Développement
33 services indiquent une intégration IA sur leurs propres pages. Les 5 152 serveurs de la catégorie développement du MCP Registry ont chacun leur propre page, dans la liste ci-dessous.
Ce qu’un assistant peut faire avec les serveurs de la catégorie développement
Les serveurs de la catégorie développement donnent à un assistant accès au code et aux systèmes qui le compilent et l’exécutent. Leurs outils typiques recherchent et modifient des dépôts, ouvrent des issues et des pull requests, interrogent des bases de données, lisent des journaux et des données de supervision, déploient sur des plateformes cloud, lancent des tests ou pilotent un navigateur.
Sur les 5 152 serveurs de la catégorie développement qui ont une page ici, 1 897 sont distants - l’assistant se connecte à l’URL de l’éditeur et rien n’est installé - et 3 524 s’exécutent en local à partir d’un paquet ; 269 proposent les deux. 482 des serveurs distants déclarent un en-tête HTTP, généralement pour une clé d’API ; les autres n’en déclarent aucun, ce qui signifie le plus souvent qu’aucune clé n’est nécessaire ou qu’il faut se connecter au service lors de la première connexion du client. 1 537 des paquets locaux déclarent des variables d’environnement, comme des clés d’API, à définir dans le client. La dernière mise à jour de l’un d’eux dans le MCP Registry date du 4 octobre 2026.
Beaucoup s’exécutent en local avec vos propres autorisations ou détiennent des clés de systèmes de production : figez les versions et limitez les clés à ce que la tâche exige.
Les catégories sont attribuées par mots-clés à partir du nom et du résumé propres à chaque serveur, de la même manière pour tous ; quelques serveurs figurent donc ici pour un mot qu’ils partagent avec la catégorie. Un serveur dont les termes ne correspondent à aucune catégorie peut être classé d’après les noms des outils listés lors de la vérification en direct, et sa page l’indique. Glossaire des termes MCP
Éditeurs comptant le plus de serveurs dans la catégorie développement
Firecrawl
Web crawling and extraction API that returns LLM-ready content.
Resend
Email sending API for developers.
Pinecone
Managed vector database.
PlanetScale
Managed MySQL and Postgres databases.
Browserbase
Hosted headless browsers for automation and agents.
Buildkite
CI/CD platform.
Convex
Reactive backend database platform.
Datadog
Infrastructure and application monitoring platform.
Fly.io
Platform for running applications close to users.
Heroku
Cloud application platform.
MongoDB
Document database and Atlas cloud service.
Netlify
Web hosting and deployment platform.
PagerDuty
Incident response and on-call management.
Pulumi
Infrastructure-as-code platform using general-purpose languages.
Redis
In-memory data store and cache.
Render
Cloud hosting for web services, databases and jobs.
Semgrep
Static analysis and code security scanning.
Sentry
Application error monitoring and performance tracing.
Turso
Edge SQLite database service.
Algolia
Hosted search and discovery API.
Clerk
User authentication and management for web apps.
DigitalOcean
Cloud infrastructure provider.
Docker
Container tooling; Docker Hub hosts an MCP server catalog.
HashiCorp Terraform
Infrastructure-as-code tool.
JetBrains
Maker of IDEs such as IntelliJ IDEA and PyCharm.
LaunchDarkly
Feature flag management platform.
Mailgun
Email sending API.
Microsoft Learn
Microsoft technical documentation and training.
Mixpanel
Product analytics platform.
PostHog
Product analytics, session replay and feature flags.
Postmark
Transactional email delivery service.
Twilio
Cloud communications APIs for SMS, voice and email.
Upstash
Serverless Redis, vector and messaging services.
Comment les services de la catégorie développement se connectent aux assistants
Chacun des 33 services ci-dessus indique au moins un moyen d’accès. Décompte par type :
Serveur MCP : 26. Un serveur Model Context Protocol : une interface standard à laquelle les assistants IA comme Claude, ChatGPT et d’autres peuvent se connecter pour appeler directement les outils du service.
Application ChatGPT : 1. Une application dans ChatGPT : une fois que vous l’avez connectée, l’assistant peut appeler le service pendant la conversation.
Connecteur Claude : 3. Un connecteur dans Claude : une fois que vous l’avez connecté, l’assistant peut lire des données du service ou y effectuer des actions.
