moirailabs-com-mcp.yml
Moirai Labs ships one remote MCP surface: an "MCP bridge" mounted on the A2A agent host at https://agent.moirailabs.com/a2a/v1/mcp, declared by the agent card as a vendor extension and by the /a2a page ("An MCP-compatible client (Claude Desktop, Cursor, custom IDE) exposes MoiraiLabs as a tool ... with credit-aware rate limits ... Streaming responses (server-sent events)"). It is bearer-gated: POST tools/list without a token returns HTTP 401 {"code":"unauthorized","message":"Missing bearer token"}, so the live tool list and inputSchemas could not be read anonymously. The provider publishes no MCP tool list anywhere else (llms.txt names no tools), so tools[] below is the A2A skill list the card publishes, which the bridge most plausibly projects — marked as such, not as an observed tools/list.
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.
Endpoint
Hosted endpoint · transport streamable-http (SSE streaming per the /a2a page)
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
analytics.cohorts— Cohort analytics for contract activityanalytics.metrics— Aggregate metrics for contract transactionsanalytics.methods— Method-level analytics breakdownanalytics.methods_by_cohorts— Method activity segmented by cohortsanalytics.transactions— Transaction-level analytics feedreports.daily— Daily aggregated contract reportreports.weekly— Weekly aggregated contract reportreports.monthly— Monthly aggregated contract reportcontracts.register— Register a contract for analytics indexingcontracts.status— Check indexing status for a registered contractmcp.bridge— Use vendor MCP bridge endpoint at /a2a/v1/mcp
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.