AceDataCloud MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level. | INFO |
| PLATFORM_API_BASE_URL | No | Management API base URL. | https://platform.acedata.cloud |
| PLATFORM_REQUEST_TIMEOUT | No | Request timeout in seconds. | 30 |
| ACEDATACLOUD_PLATFORM_TOKEN | Yes | Your AceDataCloud platform token (starts with platform-). Required. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| acedatacloud_list_blog_postsB | List published blog posts. No account or blog permission required. |
| acedatacloud_get_blog_postB | Read a published blog post and its localized Markdown content. |
| acedatacloud_get_serviceA | Get one service's full detail: title, description, type, unit, free_amount
and its display pricing ( |
| acedatacloud_get_pricingA | Get a service's pricing: the billing |
| acedatacloud_list_apisA | List API endpoints, optionally scoped to one |
| acedatacloud_get_api_specA | Get one API endpoint's OpenAPI spec ( |
| acedatacloud_list_datasetsA | List downloadable datasets (title, price, download/preview URLs). No token required. |
| acedatacloud_list_integrationsA | List third-party integrations (title, options, stage). No token required. |
| acedatacloud_search_docsA | Full-text search the AceDataCloud documentation. Returns matching docs with alias, title, snippet and url. No token required. |
| acedatacloud_list_docsA | Browse documentation pages (newest/ranked), optionally filtered by |
| acedatacloud_get_docA | Fetch one documentation page's full content by its UUID. No token required. |
| acedatacloud_get_usage_guideA | Get a guide for using the AceDataCloud platform management tools. Explains the available tools, the write-confirmation model, and the authentication requirements. |
| acedatacloud_get_services_apisC | Get services apis. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_services_proxiesC | Get services proxies. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_list_site_home_sections_publicC | List site home sections public. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_apis_idC | Get apis id. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_apis_usageC | Get apis usage. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_datasets_idC | Get datasets id. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_integrations_idC | Get integrations id. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_documents_openapi.jsonC | Get documents openapi.json. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_get_recharge_cards_allocations_tokenC | Get recharge cards allocations token. Backend account permissions and ownership checks apply. Required permissions: applications:read |
| acedatacloud_get_coin_policies_idC | Get coin policies id. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_list_showcasesC | List showcases. Backend account permissions and ownership checks apply. Required permissions: public |
| acedatacloud_list_model_catalogA | List the model catalog with provider, modality and per-model credit pricing. Returns the modality counts plus matching models. No token required. |
| acedatacloud_get_modelA | Look up models by id/name (case-insensitive substring) with their credit pricing and capabilities. No token required. |
| acedatacloud_list_servicesA | List the services available on the AceDataCloud platform. |
| acedatacloud_list_announcementsA | List published platform announcements (newest first). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| acedatacloud_guide | Guide for managing an AceDataCloud account via the platform tools. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 27 tools
Several tools overlap in purpose: list_apis, get_api_spec, get_apis_id, get_services_apis and get_service/get_pricing all revolve around API/service metadata, and list_docs vs search_docs vs get_document vs get_documents_openapi.json require careful reading to separate. Descriptions do cross-reference each other (list_docs vs search_docs) which helps, but the auto-generated 'Get X id' tools (get_apis_id, get_datasets_id, get_integrations_id, get_coin_policies_id) are indistinguishable from their list/get counterparts.
Most tools follow acedatacloud_verb_noun in snake_case, but the pattern breaks with path-derived names like get_apis_id, get_services_apis, get_documents_openapi.json (literal .json suffix), list_site_home_sections_public, and get_recharge_cards_allocations_token. The prefix is consistent, but the verb/resource ordering is not.
27 tools is on the heavy side for what appears to be a platform metadata/read surface, and a number of them (the generic '_id' getters) feel auto-generated rather than purposefully scoped. The domain is broad, so it is borderline rather than clearly excessive.
The surface is almost entirely read-oriented (list/get) with no create/update/delete tools despite the usage guide referencing a 'write-confirmation model', leaving a notable lifecycle gap. Read coverage across services, docs, datasets, integrations and models is fairly broad but inconsistent.