MCP server · 0G Labs
0g-router
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
⚠ Proposed MCP surface. No official hosted MCP server was found for 0G Labs. The tools below are a candidate set derived from this provider's API, and the link points at the source descriptor rather than a live server. If 0G Labs publishes an official server, this page will update to it on the next build.
Descriptor
Candidate descriptor · transport http
Tools
list_models— Browse the live 0G Compute model catalog — id, context window, supported parameters and formats, TEE attestation, provider count, and per-token pricing in both raw neurons and USD.list_providers— List the on-chain providers currently serving a model, with health, latency, TEE acknowledgement and per-provider pricing.list_service_types— List the service classes the network serves (chatbot, speech-to-text, text-to-image, video-generation).preview_routing— Dry-run which provider a request and its X-0G-Provider-* preferences would select, without running or paying for the inference.create_chat_completion— OpenAI-compatible chat completion with streaming, tool calling, JSON mode and reasoning tokens.create_anthropic_message— Anthropic Messages-shaped completion, for models whose supported_formats include it.transcribe_audio— Speech-to-text via the OpenAI-compatible transcription endpoint (multipart).generate_image— Synchronous OpenAI-compatible image generation.edit_image— Synchronous image edit from a supplied source image (multipart).submit_async_image_generation— Submit an image generation job and poll for the result.submit_async_image_edit— Submit an image edit job and poll for the result.submit_video_generation— Submit an async video generation job. size names a resolution tier; seconds is clamped to the model range.get_video_job— Poll an async video job for status and its billing trace.download_video_content— Download the rendered clip for a completed video job.get_account— Read account metadata — wallet address, created_at, onboarded_at.get_account_funds— One aggregated display balance across the Router ledger and the Payment Layer vault. May be negative when the account owes the Router.get_usage_history— Paginated per-request usage rows — model, provider address, token counts, cost, request_id.get_usage_stats— Rolled-up usage statistics for the account.get_daily_usage— Usage bucketed by day.list_api_keys— List sk- API keys with labels, created-at and last-used.create_api_key— Issue a new sk- API key. The secret is returned once.update_api_key— Edit an API key's label or state.revoke_api_key— Revoke an API key immediately.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.