"Traditional Welsh Dish Cawl" matching MCP servers:

MCP server exposing memory search, index, and stats tools for agents, with honesty guards to prevent re-litigation of settled decisions.

Checks a website's AI readiness: can ChatGPT, Claude, Perplexity, Google AI and 50+ other AI crawlers (GPTBot, ClaudeBot, PerplexityBot) access it? Scores the site, then generates llms.txt, an AI-crawler robots.txt and JSON-LD, and reads LLM Monitor trends, from Claude Desktop, Cursor and other MCP clients.

Delegates coding tasks to the locally installed DeepSeek Harness CLI, enabling MCP clients to run prompts through dsh and receive results with exit code and timing.

A thin, timezone-correct MCP server for scheduling against CalDAV calendars, providing tools for creating, updating, and managing events with proper timezone handling and recurrence support.

Browser acceptance testing for AI agent deliverables: verify agent output in real Chromium from JSON specs, with MCP server, visual regression, multi-browser support and GitHub Actions.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Certification lookup for DeepSeek Harness plugins: an agent-facing interface to the dsh-plugin-certification registry, checking a plugin's five reproducible dimensions (manifest compliance, build hygiene, supply-chain Scorecard, release provenance, sandboxed install smoke) before recommending or installing it.

Your mailboxes in ChatGPT and Claude: Gmail, iCloud, Fastmail or any IMAP/SMTP account, as many as you like. Search, read, threaded replies, drafts, allowlisted sending and attachments; passwords are encrypted in the browser and the server stores nothing.

Windows computer-use MCP server: accessibility-first element actions (UIA), UI read as diffed text trees instead of screenshots, guarded raw input, and a cross-session arbiter that yields to the human. 19 tools.

Local-first toolkit with 16 tools for Chinese web-novel (网文) authors: style baselines, foreshadowing and plot-thread tracking, continuity & OOC audits, keyword and sentence-pattern analysis, and offline semantic search. No API key, no network — everything runs on your machine.

Enables AI agents to pull live China A-share market data through 24 tools spanning real-time quotes, K-lines, five-level order books, financials, money flow, dragon-tiger lists, sector and valuation data, convertible bonds, ETFs, IPOs, macro indicators, and factor-based stock screening. Five of the tools work with no API key, while the rest require a paid key.

Enables MCP clients such as Claude Desktop, Cursor, and Windsurf to run two-sample Welch's t-tests that compute Satterthwaite degrees of freedom and two-tailed p-values for A/B test comparisons. It also exposes zero-dependency statistical primitives including Holt linear forecasting, Z-score/IQR anomaly detection, gradient-descent regression, and power-iteration PCA, all using only the Python standard library.

Provides deterministic, byte-stable temporal reference data over MCP, resolving civil dates and names into calendars, seasons, moon phases, planetary retrogrades, and traditional symbolic systems. Exposes tools that return a single date's identity, compare two dates across shared symbolic systems, and map a name to cosmic cards and Latin cipher sums, with coverage focused on 1900–2100.

MCP commerce surface for refurbished datacenter hardware — GPU rigs, server racks, drive arrays, and network gear, with x402 agent-payment discovery.

Provides desktop automation capabilities (e.g., click, browser snapshot) as MCP tools for DSH agents, enabling computer use via natural language.

MCP bridge enabling ChatGPT to create, view, and control DeepSeek Harness agent sessions, with session management, messaging, and approval tools.

Enables autonomous agents to automatically repair and guard tool-call schemas through deterministic AST analysis and parameter projection validation, ensuring reliable, schema-compliant interactions in MCP-compatible environments.

Search and read locally-recorded meeting transcripts over stdio. Read-only, no network. Exposes list_sessions, get_session, and search_transcripts to any MCP client.

Enables AI IDEs to chat with, search, explain, refactor, and audit a local codebase without uploading source code, returning answers backed by file-and-line source citations, confidence scores, and severity labels, plus audit and board-ready strategic reports. Runs locally and standalone as an MCP server compatible with Claude, Cursor, Windsurf, and DeepSeek Harness.

calcom-mcp