segment-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEGMENT_PUBLIC_API_URL | No | The base URL for the Segment Public API. Defaults to https://api.segmentapis.com. Override this if needed. | https://api.segmentapis.com |
| SEGMENT_PUBLIC_API_TOKEN | Yes | Your Segment Public API token. Create a read-only token in Segment under Settings -> Access Management -> Tokens -> Create Token. The server reads this from a local .env next to index.mjs first, then falls back to the ambient environment. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_sourcesA | List all Segment sources in the workspace (id, name, slug, enabled, write key settings). |
| get_sourceC | Get a single Segment source by id, including its settings. |
| list_destinationsB | List Segment destinations. Optionally filter by a case-insensitive name/slug substring (e.g. 'intercom') and/or by sourceId. |
| get_destinationA | Get a single Segment destination by id, including its full settings/config (e.g. the Intercom regional endpoint and app id). |
| list_tracking_plansB | List all tracking plans in the workspace. |
| get_tracking_planC | Get a single tracking plan by id. |
| list_functionsA | List functions in the workspace. Optionally filter by resourceType; omit it to list every type. |
| get_functionC | Get a single function by id. |
| api_getA | Read-only escape hatch: issue an arbitrary GET against any Segment Public API path (e.g. '/labels', '/warehouses'). Only GET is supported; this server can never write. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool targets a distinct resource+action: list/get pairs for sources, destinations, functions, and tracking plans are cleanly separated, and api_get is clearly scoped as a read-only escape hatch. There is no meaningful overlap between any tools.
The verb_noun pattern (list_sources, get_function, list_tracking_plans) is applied consistently across eight tools. The only deviation is api_get, which inverts the convention, but it is a distinct escape-hatch concept and remains readable.
Nine tools is well within the sweet spot and each earns its place with a clear resource-verb pairing. Nothing feels redundant or padded.
The server is explicitly read-only, and for that scope it offers list+get coverage for the four main resource families plus a generic GET escape hatch for unmodeled paths. No write operations exist, but that is by design rather than an oversight.