Pipedrive MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_PORT | No | Port for SSE transport | 3000 |
| MCP_ENDPOINT | No | Message endpoint path for SSE | /message |
| MCP_JWT_TOKEN | No | JWT token for authentication | |
| MCP_TRANSPORT | No | Transport type: stdio or sse | stdio |
| MCP_JWT_ISSUER | No | JWT issuer | |
| MCP_JWT_SECRET | No | JWT secret for authentication | |
| MCP_JWT_AUDIENCE | No | JWT audience | |
| PIPEDRIVE_DOMAIN | Yes | Your Pipedrive domain (e.g., your-company.pipedrive.com) | |
| MCP_JWT_ALGORITHM | No | JWT algorithm | HS256 |
| PIPEDRIVE_API_TOKEN | Yes | Your Pipedrive API token | |
| PIPEDRIVE_RATE_LIMIT_MIN_TIME_MS | No | Minimum time between requests in milliseconds | 250 |
| PIPEDRIVE_RATE_LIMIT_MAX_CONCURRENT | No | Maximum concurrent requests | 2 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get-usersA | List Pipedrive users/owners. |
| get-dealsB | List visible, non-archived Pipedrive deals without hidden status or date defaults. |
| get-dealA | Get a Pipedrive deal by ID, including generic custom fields. |
| get-deal-notesB | List notes attached to a Pipedrive deal. |
| search-dealsA | Search Pipedrive deals by title, notes, or searchable custom fields. |
| get-personsC | List Pipedrive persons. |
| get-personA | Get a Pipedrive person by ID. |
| search-personsC | Search Pipedrive persons. |
| get-organizationsC | List Pipedrive organizations. |
| get-organizationC | Get a Pipedrive organization by ID. |
| search-organizationsC | Search Pipedrive organizations. |
| get-pipelinesC | List Pipedrive pipelines. |
| get-pipelineB | Get a Pipedrive pipeline by ID. |
| get-stagesB | List Pipedrive stages, optionally filtered by pipeline. |
| search-leadsC | Search Pipedrive leads. |
| search-allB | Search across supported Pipedrive item types. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| list-all-deals | List Pipedrive deals |
| list-all-persons | List Pipedrive persons |
| list-all-pipelines | List Pipedrive pipelines |
| analyze-deals | Analyze deals by stage |
| analyze-contacts | Analyze contacts |
| analyze-leads | Analyze leads |
| compare-pipelines | Compare pipelines |
| find-high-value-deals | Find high-value deals |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 16 tools
Each tool targets a distinct entity or operation (e.g., get-deals vs. get-deal vs. search-deals). The differences are clear from descriptions, reducing ambiguity.
All tools use a consistent verb_noun pattern (e.g., get-users, search-persons). List operations use plural nouns, single retrieval uses singular, and searches are prefixed with 'search-'.
With 16 tools, the count is slightly above the typical 3-15 range but still reasonable for covering multiple CRM entities. No tools are redundant.
Only read operations are provided (list, get, search). Missing create, update, delete tools, which are essential for a CRM server. Agents cannot perform any write actions.