Skip to main content
Glama
byndcloud

Unofficial Dex CRM MCP Server

by byndcloud

dex_list_contacts

Retrieve and filter contacts from your Dex CRM with criteria like birthdays, job titles, tags, groups, and keep-in-touch frequency. Supports pagination and field selection for targeted contact management.

Instructions

List contacts with advanced filtering, pagination, and field selection. Use 'where' to filter by starred, archived, frequency, birthday, location, job title, tags, groups, and more. Examples: find today's birthdays (where.hasBirthday), contacts with a keep-in-touch frequency (where.hasFrequency), monthly contacts (where.hasFrequency='monthly'), starred contacts (where.isStarred=true).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
takeNoNumber of contacts to return (default varies by API)
skipNoNumber of contacts to skip
cursorNoPagination cursor (UUID) from a previous response
whereNo
includeNo
selectNo

Implementation Reference

  • The handler function for dex_list_contacts, which constructs the request body and calls the dex API endpoint /v1/contacts/filter.
    async (args) => {
      try {
        const body: Record<string, unknown> = {};
    
        if (args.take !== undefined) body.take = args.take;
        if (args.skip !== undefined) body.skip = args.skip;
        if (args.cursor !== undefined) body.cursor = args.cursor;
    
        if (args.where) {
          const w: Record<string, unknown> = {};
          const src = args.where;
          if (src.in !== undefined)                  w.in = src.in;
          if (src.notIn !== undefined)               w.not_in = src.notIn;
          if (src.ignoreMerge !== undefined)          w.ignore_merge = src.ignoreMerge;
          if (src.isStarred !== undefined)            w.is_starred = src.isStarred;
          if (src.isArchived !== undefined)           w.is_archived = src.isArchived;
          if (src.hasLinkedin !== undefined)          w.has_linkedin = src.hasLinkedin;
          if (src.hasSource !== undefined)            w.has_source = src.hasSource;
          if (src.hasName !== undefined)              w.has_name = src.hasName;
          if (src.hasGroups !== undefined)            w.has_groups = src.hasGroups;
          if (src.hasFrequency !== undefined)         w.has_frequency = src.hasFrequency;
          if (src.hasLocation !== undefined)          w.has_location = src.hasLocation;
          if (src.hasJobTitle !== undefined)          w.has_job_title = src.hasJobTitle;
          if (src.hasNeverKeepInTouch !== undefined)  w.has_never_keep_in_touch = src.hasNeverKeepInTouch;
          if (src.hasCreatedAt !== undefined)         w.has_created_at = src.hasCreatedAt;
          if (src.hasUpdatedAt !== undefined)         w.has_updated_at = src.hasUpdatedAt;
          if (src.hasBirthday !== undefined)          w.has_birthday = src.hasBirthday;
          if (src.hasTag !== undefined)               w.has_tag = src.hasTag;
          if (src.hasInteraction !== undefined)       w.has_interaction = src.hasInteraction;
          if (src.hasNextReminder !== undefined)      w.has_next_reminder = src.hasNextReminder;
          body.where = w;
        }
    
        if (args.include) {
          const inc: Record<string, boolean> = {};
          if (args.include.linkedinData !== undefined) inc.linkedin_data = args.include.linkedinData;
          if (args.include.groupsCount !== undefined)  inc.groups_count = args.include.groupsCount;
          body.include = inc;
        }
    
        if (args.select) {
          const sel: Record<string, boolean> = {};
          if (args.select.linkedinData !== undefined) sel.linkedin_data = args.select.linkedinData;
          if (args.select.groupsCount !== undefined)  sel.groups_count = args.select.groupsCount;
          body.select = sel;
        }
    
