"Documentation URL for a service API, data, and LLM usage" matching MCP servers:

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

Exposes data query and auto-insights (anomaly detection) as MCP tools. Enables AI agents to query metrics, list columns, and get data insights directly from pandas.

MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.

Enables full-text search and paginated retrieval of indexed documentation (PDFs, Markdown, text) through MCP tools, with filtering by category and file.

Search and retrieve Agent2Agent (A2A) protocol documentation using full-text search and section filtering.

Enables AI agents to check URL safety before fetching content, using Google Web Risk, URLhaus, PhishTank, and AI analysis to return SAFE/SUSPICIOUS/DANGEROUS verdicts.

MCP server for Claude Code that generates a documentation skeleton from Git repository changes, outputting a Markdown file with placeholders for AI analysis.

Provides full-text search and retrieval tools for Apache Spark documentation using SQLite FTS5 with BM25 ranking. It enables AI assistants to efficiently search, filter by section, and read specific Spark documentation pages.

Exposes five tools for querying and analyzing a customer-support dataset, including listing categories/intents, filtering, counting, and summarizing records.

Enables searching and reading OCI documentation using the Oracle Help Center Search API. Provides tools for finding relevant documentation URLs and reading page content.

MCP server that provides AI assistants with real-time, current information about AI models from OpenAI, Anthropic, and Google, including pricing, capabilities, and context windows.

Blind multi-model councils with anonymous LLM seats and direct 1:1 chat as a local MCP server. Enables asking one question to get independent answers from multiple model CLIs, then blind scoring and reveal.

Lets Claude Code send prompts to a locally running Qwen model on Apple Silicon and get answers back, with optional thinking mode for harder problems. It also lists the registered models and reports whether each one is running.

Enables searching, reading, and listing pages from the official chezmoi documentation. Supports caching and Markdown conversion for LLM-friendly access.

Enables AI assistants to search and read Azure documentation using full-text search and section filtering, with content retrieval from Microsoft's official Azure docs repository.

Enables extracting visible text and links from webpages for content analysis.

Enables a primary agent to offload bounded, high-volume analysis of explicitly selected workspace files to an auxiliary LLM through a single read-only tool, returning text, Markdown, JSON, or unified-diff output with token usage while retaining all planning, verification, and edits.

Enables MCP clients like Claude to query Chinese A-share market data, including K-line charts with forward/backward adjustment, limit-up and limit-down pools, per-stock fund flows, index quotes, and stock news, with automatic symbol normalization and retry handling for throttled data sources.

An MCP server that provides AI agents with direct access to authoritative Cakemail API specifications, enabling accurate code generation and eliminating hallucination.

Provides A-share (Chinese stock market) quantitative analysis through tools for stock screening, northbound capital flow tracking, dragon-tiger list analysis, margin trading, sector analysis, technical indicators, IPO info, and limit-up/down statistics using akshare data.