MCP Servers Directory — Page 439

Agent-only long-form publishing: articles, notes, replies and follows under the agent's own byline.

A zero-dependency Python CLI and library for looking up and comparing LLM API costs across all major providers.

llmprobe is a CLI tool for LLM serving reliability. It probes hosted APIs or OpenAI-compatible inference servers, then reports the metrics that

LLM provider intelligence: recommendations, pricing, and status

Delegate asynchronous coding jobs between Claude Code, Codex, Cursor Agent, and Pi.

AI visibility analytics for brand mentions, citations, sentiment, and GEO reports

Skill + slash commands for LLMPvP — a bring-your-own-LLM chess/Go arena — installable into any of 8 coding-agent CLIs (plus the universal .agents/skills convention) with one command.

Active jailbreak/extraction/obfuscation red-teaming for live LLM endpoints

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

Versioned documentation registry and semantic search for AI tools and coding assistants.

llm-router hooks into your coding tool's own lifecycle, reads each prompt before the model does, and drafts an answer on a free or local model first. No API keys needed on a Claude subscription — routing runs through…

Runs 21 technical-SEO and GEO (generative-engine-optimization) checks against your site, in pure TypeScript or pure Python, with zero Python interpreter, zero headless browser, and zero external…

Deterministic repo map, search and file reader for AI agents.

MCP server for the Elephant Accountability certification bureau. Surfaces vendor offerings, methodology, and audit requests to AI agents over the Model Context Protocol.

Crawls any website and generates a standards-compliant /llms.txt file and JSON-LD schema bundle.

Public integration metadata for llmsmap.me and llmsmap.ru.

This project demonstrates the integration between LLM clients and MCP (Model Context Protocol) servers using Server-Sent Events (SSE) for real-time

Build llms.txt from local Markdown or a sitemap.xml and check an existing llms.txt file.

Checks llms.txt, AI crawler access in robots.txt, and sitemap - with a 0-100 AI readiness score.

BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime.

Any site's llms.txt: find the covering index, read its linked docs as markdown, search sections. Remote MCP server over Streamable HTTP at https://llmstxtmcp.dev/mcp. Free, no API key. Tools…

Create, validate and audit llms.txt, incl. the Lighthouse Agentic Browsing check.

Does a site publish llms.txt, robots permissions and a sitemap agents can use? Bounded check.

Validate a site's llms.txt against the spec: fetches every linked URL, scores it 0-100.

llms.txt 檢查工具：檢查網站的 llms.txt、robots 與 sitemap。台灣繁體中文 MCP 工具。

檢查網站 llms.txt 與 AI 爬蟲 robots.txt 設定，並自動產生 llms.txt。

LLMTest MCP server — benchmark AI models and get cost-saving suggestions in your IDE

The llm_to_mcp_integration_engine is a communication layer designed to enhance the reliability of interactions between LLMs and tools (like MCP

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

Local-first MCP server for LLM output verification — risk signals, injection and PII checks.

Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP.

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

A Laravel 12 MCP (Model Context Protocol) package that provides AI agents with comprehensive API discovery and analysis capabilities. LMAD enables AI

Consent-based human matchmaking for peer advice, collaboration, and practical help.

LM hash 16-hex shape, value discarded

L-Moments for robust statistics & inference.

1. **Clone the repository:** ```bash git clone <your-repo-url> cd LMS-MCP ```

A Model Control Protocol (MCP) server that allows Claude to communicate with locally running LLM models via LM Studio.

OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base

Inspect-only HTTP 402 surface classifier. Keyless, no wallet, no signing, no payments.

This is a Node.js service for interacting with the LnExchange API, providing spot trading functionality.

This is a Node.js service for interacting with the LnExchange API, providing spot trading functionality.

Manage your Lnk.Bio page through AI: links, pages, themes, social icons, and more.

Build a free link-in-bio page (lnx.net/name) for the user from their links, socials and bio.

Styled, print-ready QR codes for links, text, email or phone, with frames and custom colors.

Catalog of 370+ open-source AI-agent harnesses. Search, list your own, earn USDC tips via x402.

Checks .NET solutions against a fluent C architecture spec and explains the rules to agents.

MCP server for structural load & stability math: tipping, support reactions, beam checks.

Search and install 20,000+ security-graded MCP servers and agent skills.

Loadster is a cloud load testing and monitoring platform. Its built-in Model Context Protocol (MCP) server lets AI agents like Claude, ChatGPT, Codex, Cursor, and VS Code write and play load test…

Search source-labeled hospital prices, CPT codes, providers, and healthcare cost estimates.

Loan and mortgage math: monthly payment, amortization schedule, payoff comparison.

A Model Context Protocol (MCP) server that exposes read-only access to LoanPro data via multiple transport protocols: HTTP, Server-Sent Events (SSE)

Amortization schedules for a loan: the level payment, the interest, and what settling early saves.

Verify US & international addresses and send physical mail (postcards, letters, checks) via Lob.

Lob MCP — US address verification, bulk verification, and autocompletion

Lobbywatch.ch transparency data on parliamentarians, interests, access badges

Agent-to-agent marketplace MCP: list skills, buy/sell services, earn gas, cash out BTC.

Public affairs CRM: stakeholders, projects, actions, Finnish Transparency Register

Unlike Slack or Discord (built for humans, patched for bots), Lobster Roll treats agents as first-class citizens with full account capabilities