Description OpenAPI : 2. Une description d’API publiée, lisible par une machine, qu’un agent peut lire pour apprendre à appeler le service.
llms.txt : 24. Un guide en texte brut, à l’adresse /llms.txt, qui indique aux systèmes d’IA ce qu’est le site et où se trouvent ses pages principales.
Serveurs distants de la catégorie développement à ajouter par URL (1 897)
Rien à installer : un assistant qui accepte les serveurs MCP distants se connecte au point de terminaison indiqué sur la page de chaque serveur. Les 20 mis à jour le plus récemment, les plus récents d’abord.
| Serveur | Exécution | Mis à jour |
|---|---|---|
| CloudovňaOrder, configure and deploy Docker containers and PostgreSQL or SQL Server databases in the EU. | Distant · HTTPVérification en direct : connexion requise | 4 oct. 2026 |
| Mlola UIMlola UI components, tokens and design rules for coding agents, with a markup checker. | Distant et local · HTTP et stdioVérification en direct : ✓ poignée de main | 4 oct. 2026 |
| Agentic KeychainAgent Skill ROI Registry & Benchmarking. It sells skills for log triage and repository mapping. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| AgentSpaceGive your agent a persistent workspace: files, a code sandbox and a public URL to publish to. | Distant · HTTPVérification en direct : connexion requise | 3 oct. 2026 |
| ai·rete·ragAuthor rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why. | Distant et local · HTTP et stdioVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| ArcticRead Robinhood Chain live: scan a token, trace its deployer, list new launches. | Distant · HTTPVérification en direct : ✗ pas de poignée de main | 3 oct. 2026 |
| Astro Agents - deterministic Western + Vedic astrologyNatal charts, transits, kundli, dashas, panchang, Gun Milan. JPL DE440, no LLM, hashed. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| BlackVeil DNS & Email Security ScannerDNS and email security scanner with 81 MCP tools for SPF, DMARC, DNSSEC, SSL, and brand audits. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| Clickwise Affiliate NetworkMulti-store GTIN product feed, tracked affiliate links and programs. Free sandbox key, no account. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| ContentrainGit-native content governance for AI agents - 27 deterministic MCP tools over stdio and HTTP. | Distant et local · HTTP et stdio | 3 oct. 2026 |
| ContextStream MCP ServerProject memory, semantic code search, and grounded agent context. | Distant et local · HTTP et stdioVérification en direct : connexion requise | 3 oct. 2026 |
| CustomDomain™Custom domains for SaaS and AI agents: search, buy, connect DNS, verify ownership and issue HTTPS. | Distant · HTTPVérification en direct : connexion requise | 3 oct. 2026 |
| CVE Risk CheckTriage a CVE: how severe it is, whether it is exploited, and how likely exploitation is. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| DefaultRankCheck npm dependencies for outdated majors, and see which dev tools AI models pick. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| Domain IntelligenceWHOIS/RDAP, DNS, SSL, live subdomains with IPs, and SPF/DMARC/DKIM for any domain. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| DvtDashboards as data. Author, validate, render, and share dvt dashboards from any MCP client. | Distant · HTTPVérification en direct : connexion requise | 3 oct. 2026 |
| ExactGroundCheck npm/PyPI packages exist and that a function or method exists in an exact package version. | Distant · HTTPVérification en direct : connexion requise | 3 oct. 2026 |
| Git.TopEvidence-backed open-source project search, recommendations, alternatives, and comparisons. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| Google Play Reviews (via Apify)Google Play reviews for AI agents: any app, country or language, with developer replies. | Distant · HTTPVérification en direct : connexion requise | 3 oct. 2026 |
| Industry PulseWhat happened in AI coding agents like Claude Code, Codex, Cursor and Copilot, and what people say. | Distant · HTTPVérification en direct : ✓ poignée de main | 3 oct. 2026 |
Paquets locaux de la catégorie développement (3 524)
Programmes qu’une application de bureau, un éditeur de code ou un agent en ligne de commande lance sur votre propre ordinateur, depuis npm, PyPI, une image de conteneur ou un autre registre de paquets. Les 20 mis à jour le plus récemment, les plus récents d’abord.
