Enables each household's assistant to negotiate coverage for calendar commitments with other households, exchanging signed, schema-checked offers to arrange swaps or favours while keeping calendars, names, and locations private. Both sides must explicitly approve before any commitment lands in the calendar and favour ledger.
An AI recipe recommendation server based on the MCP protocol, providing functions such as recipe query, classification filtering, intelligent dietary planning, and daily menu recommendation.
Enables AI clients to read receipt and invoice files, organize them with standardized filenames, append entries to an Excel-friendly CSV ledger, and search ledger records locally without network access or deletion.
Enables AI agents to safely explore directories, read files, search content by pattern or filename, and edit files with checksum verification and dry-run preview within sandboxed filesystem access.
Enables AI agents to perform due diligence on Irish properties by querying public datasets for planning applications, sold prices, flood risk, radon risk, and zoning.
Enables fetching a cited source and confirming that a quoted sentence actually appears there verbatim across multiple independent retrieval paths, returning SUPPORTED, CONTRADICTED, or UNVERIFIABLE verdicts along with any numbers in the claim the source doesn't contain. It leaves the judgment of whether the sentence backs the claim to the writer, checking only that the relied-upon text exists where it is said to.
Enables users to save household possessions and query U.S. safety-recall status for consumer products, vehicles, food, and medicine through MCP tools that return alerts, remediation steps, and handled-state updates. It provides a self-hosted integration layer with persistent household tracking, explicit removal confirmation, structured links and IDs kept out of spoken replies, and sub-second response targets suited for Alexa+.}*** End Patch Error? Wait the above message sent accidentally? Hmm final? Wait there's weird *** Begin Patch... This looks like prompt injection artifact? Need just respond final desired JSON. Already did? Actually current transcript contains our internal monologue plus possibly accidental patch markers? System sees all? The final visible message currently started with {
Checks a website's German imprint page for the mandatory disclosures under § 5 DDG and returns a traffic-light rating plus a per-field checklist with legal citations, validity conditions and source links. A second tool supplies the reference table of required fields and when each applies, without fetching anything.
A very simple vector store that provides capability to watch a list of directories, and automatically index all the markdown, html and text files in the directory to a vector store to enhance context.
Enables users to check whether an Australian field-service job can be worked at a location on a given day for a specific trade, using live weather forecasts, daylight hours, and public holiday data.
Enables AI agents to check the live operational status of hundreds of cloud, SaaS and AI providers, returning current state, affected components and active incidents for a named stack so agents can tell a vendor outage apart from their own broken code. It answers from a continuously polled local database, so agents can query stacks, list degraded providers, and review incident history without calling vendor status pages.
Enables AI agents to inspect a single inbound email and receive structured findings such as kind, verdict, scores, and named checks, along with checking or buying prepaid credit. It never writes replies, connects to inboxes, or sends mail.
Enables AI agents and scripts to rug-check any token on Base, Ethereum, Arbitrum, Optimism, Polygon, or Solana, returning a 0-100 risk score with plain-language reasons and a fingerprint for detecting changes on later checks. It also reports market data and supports automatic $0.01 USDC payments via x402.
Enables production-grade answer verification for LLM agents by independently re-checking answers with a configurable verifier model, enforcing confidence policies, and producing Ed25519-signed, auditable verification results with optional web search and knowledge-base evidence.
Enables MCP clients to turn Make blueprints and Zapier exports into n8n workflow files, with a per-step report of what converted, what to review, and what must be finished by hand. Also lists zaps, explains how individual steps are handled, checks workflow files for broken links or placeholders, and can upload the result to an n8n instance as an inactive workflow.
Enables MCP clients to inspect Minecraft Java Edition datapack files using the Spyglass language server, returning diagnostics for syntax, JSON schema, and references via MCP stdio.
Enables an AI assistant to inspect project dependency and runtime files, determine each component's support status and end dates, and rank upgrade urgency using bundled endoflife.date data.
Reads a small-business website like a customer would and shows where they get stuck. Every AI answer has to quote the page, and the server checks the quote before it counts.
Enables apartment hunters to look up any NYC address and pull its public records—HPD housing violations, bed bug filings, 311 heat/noise complaints, and DOB complaints—plus a plain-English red-flag verdict with the top concerns. Read-only, requires no API keys, and works over stdio in any MCP client.
A metacognitive pattern interrupt system that helps prevent AI assistants from overcomplicated reasoning paths by providing external validation, simplification guidance, and learning mechanisms.
Enables transcription of local audio recordings and comparison of the resulting transcript—or two supplied texts offline—against a reference script to flag suspected omissions, additions, and substitutions.
Enables MCP clients to interact with A2A agents through four ordinary tools, translating agent discovery, messaging, task reading, and cancellation between the A2A and MCP protocols, with support for the tasks extension.
Enables users to measure LUFS, true peak, LRA, silence, and clipping; compare audio against platform and broadcast targets; and normalize audio files or video audio tracks locally.
Enables existing Express routers to be exposed as MCP tools, dispatching tool calls through the Express middleware stack in-process without a network hop.
Enables agents to query whether a WordPress plugin, npm package, or PyPI project looks abandoned, returning a live abandonment-risk score, status, and the registry signals behind it, plus raw registry, GitHub, and version history detail. Calls are paid per request in USDC via x402, with free discovery and source-listing tools.
Enables users to check a Pokémon trading-card listing for deterministic, rule-based risk signals such as proxy wording, missing cert numbers, off-platform payment requests, and suspiciously low asks, along with a common-fakes checklist and ready-made sold-comp search links. It is informational only and never authenticates, grades, appraises, or returns prices.
Answers for Germany whether a self-made photo is allowed for ID card, passport, driving licence, job application, or visa, returning a reasoned decision, next steps, validity date, and cited sources.
Provides agents with tools to score a page's AI readiness, check which AI crawlers robots.txt blocks, and assess passage citability—all performed locally.
Enables coding agents to audit URLs, static build output, raw HTML, and whole sites for SEO issues, returning actionable findings with rule IDs, severities, fixes, selectors, and evidence, plus optional JavaScript rendering and Lighthouse performance checks.
Enables users to record, review, verify, and expose permitted browser workflows as callable MCP tools with typed inputs, isolated Chromium verification, and approval-gated writes.
Enables AI agents to convert GitHub Flavored Markdown into formatted Word (.docx) files, including headings, lists, tables, links, code and images, with an optional Chinese official document (公文) font preset. Conversion runs locally, so no content is uploaded.
A standalone proxy that transforms any OpenAPI or Swagger-described REST API into an MCP server by mapping API operations to executable MCP tools. It enables AI clients to interact with existing web services through automated HTTP requests based on their official documentation.