demandsphere-mcp.yml

Endpoint

Hosted endpoint · transport streamable-http

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:

Tool quality observed · not scored

From an anonymous initialize + tools/list capture measured 2026-10-20; tokens are chars/3.6 of each tool definition. Recorded for the Kin Score's agent readiness as an observed signal — it contributes no points yet.

Tools

• get_ai_models — Use structured filters to list frontier AI models from the DemandSphere Radar tracker at demandsphere.com/research/demandsphere-radar/ai-frontier-model-tracker/. Returns name, provider, country the lab is based in, release date, training data cutoff date, parameters, context window, benchmarks (MMLU-Pro, GPQA Diamond, SWE-bench, HumanEval, MATH-500, AIME, HLE), and API pricing. Sorted by release date descending. Use this with known filter values; use search_ai_models for natural-language queries.
• get_ai_model_by_id — Get a single AI model by its ID from the DemandSphere Radar tracker. Returns the full record including all benchmarks, pricing, parameters, and download links.
• search_ai_models — Full-text search across AI models from the DemandSphere Radar tracker at demandsphere.com/research/demandsphere-radar/ai-frontier-model-tracker/. Matches against model name, provider, and description. Use this for natural-language queries; use get_ai_models for structured filtering by provider, type, access level, or date range.
• calculate_model_cost — Calculate the token cost of running a specific AI model. Data from the DemandSphere Radar tracker. Requires model name or ID plus at least one of input_tokens or output_tokens.
• get_providers — List all AI model providers/labs tracked by the DemandSphere Radar tracker at demandsphere.com/research/demandsphere-radar/ai-frontier-model-tracker/, with the country each lab is based in, model counts, and provider metadata.
• get_algorithm_updates — Use structured filters to list Google algorithm and AI search updates from the DemandSphere Radar tracker at demandsphere.com/research/demandsphere-radar/algorithm-update-tracker/. Covers core updates, spam updates, AI innovations, and system changes from 2000 to present. Updated as new updates are confirmed. Sorted by date descending. The "type" field here refers to Google update categories (Core, Spam, AI, System, Other) - not AI model types. Use this with known filter values; use search_algorithm_updates for natural-language queries.
• search_algorithm_updates — Full-text search across Google algorithm and AI search updates from the DemandSphere Radar tracker at demandsphere.com/research/demandsphere-radar/algorithm-update-tracker/. Matches against update name, description, and slug. Use this for natural-language queries; use get_algorithm_updates for structured filtering by type, year, or date range.
• get_server_info — Get DemandSphere Radar MCP server metadata including version, data freshness timestamps, model count, update count, and provider count. AI model data is updated daily. Algorithm update data is updated as new updates are confirmed by Google.

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.

curl "https://apis.io/api/v1/mcp/demandsphere-mcp-yml"

curl "https://apis.io/api/v1/mcp?limit=25"