| Serveur | Exécution | Mis à jour |
|---|---|---|
| CliCross-tool decision memory for AI coding agents: search your decision graph, check changes over MCP. | Local · stdio | 4 oct. 2026 |
| corralctlSearch code and symbols across every clone in your corralctl workspace. Zero network calls. | Local · stdio | 4 oct. 2026 |
| Mlola UIMlola UI components, tokens and design rules for coding agents, with a markup checker. | Distant et local · HTTP et stdioVérification en direct : ✓ poignée de main | 4 oct. 2026 |
| repomapA map of your codebase for AI agents: code graph, search, call paths and change impact. No API key. | Local · stdio | 4 oct. 2026 |
| 4da MCP ServerUpgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans. | Local · stdio | 3 oct. 2026 |
| Action1 MCPEvery Action1 endpoint, plus fleet-wide patch and vulnerability views across all your organizations. | Local · stdio | 3 oct. 2026 |
| adrkit decision memoryDeterministic, offline, read-only ADR decision memory for coding agents. No model or network calls. | Local · stdio | 3 oct. 2026 |
| AI Workbench MCPRead-only MCP server for reusable AI prompts and assistant blueprints. | Local · stdio | 3 oct. 2026 |
| ai·rete·ragAuthor rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why. | Distant et local · HTTP et stdioVérification en direct : ✓ poignée de main | 3 oct. 2026 |
| AIContextBuilderSymbol-aware C# and.NET code context for AI coding assistants. | Local · stdio | 3 oct. 2026 |
| Appmetrica MCPAppMetrica (Yandex) analytics: reports, funnels, segments, dashboards, logs export, push. | Local · stdio | 3 oct. 2026 |
| AstriaTurn any codebase into a queryable knowledge graph - offline-first, zero API keys. | Local · stdio | 3 oct. 2026 |
| Atlas MCPBase token safety checks (honeypot test, liquidity, new launches), paid per call in USDC via x402. | Local · stdio | 3 oct. 2026 |
| Awareness LocalLocal-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls. | Local · stdio | 3 oct. 2026 |
| BenziCompiler-backed code intelligence: calls, data flow, references and class hierarchy as tools. | Local · stdio | 3 oct. 2026 |
| BomlyGive your coding agent the dependency graph it is about to change: scan, diff, explain, audit. | Local · stdio | 3 oct. 2026 |
| CejelOffline deterministic engineering-trust certificates for repositories, with no telemetry. | Local · stdio | 3 oct. 2026 |
| ClaudexorRoute coding work across Claude Code, Codex, Cursor, and OpenCode with shared context. | Local · stdio | 3 oct. 2026 |
| cmssyHeadless CMS whose page sections are defined by your own code: pages, records, media, commerce. | Local · stdio | 3 oct. 2026 |
| CodeInspectusLocal-first MCP security scanner and CLI for AI-generated applications. | Local · stdio | 3 oct. 2026 |
Tous les serveurs de la catégorie développement dans le MCP Registry (5 152)
Tous les serveurs de cette catégorie qui remplissent les critères d’admission de l’annuaire - un vrai résumé, un dépôt ou un site web indiqué, et un point de terminaison ou un paquet -, de A à Z, chacun avec sa propre page.
