Service Atlas MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_URL | Yes | The URL of the service dependency API |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_debtB | Gets a report of all services that have open debts and a count of the number of debts associated with them :return: |
| get_debts_for_serviceC | Gets the debts for a specific service :param service_id: :return: |
| get_all_teamsA | Returns all teams from the service atlas api :return: array of teams objects |
| get_services_by_teamB | Tool that returns a list of services for a team based on id :param team_id: guid for the team :return: array of services objects from the api |
| find_service_by_nameC | Search for a service by name :param query: the name to search against :return: a list of services objects |
| get_teams_by_serviceB | Gets a list of teams that own a service based on id :param service_id: the guid for the service :return: a list of teams objects |
| get_releasesA | Get a list of releases between two dates. Start date is inclusive, while the end date is an exclusive :param start: start date in the format YYYY-MM-DD (inclusive) :param end: end date in the format YYYY-MM-DD (exclusive) :return: list of releases |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| get_debt | |
| find_which_team_owns_a_service | Prompt for telling the AI how to find which team owns a service :return: |
| get_all_teams | |
| get_services_by_team | Prompt for telling the AI how to get services if it has a team id :param team_id: :return: |
| find_service_by_name | Prompt for telling the AI how to find a service by name :return: |
| get_releases | Get a list of releases between two dates :param start: start date in the format YYYY-MM-DD :param end: end date in the format YYYY-MM-DD :return: string prompt |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Debt Report | Gets a report of all services that have open debts and a count of the number of debts associated with them :return: |
| All Teams | Returns all teams from the service atlas api :return: array of teams objects |
TDQS
Scored across 7 tools
Each tool has a distinct purpose targeting specific resources and operations: find_service_by_name searches services by name, get_all_teams retrieves all teams, get_debt provides a debt report, get_debts_for_service gets debts for a specific service, get_releases fetches releases between dates, get_services_by_team lists services for a team, and get_teams_by_service lists teams for a service. No overlap or ambiguity exists between these functions.
Tool names follow a consistent snake_case pattern with a clear verb_noun structure (e.g., find_service_by_name, get_all_teams). However, there is a minor deviation: get_debt uses a singular noun while others use plural or compound nouns, slightly breaking the pattern but not affecting readability.
With 7 tools, the count is well-scoped for a service atlas domain, covering key operations like service and team retrieval, debt management, and release tracking. Each tool serves a unique function without redundancy, making the set efficient and manageable.
The toolset provides good coverage for querying services, teams, debts, and releases, supporting core workflows. A minor gap exists in update or delete operations for these resources, but agents can likely work around this for read-heavy use cases in a service atlas context.