description: 'Phone number of the person',
              },
              name: {
                type: 'string',
                description: 'Full name of the person',
              },
              profile: {
                type: 'array',
                items: {
                  type: 'string'
                },
                description: 'Social media profile URLs of the person',
              },
              location: {
                type: 'string',
                description: 'Location of the person (city, state, country)',
              },
              company: {
                type: 'string',
                description: 'Company name where the person works',
              },
              title: {
                type: 'string',
                description: 'Job title of the person',
              },
              min_likelihood: {
                type: 'number',
                description: 'Minimum likelihood score (0-1) for the match',
                minimum: 0,
                maximum: 1,
              },
            },
            anyOf: [
              { required: ['email'] },
              { required: ['phone'] },
              { required: ['name'] },
              { required: ['profile'] },
            ],
          },
        },
        {
          name: 'search_people',
          description: 'Search for people matching specific criteria',
          inputSchema: {
            type: 'object',
            properties: {
              query: {
                type: 'string',
                description: 'SQL-like query to search for people',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['query'],
          },
        },
        {
          name: 'bulk_person_enrich',
          description: 'Enrich multiple person profiles in a single request',
          inputSchema: {
            type: 'object',
            properties: {
              requests: {
                type: 'array',
                items: {
                  type: 'object',
                  properties: {
                    params: {
                      type: 'object',
                      description: 'Parameters for person enrichment',
                    },
                  },
                  required: ['params'],
                },
                description: 'Array of person enrichment requests',
              },
            },
            required: ['requests'],
          },
        },
        
        // Company API tools
        {
          name: 'enrich_company',
          description: 'Enrich a company profile with additional data',
          inputSchema: {
            type: 'object',
            properties: {
              name: {
                type: 'string',
                description: 'Name of the company',
              },
              website: {
                type: 'string',
                description: 'Website of the company',
              },
              profile: {
                type: 'array',
                items: {
                  type: 'string'
                },
                description: 'Social media profile URLs of the company',
              },
              ticker: {
                type: 'string',
                description: 'Stock ticker symbol of the company',
              },
            },
            anyOf: [
              { required: ['name'] },
              { required: ['website'] },
              { required: ['profile'] },
              { required: ['ticker'] },
            ],
          },
        },
        {
          name: 'search_companies',
          description: 'Search for companies matching specific criteria',
          inputSchema: {
            type: 'object',
            properties: {
              query: {
                type: 'string',
                description: 'SQL-like query to search for companies',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['query'],
          },
        },
        
        // School API tools
        {
          name: 'search_schools',
          description: 'Search for schools matching specific criteria',
          inputSchema: {
            type: 'object',
            properties: {
              query: {
                type: 'string',
                description: 'SQL-like query to search for schools',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['query'],
          },
        },
        
        // Location API tools
        {
          name: 'search_locations',
          description: 'Search for locations matching specific criteria',
          inputSchema: {
            type: 'object',
            properties: {
              query: {
                type: 'string',
                description: 'SQL-like query to search for locations',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['query'],
          },
        },
        
        // Job Title API tools
        {
          name: 'search_job_titles',
          description: 'Search for job titles matching specific criteria',
          inputSchema: {
            type: 'object',
            properties: {
              query: {
                type: 'string',
                description: 'SQL-like query to search for job titles',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['query'],
          },
        },
        
        // Skill API tools
        {
          name: 'search_skills',
          description: 'Search for skills matching specific criteria',
          inputSchema: {
            type: 'object',
            properties: {
              query: {
                type: 'string',
                description: 'SQL-like query to search for skills',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['query'],
          },
        },
        
        // Autocomplete API tools
        {
          name: 'autocomplete',
          description: 'Get autocomplete suggestions for a partial query',
          inputSchema: {
            type: 'object',
            properties: {
              field: {
                type: 'string',
                description: 'Field to autocomplete (company, school, title, skill, location)',
                enum: ['company', 'school', 'title', 'skill', 'location'],
              },
              text: {
                type: 'string',
                description: 'Partial text to autocomplete',
              },
              size: {
                type: 'number',
                description: 'Number of results to return (max 100)',
                minimum: 1,
                maximum: 100,
              },
            },
            required: ['field', 'text'],
          },
        },
      ],
    }));
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'search' but doesn't specify whether this is a read-only operation, if it requires authentication, rate limits, or what the output format might be. It lacks critical behavioral context for a search tool.

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?

The description is a single, efficient sentence with no wasted words. It's appropriately sized for a simple search tool and front-loads the core action ('search for skills').

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

Completeness2/5

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

Given no annotations and no output schema, the description is incomplete. It doesn't explain what 'skills' are in this context, how results are returned, or any behavioral traits. For a search tool with two parameters, it lacks sufficient context for effective agent use.

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?

The input schema has 100% description coverage, clearly documenting the 'query' as a SQL-like string and 'size' with numeric constraints. The description adds no additional parameter semantics beyond what's in the schema, so it meets the baseline for high schema coverage without compensating value.

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

Purpose3/5

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

The description 'Search for skills matching specific criteria' states a clear verb ('search') and resource ('skills'), but it's vague about what 'skills' means in this context and doesn't distinguish from sibling tools like search_people or search_companies. It provides basic purpose but lacks specificity about the domain or scope.

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

Usage Guidelines2/5

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

The description offers no guidance on when to use this tool versus alternatives like search_people or search_companies, nor does it mention prerequisites or exclusions. It's a generic statement that leaves the agent to infer usage from the tool name alone.

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

Related 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/phxdev1/peopledatalabs-mcp'

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