| Serveur | Exécution |
|---|---|
| .FAF ContextFAF Context - persistent project context for Cursor, VS Code and every MCP-compatible IDE. | Local · stdio |
| .NET Debugger for MCPGive an AI agent a real.NET debugger: breakpoints, stepping, locals, expression evaluation. | Local · stdio |
| .NET MCP ServerAI assistant access to.NET SDK for projects, packages, building, testing, and development tools. | Local · stdio |
| .promptsPrompts, the home to all your AI prompts, everywhere you need them. | Distant · HTTPVérification en direct : connexion requise |
| @imqueueSearch @imqueue docs and scaffold typed services & clients from your AI coding agent. | Distant et local · HTTP et stdioVérification en direct : ✓ poignée de main |
| 🐴 GulltopprResolve any EVM contract ABI (even unverified, via decompilation), read, simulate, prepare txs. | Distant · HTTPVérification en direct : ✓ poignée de main |
| 11agents Cloud MCPCloud MCP for project data, analytics, research, content planning, media generation, and growth. | Distant · HTTPVérification en direct : ✗ pas de poignée de main |
| 1Claw VaultHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning. | Local · stdio |
| 1lev1Track partnership work, log mission hours, and see what needs your approval on 1lev1.com. | Distant · HTTPVérification en direct : ✓ poignée de main |
| 21st.devFind UI components and themes, retrieve code, and generate with hosted 21st AI when enabled. | Distant · HTTPVérification en direct : connexion requise |
| 2Captcha MCPFull 2Captcha API (43 tools) for Claude Code: 31 captcha solvers + management + webhook. | Local · stdio |
| 2native SSH MCP ServerSSH-based MCP server for remote command execution and file transfer. Credentials stay local. | Local · stdio |
| 37soul MCPRun your 37Soul AI characters from any MCP client: list them, chat with them, and tell them to post. | Distant et local · HTTP et stdioVérification en direct : connexion requise |
| 3dstreetDrive an open 3DStreet scene tab from Claude Desktop or Claude Code via MCP tool calls. | Local · stdio |
| 3ilm MCPSearch 1,032 verified contract vulnerability findings from Sherlock audits by pattern. | Local · stdio |
| 402cronPaid cron for AI agents: we call your https URL on schedule, signed. No account, paid with x402. | Distant · HTTPVérification en direct : ✓ poignée de main |
| 4da MCP ServerUpgrade intelligence for AI agents: what an upgrade changes, where it touches your code, CVE scans. | Local · stdio |
| 4q TokenzMCP proxy that reduces token usage by exposing only mcp_search and mcp_call. | Local · stdio |
| 7IT SolutionsStore speed, web-app security checks, automation ROI, checklists and guides from 7IT Solutions. | Distant · HTTPVérification en direct : ✓ poignée de main |
| A2a AuditorScans Agent2Agent (A2A) protocol code for webhook SSRF, missing auth, and credential exposure. | Local · stdio |
| A2adependencyinspector MCPRemote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready evi. | Distant · HTTPVérification en direct : ✗ pas de poignée de main |
| A2ahubReliable handoffs between autonomous agents, using a Git repository both sides can inspect. | Local · stdio |
| A2AL DaemonMakes any AI agent globally reachable and discoverable-no cloud, domain, or port forwarding needed. | Local · stdio |
| A2AParkPublic behavioral test environment for AI agents with stateful rides and signed scorecards. | Distant · HTTPVérification en direct : ✓ poignée de main |
| A2areplayreceipt MCPRemote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence. | Distant · HTTPVérification en direct : ✗ pas de poignée de main |
| A2dbSafe, read-only database access for AI agents. 5 databases, batch queries, SQLGlot. | Local · stdio |
| AARF Utility NetworkPaid AI utilities for web comparison, code checks, document extraction, security, and research. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Abap Adt MCPABAP development from Claude and other MCP hosts: source, transports, tests, ATC, debugger. | Local · stdio |
| Abap MCPOffline SAP ABAP/RAP tools for AI agents: lint, Cloud readiness, released APIs, knowledge. | Local · stdio |
| abcopABC complexity gate for AI-written code with an MCP inspection tool. | Local · stdio |
| ABMeterRun A/B experiments through your AI assistant. SDKs for Ruby, Python, JS, Node, React Native, Go. | Distant · HTTPVérification en direct : connexion requise |
| Abnormal MCP ServerAbnormal Security MCP: threats, search, remediation, ATO cases, vendor/BEC, and evidence download. | Local · stdio |
| Abnormal SecurityMCP server for Abnormal Security - AI-powered email threat detection, cases, and remediation. | Local · stdio |
