MCP server · S&P Global

spglobal-kfinance

Hosted (remote) MCP server for the S&P Global LLM-Ready API (kFinance), operated by Kensho. Documented first-class integrations: Claude (Desktop/Cowork/Code), ChatGPT, Microsoft Copilot Studio, Amazon Quick Suite, Databricks, and Mistral (Beta). The kensho-kfinance Python package also runs a local MCP server (python -m kfinance.mcp) with stdio, SSE, and streamable-http transports.

Open endpoint → S&P Global provider profile

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.

Provider: S&P Global Type: Hosted endpoint Transport: http Host: kfinance.kensho.com

Endpoint

https://kfinance.kensho.com/integrations/mcp

Hosted endpoint · transport 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, …):

# mcp client config (e.g. .mcp.json / mcp settings) { "mcpServers": { "sp-global": { "url": "https://kfinance.kensho.com/integrations/mcp" } } }

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

# Add to claude_desktop_config.json { "mcpServers": { "sp-global": { "command": "npx", "args": ["-y", "mcp-remote", "https://kfinance.kensho.com/integrations/mcp"] } } }

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

curl -i -X POST https://kfinance.kensho.com/integrations/mcp \ -H "Content-Type: application/json" -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

get_latest —
get_n_quarters_ago —
get_business_relationship_from_identifiers —
get_capitalization_from_identifiers —
get_info_from_identifiers —
get_company_other_names_from_identifiers —
get_company_summary_from_identifiers —
get_company_description_from_identifiers —
get_financial_auditors_from_identifiers —
get_competitors_from_identifiers —
get_cusip_from_identifiers —
get_isin_from_identifiers —
get_earnings_from_identifiers —
get_latest_earnings_from_identifiers —
get_next_earnings_from_identifiers —
get_transcript_from_key_dev_id —
get_key_devs_from_identifier —
get_financial_line_item_from_identifiers —
get_visible_alpha_financial_line_item_from_identifiers —
get_prices_from_identifiers —
get_history_metadata_from_identifiers —
get_professionals_from_identifiers —
get_professionals_from_person_ids —
get_segments_from_identifiers —
get_visible_alpha_segments_from_identifiers —
get_financial_statement_from_identifiers —
get_mergers_info_from_transaction_ids —
get_mergers_from_identifiers —
get_rounds_of_funding_from_identifiers —
get_rounds_of_funding_info_from_transaction_ids —
get_funding_summary_from_identifiers —
get_consensus_estimates_from_identifiers —
get_visible_alpha_consensus_estimates_from_identifiers —
get_guidance_from_identifiers —
get_consensus_target_price_from_identifiers —
get_analyst_recommendations_from_identifiers —
get_issuer_ratings_from_identifiers —

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.