Skip to main content
Glama
bratland

Pipedrive MCP Server

by bratland

get_deals

Retrieve and filter deals from Pipedrive CRM by status, user, organization, or custom filters to monitor sales pipeline and track opportunities.

Instructions

Get a list of deals from Pipedrive

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
startNoPagination start (default: 0)
limitNoNumber of items to return (default: 100, max: 500)
statusNoFilter by deal status
filter_idNoPredefined filter ID
user_idNoFilter by user ID
person_idNoFilter by person ID
org_idNoFilter by organization ID

Implementation Reference

  • The handler method `getDeals` within `PipedriveClient` class that executes the API request.
    async getDeals(params?: {
      start?: number;
      limit?: number;
      status?: 'all_not_deleted' | 'open' | 'won' | 'lost' | 'deleted';
      filter_id?: number;
      user_id?: number;
      person_id?: number;
      org_id?: number;
    }): Promise<PipedriveResponse<Deal[]>> {
      return this.handleRequest<Deal[]>(
        this.client.get('/deals', { params })
      );
    }
  • The MCP tool definition (schema) for 'get_deals' in `src/tools/deals.ts`.
    {
      name: 'get_deals',
      description: 'Get a list of deals from Pipedrive',
      inputSchema: {
        type: 'object',
        properties: {
          start: {
            type: 'number',
            description: 'Pagination start (default: 0)',
          },
          limit: {
            type: 'number',
            description: 'Number of items to return (default: 100, max: 500)',
          },
          status: {
            type: 'string',
            enum: ['all_not_deleted', 'open', 'won', 'lost', 'deleted'],
            description: 'Filter by deal status',
          },
          filter_id: {
            type: 'number',
            description: 'Predefined filter ID',
          },
          user_id: {
            type: 'number',
            description: 'Filter by user ID',
          },
          person_id: {
            type: 'number',
            description: 'Filter by person ID',
          },
          org_id: {
            type: 'number',
            description: 'Filter by organization ID',
          },
        },
      },
    },
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to mention pagination behavior beyond the bare schema, rate limits, authentication requirements, or whether this is a safe read operation versus potentially expensive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is not wasteful, but given 7 parameters, zero annotations, no output schema, and numerous similar sibling tools, it is undersized rather than appropriately concise. Front-loading is impossible with such brevity.

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?

For a tool with 7 filterable parameters and multiple similar siblings, the description is incomplete. It should explain pagination limits, the relationship between filter_id and other filter parameters, and when to prefer search_deals versus this listing endpoint.

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?

With 100% schema description coverage, the structured fields already document start/limit pagination and filtering options sufficiently. The description adds no additional parameter context (e.g., that status filters are mutually exclusive with filter_id, or pagination best practices), warranting the baseline score.

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 states the basic action (Get) and resource (deals from Pipedrive), but lacks specificity to distinguish from siblings like get_deal (singular), search_deals, or get_deals_summary. It doesn't clarify if this is a bulk listing operation versus a targeted fetch.

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?

No guidance provided on when to use this tool versus the 6+ sibling deals tools (e.g., search_deals for queries, get_deal for single record retrieval, get_deals_summary for analytics). No mention of prerequisites or filtering recommendations.

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/bratland/pipedrive-mcp-server'

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