"date-fns" matching MCP servers:

MCP server to temporarily add a global Codex directive requiring Claude Code usage until a configured expiry date, with guardrails and cleanup.

Fleet-wide shared rate limiter for A2A + multi-MCP deployments, providing a shared counter with sliding window, concurrency grants, and signed enforcement attestations.

Enables AI clients to call upstream MCP tools under each user's own identity, with guardrails, approvals, data filtering, and tamper-evident audit streaming to SIEM.

Enables any MCP host to search open positions and fetch individual job details from oneforma.com's public API/RSS through read-only search_jobs and get_job tools, with keyword, location, remote, and date filters. Runs as a standalone stdio server that works with Cursor, Claude Desktop/Code, Codex, and comparable agents without extra infrastructure.

Provides a human approval gate for AI agents, enabling interactive inline cards for approving, editing, or rejecting actions before they are executed.

Proxy for any MCP server that lets read tools pass straight through while turning every write tool into a pending card the agent cannot release on its own. Only signed evidence from the user's paired device — a tap on the approval page or their own transcribed voice — actually executes the action, with one-time nonces, expiry, replay checks and receipts.

This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Google Data Catalog (beta): https://www.cdata.com/download/download.aspx?sku=HGZK-V&type=beta

Enables AI agents and MCP-compatible clients to enforce multi-provider token-bucket and sliding-window rate limits, preventing TPM/RPM throttling across LLM APIs with predictive token consumption budgeting.

A paid hosted MCP server that enforces explicit state transitions for AI agent workflows, providing tools to check, explain, and log state changes.

Enables high-throughput API rate limiting with deterministic token bucket throttling and burst quota management for AI agents.

Enables AI assistants to perform basic and advanced web searches through the Exa API, returning real-time Markdown-formatted results with titles, URLs, publication dates, and content summaries. Supports filtering by domains, required text, and date ranges for more targeted searches.

Enables autonomous agents to apply adaptive token bucket concurrency limits and backoff scheduling to avoid HTTP 429 errors. It provides deterministic rate-limiting permits and structured telemetry through MCP-compatible clients.

Enables AI assistants to run basic and advanced web searches through the Exa API, with filtering by domains, required text, and date ranges. Returns real-time, markdown-formatted results including titles, URLs, publication dates, and content summaries.

A server that routes user questions to specialized agents (date, location, weather) or an LLM expert, with a simple Streamlit web interface for easy interaction.

Enables adaptive token bucket rate limiting and backoff scheduling to prevent HTTP 429 errors for autonomous agents and API clients. Provides a deterministic zero-dependency MCP/CLI engine for acquiring token permits and returning structured telemetry.

Paid remote MCP server providing structured receipts, audit logs, and reviewer-ready evidence for Claude Code skill update gate operations.

An MCP server that enables AI models to search the web using OpenAI's 4o-mini Search model, allowing access to up-to-date information for just a few cents per search.

Integrates real-time web search into AI assistant frameworks through the Exa API, returning Markdown-formatted results with titles, URLs, publication dates, and content summaries. Supports both basic queries and advanced searches with filtering by domain, required text, and date range.

Enables AI agents to search the public pages of Soft98, P30Download, Downloadly and VGDL for software and games, returning metadata only — name, version, size, category, date, short description, system requirements and the item page URL. It is read-only and never downloads files, returns file links, passwords or crack notes.

Human-in-the-Loop approval gate for AI agents to assess risky operations and require user approval via Cursor forms.