Hosted tools for agents
MCP servers, one URL away.
A hosted MCP server gives your agent live tools and data without a local install. Browse 3,808 MCP servers, copy the endpoint, and use the one-line installer for your client.
- MCP servers
- 3,808
- Categories
- 15
- Client guides
- 14
- Distinct hosts
- 3,667
QA WolfDevelopmentConnect your coding agent to QA Wolf to create, run, and troubleshoot end-to-end tests. Explore your app in a cloud browser, review a proposed test outline, and approve QA Wolf to implement and validate it. Sign in with your QA Wolf account and follow progress through live session links.app.qawolf.comView setupqarunbookDevelopmentShared app-testing runbook: read the plan, record results per platform, raise and fix issues. A fixed issue sends the check back for a retest rather than passing.qarunbook.comView setupQBCore Community DocumentationDevelopmentIndependent QBCore community documentation for AI coding agents: docs_search, docs_get and docs_list cover QBCore APIs, qb-* resources, setup and troubleshooting with canonical Markdown paths. The live endpoint answers without authentication; the provider does not publish separate MCP setup docs beyond the developers page.qbcore.netView setupQueayDevelopmentQueay exposes a remote MCP server so a coding agent - Claude Code, Claude Desktop, GitHub Copilot, Kilo Code, and others - can list your test scripts, trigger a run, and check its status without leaving your editor. All execution still runs on Queay's own infrastructure; the agent only triggers and reads back results, the same as CI/CDqueay.comView setupQuota Reset WatchDevelopmentRead-only Codex and Claude public quota reset evidence, history, source health and historical 24/48-hour estimates. Remote MCP at https://quotaresetwatch.com/mcp. No API key; no personal account monitoring.quotaresetwatch.comView setupRatedWithAI Accessibility CheckerDevelopmentRemote MCP server that scans a public web page with axe-core and reports WCAG 2.1/2.2 AA issues: score, grade and failing rules, plus plain-language fix guidance per rule. Read-only, no auth. Streamable HTTP endpoint: https://ratedwithai.com/api/mcpratedwithai.comView setupReconstructDevelopmentCaptured web interfaces, screenshots and flows as evidence for AI coding agents.reconstruct.devView setupRedM NativesDevelopmentLook up RedM / RDR3 natives: exact signatures, hashes and Lua/JS/C# calls, plus enums, blip sprites/styles, ped models, animations and joaat hashing.natives.borderlinerp.comView setupRegSentryDevelopmentInspect authorized static tracking signals and review supplied consent evidence.regsentry.comView setupRein Agent Risk ScaleDevelopmentAgent Risk Scale self-check for agents that can spend money: returns an indicative A-D Agent Risk Rating (NR = not rated) from the controls around the agent, including accountability, spend caps, payee limits and who holds the stop switch. Self-declared and unverified, not a credit rating.rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.ioView setupRelvatoDevelopmentWebsite monitoring for any site, deepest on WordPress WooCommerce: add sites, run checks, read results and get fix prompts.app.relvato.comView setupReMCPDevelopmentSecure OAuth remote MCP control of explicitly paired computers: files, terminal, browser and desktop automation. Device operations can modify state.remcp.siteView setupRemote Desktop CommanderDevelopmentRemote Desktop Commander: use files, terminal and processes on your own computers from any AI app. Sign in with Google or email before connecting.mcp.desktopcommander.appView setupRendlet PDFDevelopmentRemote MCP server that renders HTML, or JSON plus an invoice or itinerary template, to PDF in one call. Free keyless tools: list_capabilities, get_pricing and preview_pdf. Rendering uses headless Chromium and supports Simplified Chinese with Noto Sans SC; other scripts need embedded fonts. Renders use an API key, with a free plan of 100 documents a month.rendlet.comView setupRetascDevelopmentRetasc is a work queue for AI coding agents. Two agents can never hold the same issue. Run npx @retasc/cli@latest bind in the folder to connect Claude Code, Codex, Cursor or another MCP client. The direct mcp.retasc.com endpoint is not documented by the provider.mcp.retasc.comView setupRichAPIDevelopmentLive B2B GTM data API: people, companies, emails, phones, web intelligence. One key. On waterfall endpoints a miss costs zero credits.mcp.richapi.aiView setupRightsholdDevelopmentTrust and rights-verification for the agent economy: agent identity verification (RS-KYA), a public registry and ledger, rights receipts, and a remote MCP server at https://www.rightshold.com/mcp. Requires an Authorization: Bearer API key; email-free agent signup is available at /v1/accounts/signup.www.rightshold.comView setupRiskRouter evidence logDevelopmentHosted MCP endpoint for a tamper-evident evidence log. Without a key, read signed heads, inclusion and consistency proofs and checkpoints; with one, record the salted SHA-256 of a decision record. The record itself never leaves you.api.riskrouter.euView setupRiusDevelopmentQuery your AI agents' traces, errors, cost and alerts in Rius, the agent observability platform. On a machine with a browser, sign in with OAuth; headless agents use a read-scoped API key instead.mcp.eu.console.rius-glassflow.comView setupRobotActionsDevelopmentReal iPhone, Android, Apple TV and Google TV devices plus desktop browsers in the cloud, driven by your AI agent over MCP. Live control, network capture and mocking, Jira, TestRail and Azure DevOps. Free tier.mcp.robotactions.comView setupRocketReachDevelopmentFind verified work emails, phone numbers and company data without leaving the conversation. RocketReach searches 700M+ professional profiles and 60M companies powering sales prospecting, lead generation, recruiting, enrichment, and research.mcp.rocketreach.coView setupRokhaDevelopmentSearch a registry of agent skills and MCP servers, run them for real (sandbox or remote MCP, no install, a trace on every run), and hire proven agents for USDC.rokha.aiView setupRufloDevelopmentOrchestrates intelligent multi-agent swarms for Claude, coordinating autonomous workflows and building conversational AI systems.ruos.cognitum.oneView setuprunnerID by TorchrunnerDevelopmentLogs your AI agent into websites, catches verification codes, and asks you before anything risky.api.runnerid.torchrunner.aiView setup
Endpoints and setup links are checked against provider documentation where available. Verify access, scopes, and rate limits with the provider before connecting.