| Abnormal SecurityMCP server for Abnormal Security - AI-powered email threat detection, cases, and remediation. | Local · stdio |
| Abnormal Security MCPAbnormal Security email threats, cases, and reporting in your terminal and your AI agents. | Local · stdio |
| AccAutodesk Construction Cloud: issues, RFIs, sheets, coordination. | Distant · HTTPVérification en direct : connexion requise |
| Accelerators36 tools for AWS infrastructure, security compliance, AI workflows, and ACI governance. | Local · stdio |
| Accessibility Statement LintChecks the accessibility statement you already published against the EU model statement and its two. | Local · stdio |
| Account PoolExclusive, crash-safe leases on a pool of test accounts for parallel agent QA runs. | Local · stdio |
| AchlensLocal-first MCP server and CLI for validating and generating synthetic ACH files. | Local · stdio |
| Acmi MCPPersistent agent memory via ACMI - Profile/Signals/Timeline. 16 tools on Upstash Redis. | Distant et local · HTTP et stdioVérification en direct : connexion requise |
| ACMSApple Container MCP Server (ACMS) provides access to Apple's container CLI tool on macOS. | Local · HTTP |
| Acorn ReplyRead and edit your Acorn Reply knowledge base from any MCP client. | Distant · HTTPVérification en direct : connexion requise |
| ACR - Agent Composition RecordsInteraction profile registry for AI agents. Log interactions, query behavioral lenses. | Local · stdio |
| Acronis MCPThe first real CLI for the Acronis Cyber Protect Cloud platform - every tenant, agent, and usage. | Local · stdio |
| Acta - Verifiable Agent MemoryVerifiable agent memory with signed ledger receipts - verify every write offline. | Local · stdio |
| Action Runtime Sunset LintFinds the GitHub Actions steps that stop running on 2026-09-23, with the version to move to. | Local · stdio |
| Action1 MCPEvery Action1 endpoint, plus fleet-wide patch and vulnerability views across all your organizations. | Local · stdio |
| ActionforgeMCP server for ActionForge: expose your account's tools to Claude and any MCP client. | Local · stdio |
| Actions Deprecation Lint 2026Node 20 is removed from GitHub-hosted runners on 2026-09-23 and ubuntu-22.04 deprecation opens 2026. | Local · stdio |
| ActionsPulseReal-time GitHub Actions observability: DORA Metrics, Cost Analysis, CI/CD Health dashboards. | Local · stdio |
| Activitypub MCPRead-only-by-default MCP server: let LLMs explore the Fediverse - Mastodon, Misskey, Pleroma. | Local · stdio |
| adb-mcp: Android emulator and device control over adbDrive an Android emulator or device over adb: screenshot, inspect UI, tap, type, build and test. | Local · stdio |
| ADCIRC Model Setup MCP ServerADCIRC model configuration debugging, parameter lookup, and validation. | Local · stdio |
| Adguardhome MCPQuery your AdGuard Home: status, stats, query log. Endpoints per official docs. | Local · stdio |
| ADITUS Developer Portal MCPRead-only docs for the ADITUS event-technology APIs (ticketing, access, BI) and Shop Micro Frontend. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Adobe MCPDrive Adobe CC (AE, Photoshop, Illustrator, Premiere, Character Animator) from any MCP client. | Local · stdio |
| AdoMcpDatabase MCP server for schema discovery, comments, and SQL queries. | Local · stdio |
| adrkit decision memoryDeterministic, offline, read-only ADR decision memory for coding agents. No model or network calls. | Local · stdio |
| AdsideAI agents that manage paid ads on Meta, LinkedIn, and Google Ads from any MCP client. | Distant · HTTPVérification en direct : connexion requise |
| AdsTurbo Creative MCPLocal-only MCP server and CLI for AI video ad briefs, UGC scripts, storyboards, and prompts. | Local · stdio |
| Advanced GitLab MCP server58 CQRS tools exposing 230 GitLab operations across 26 entity types. | Local · stdio |
| Advanced Zebrunner MCP ServerAdvanced analytics, reporting, and safe mutations for Zebrunner. 64 tools, 14 resources, 17 prompts. | Local · stdio et HTTP |
| AegisCharter-bound defensive security copilot: secrets, obfuscation, deps, Dockerfile, IaC scans. | Local · stdio |
| Aegis - AI Agent GovernancePolicy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging. | Local · stdio |
| AEO ScannerAI visibility for ChatGPT/Perplexity/Claude - triple score (AEO+GEO+Agent) with fix code. Free. | Distant et local · HTTP et stdioVérification en direct : ✓ poignée de main |
| Aesthetic ComputerMCP server for aesthetic.computer - publish JavaScript, KidLisp art, and clock melodies. | Local · stdio |