        const result = await dex.post("/v1/contacts/filter", body);
        return toResult(result);
      } catch (error) {
        return toError(error);
      }
  • Registration of the dex_list_contacts tool using server.tool, including its schema definitions.
    server.tool(
      "dex_list_contacts",
      "List contacts with advanced filtering, pagination, and field selection. " +
        "Use 'where' to filter by starred, archived, frequency, birthday, location, job title, tags, groups, and more. " +
        "Examples: find today's birthdays (where.hasBirthday), contacts with a keep-in-touch frequency (where.hasFrequency), " +
        "monthly contacts (where.hasFrequency='monthly'), starred contacts (where.isStarred=true).",
      {
        take: z.number().min(1).optional().describe("Number of contacts to return (default varies by API)"),
        skip: z.number().min(0).optional().describe("Number of contacts to skip"),
        cursor: z.string().optional().describe("Pagination cursor (UUID) from a previous response"),
        where: z.object({
          in: z.array(z.string()).optional().describe("Only return contacts with these IDs"),
          notIn: z.array(z.string()).optional().describe("Exclude contacts with these IDs"),
          ignoreMerge: z.boolean().optional(),
          isStarred: z.boolean().optional(),
          isArchived: z.boolean().optional(),
          hasLinkedin: z.string().optional().describe("Filter by LinkedIn URL or true/false"),
          hasSource: z.string().optional().describe("Filter by source"),
          hasName: z.string().optional().describe("Filter by name substring"),
          hasGroups: z.union([z.string(), z.object({ not: z.string() })]).optional().describe("Group ID, or { not: groupId } to exclude"),
          hasFrequency: z.union([z.string(), z.boolean()]).optional().describe("Filter by frequency — true for any, or a specific value: '7 days', '14 days', '1 mon', '42 days', '3 mons', '6 mons', '1 year'"),
          hasLocation: z.string().optional(),
          hasJobTitle: z.string().optional(),
          hasNeverKeepInTouch: z.boolean().optional(),
          hasCreatedAt: dateRangeSchema.describe("Filter by creation date range { gte, lte }"),
          hasUpdatedAt: dateRangeSchema.describe("Filter by update date range { gte, lte }"),
          hasBirthday: z.union([z.boolean(), z.string()]).optional().describe("true to list all contacts with a birthday set, or an ISO 8601 datetime to match a specific date"),
          hasTag: z.string().optional().describe("Tag UUID"),
          hasInteraction: z.union([z.boolean(), z.string()]).optional(),
          hasNextReminder: z.union([z.boolean(), z.string()]).optional(),
        }).optional(),
        include: z.object({
          linkedinData: z.boolean().optional(),
          groupsCount: z.boolean().optional(),
        }).optional(),
        select: z.object({
          linkedinData: z.boolean().optional(),
          groupsCount: z.boolean().optional(),
        }).optional(),
      },
      async (args) => {
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 pagination and filtering capabilities but fails to describe critical behaviors like rate limits, authentication requirements, error handling, or the structure of the returned data. This leaves significant gaps for an agent to understand operational constraints.

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 efficiently structured with a clear opening sentence followed by specific examples. Each sentence adds practical value, though the examples could be slightly more concise. Overall, it's well-front-loaded and avoids unnecessary verbosity.

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?

Given the complexity (6 parameters, nested objects, no output schema, and no annotations), the description is moderately complete. It excels in explaining the 'where' parameter but neglects others and omits behavioral details. For a tool with rich filtering options, more comprehensive guidance on usage and output would be beneficial.

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

Parameters4/5

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

The description adds substantial value beyond the schema, which has only 50% coverage. It explains the 'where' parameter with specific examples (e.g., 'where.hasBirthday', 'where.isStarred=true'), clarifying usage that isn't fully documented in the schema. However, it doesn't cover other parameters like 'take', 'skip', 'cursor', 'include', or 'select'.

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

Purpose4/5

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

The description clearly states the verb ('List') and resource ('contacts'), and mentions advanced filtering, pagination, and field selection. However, it doesn't explicitly differentiate from sibling tools like 'dex_search' or 'dex_get_contact', which might have overlapping functionality for retrieving contacts.

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 provides implied usage through examples (e.g., 'find today's birthdays'), suggesting when to use certain filters, but lacks explicit guidance on when to choose this tool over alternatives like 'dex_search' or 'dex_get_contact'. No exclusions or prerequisites are mentioned.

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/byndcloud/unofficial-dex-mcp'

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