Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TOSEA_API_KEYYesYour ToseaAI API key. Must start with 'sk_'.
TOSEA_LOG_LEVELNoOptional: Logging level for the MCP server.
TOSEA_TIMEOUT_MSNoOptional: Timeout for API requests in milliseconds.
TOSEA_MAX_POLL_MSNoOptional: Maximum total duration to poll for job completion in milliseconds.
TOSEA_MAX_RETRIESNoOptional: Maximum number of retries for failed requests.
TOSEA_API_BASE_URLYesThe base URL for the ToseaAI API (e.g., https://tosea.ai).
TOSEA_POLL_INTERVAL_MSNoOptional: Interval for polling long-running operations in milliseconds.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
tosea_healthA

Check MCP connectivity to ToseaAI.

tosea_get_permissions_summaryA

Inspect current account tier and feature access before expensive runs.

tosea_get_quota_statusA

Inspect quota status for all features or a single feature key.

tosea_list_presentationsC

List the current user's presentations.

tosea_get_presentation_full_dataB

Fetch full structured presentation data, including outlines and slides.

tosea_switch_templateB

Fork an existing presentation into a new presentation using exactly one template source: template_name, user_template_id, or system_template_key.

tosea_create_document_parseC

Upload local source files and create a parse-only document job that can later return combined Markdown and extracted image URLs.

tosea_get_document_parseC

Fetch parse job status for a document_parse_id without exposing presentation details.

tosea_wait_for_document_parseA

Poll a document parse job until completed, failed, or cancelled.

tosea_get_document_parse_resultA

Fetch the final Markdown, per-file parse payloads, and extracted image URLs for a completed document parse job.

tosea_parse_pdfB

Upload local source files and run the parse-only stage. Use logo_file_id for a previously confirmed logo upload. Use template_file_id only with slide_mode='image'; it points to a previously confirmed custom-template upload, not a source document.

tosea_generate_outlineC

Queue outline generation for an existing presentation.

tosea_edit_outline_pageC

Modify or insert outline content synchronously through the aggregated MCP edit contract.

tosea_render_slidesC

Queue slide rendering for all slides or a subset of slide numbers.

tosea_edit_slide_pageC

Modify or insert a slide. Supports optional screenshot grounding for multimodal edits.

tosea_export_presentationA

Queue an export job for a completed presentation. Use output_format='pptx_image' when an image-mode deck must be delivered as a pure image-based PPTX. Use html_zip only for HTML-mode decks.

tosea_pdf_to_presentationA

Upload local source files and generate a final export in one shot. Keep slide_mode='html' by default. Use slide_mode='image' only when the user explicitly wants image-mode rendering. Use template_file_id only with slide_mode='image'; it points to a previously confirmed custom-template upload, not a source document. Use logo_file_id for a previously confirmed logo upload. Choose output_format='pptx_image' when the user wants an image-based PPTX export.

tosea_wait_for_jobA

Poll a presentation job until completed, failed, or cancelled. When backend payload includes nested job progress, wait on data.job.status instead of the top-level presentation status.

tosea_list_exportsB

List presentations that already have export history.

tosea_list_export_filesC

List user-visible exported files for a presentation.

tosea_redownload_exportC

Get a fresh download URL for an existing exported file.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

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/ToseaAI/mcp-ToseaAI'

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