| AetherMarketplace where AI agents hire other agents, paid per call in USDC. Plus LLM inference. | Distant · HTTPVérification en direct : ✓ poignée de main |
| AethereumThe team layer for AI coding agents: shared contracts, collision alerts, E2EE sessions. | Distant et local · HTTP et stdioVérification en direct : connexion requise |
| Aethis MCPDeterministic eligibility decisions and test-driven rule authoring via the Aethis developer API. | Local · stdio |
| AeviaAI-powered life cycle assessment and modelling: connect to LCA databases, build and analyze systems. | Distant · HTTPVérification en direct : connexion requise |
| Aevum SecurityBrowse Aevum Security's Singapore cybersecurity services and submit a business enquiry. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Afgong Sqlite MCP ServerExplore your Messages SQLite database to browse tables and inspect schemas with ease. Run flexible… | Distant · HTTPVérification en direct : ✗ pas de poignée de main |
| Afi MCPThe first CLI for Afi SaaS backup - full public-API coverage plus the fleet-wide coverage. | Local · stdio |
| AfriResolveAfrican intelligence infrastructure for AI apps, developers, and data products via MCP. | Distant · HTTPVérification en direct : ✓ poignée de main |
| aft.pageDeploy HTML or dist/ to a live HTTPS URL. No account. Drop, MCP, or CLI. | Distant · HTTPVérification en direct : ✓ poignée de main |
| AfterpathsSession memory for AI coding agents. Search past sessions, extract rules, and track what works. | Local · stdio |
| Ag BashSandboxed AI-native bash with 70 agentic tools: run_bash, code edit/diff, WASM Python/JS. | Local · stdio |
| Aganium MCP-SERVERBridge MCP servers to the AGENIUM agent:// network with DNS resolution and mTLS. | Local · stdio |
| Age Gate Lint8 rules for Ofcom's highly effective age assurance duty, in force since 25 July 2025, where the pena. | Local · stdio |
| AgenceAI governance MCP server - policy enforcement, skills, memory, multi-LLM consensus. | Local · stdio |
| AgenshiveAI agents post reproducible tests, answer questions and verify each other's results. | Distant · HTTPVérification en direct : connexion requise |
| Agent Abilities for MCPSelf-hosted WordPress MCP server with per-capability permission controls and a full audit log. | Distant · HTTP |
| Agent ArcadeCreate, test and play AI-native games through server-authoritative contracts. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Agent AuditTurn Lighthouse audits into coding-agent fix packs for Claude Code, Cursor, and Copilot. | Local · stdio |
| Agent BillboardRead and post to The Agent Billboard on Solana, with spend limits in code and a reasoning log. | Local · stdio |
| Agent BlueprintExplore and download AI agent blueprints as Agent Skills directories for coding agents. | Local · stdio |
| Agent BoosterCut AI agent token costs 5-15x - routes only relevant code symbols instead of full files. | Local · stdio |
| Agent Channel PlacementPlacement across agent channels: MCP, Cursor, Claude, ChatGPT, npm, docs, Smithery, Glama. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Agent Claim MCPFile-claim coordination for parallel AI coding agents: claim files before edits, no stomping. | Local · stdio |
| Agent Cloud ToolsFree no-signup cloud tools for AI agents: file transfer, static site hosting, memory, handoff. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Agent CommsCross-harness communication mesh for LLM agents - rooms, DMs, presence, and visibility over TCP. | Local · stdio |
| Agent DiscoverMCP server registry and marketplace - discover, install, activate tools on demand. | Local · stdio |
| Agent Droid BridgeMCP server giving AI agents eyes and hands inside Android devices via ADB. | Local · stdio |
| Agent DVRAsk your security cameras anything and set up alert rules in a sentence. Built into Agent DVR. | Distant et local · HTTP et stdioVérification en direct : connexion requise |
| Agent EvalStatistical regression testing for LLM agents: p-value, effect size, and CI on behavior change. | Local · stdio |
| Agent Forum · Free Tools + Open Falsification ChallengeFree: ed25519 hash timestamps, randomness tests, lottery data. Open falsification challenge. | Distant · HTTPVérification en direct : ✓ poignée de main |
| Agent Guard MCPGit-aware safe file ops for AI agents: delete anything except git-tracked source code. | Local · stdio |
| Agent GuardsAll six agent guard suites in one local MCP server, with optional cloud intelligence. | Local · stdio |
| Agent GuestbookRead and verify the Blue Cloud Cyber agent guestbook, and sign one Ed25519 entry per UTC day. | Local · stdio |