Pod

Available as Markdown and JSON. Pod is also available over MCP.

MCP Servers in the Claude Directory

Current MCP listings Pod ingested directly from Anthropic's Claude directory. Membership is source provenance, not an inferred client-compatibility claim.

2,506 servers, ordered by decision readiness and adoption — GitHub stars and npm downloads where available, then reported issue volume. Pod has connected to 2252 of them; the rest are publisher-reported and unverified.

Showing 2176–2200 of 2,506 · page 88 of 101.

Agentwork

Agentwork is your company brain. It connects to the tools your team already uses (Slack, Google Workspace, Notion, Linear, GitHub, email, the CRM) and answers questions across all of them in plain language, with sources you can check. Think of it as enterprise search that gives you the answer instead of a list of links, and a knowledge base that writes itself instead of a wiki nobody updates.

With this connector, Claude can ask Agentwork on your behalf.

Answers to the questions that normally cost half a day or three interruptions. Who owns the billing service and what is risky to touch in it. What we promised Acme about data residency. How refunds work on annual contracts upgraded mid-term. Why we moved off the old onboarding flow last year. Each answer comes with the records it came from, and each is filtered to what you are allowed to see.

Work done with company context. Hand Agentwork a task and it runs it with your company's memory and connected tools, then returns the result: a briefing on this quarter's churn risks, an analysis of a spreadsheet, a first draft written from what the company actually knows. Tasks appear in your team's Agentwork inbox. Anything that needs a human approval in Agentwork is left for you, and the result says so, unless your organisation has opted that tool out of approval.

Gaps get closed instead of guessed. When the answer is not written down anywhere, or two sources disagree, Agentwork asks the person most likely to know, in one short question, and keeps their reply for everyone. The knowledge base gets better every time someone uses it.

You stay in control. Agentwork respects the access rules your people already have, so nobody gets an answer they should not. It is hosted in the EU.

You need an Agentwork account with at least one source connected. Sign in with your Agentwork login when you connect; no API key is required.

4 tools reported — Publisher-reported; not verified by Pod.

AlterVision

O conector oficial da AlterVision dá ao Claude acesso somente leitura aos indicadores das suas lojas físicas, para você perguntar em linguagem natural em vez de montar relatório.

Com ele o Claude responde sobre:

• Vendas e conversão — faturamento, número de vendas, taxa de conversão, PA (peças por atendimento), preço médio por peça e uptime das câmeras, por loja e dia a dia. • Fluxo — contagem de visitantes e média diária por loja. • Metas — realizado x projetado de faturamento, fluxo, conversão e PA para cada meta ativa, com projeção de fechamento, metas escalonadas e recorte por vendedor. • Corridas — corridas entre lojas ou entre vendedores, com KPI, período, participantes e ranking atual. • Motivos de não conversão — distribuição dos motivos, receita perdida, comparação com o período anterior e recortes por subclassificação, loja e vendedor. • Transcrições de não conversão — o relato do próprio vendedor sobre o que o cliente pediu: ruptura de estoque, marcas, formas de pagamento, objeção de preço.

Perguntas como "como foi a conversão das minhas lojas essa semana?", "estou batendo a meta do mês?", "por que os clientes não estão comprando na loja X?" ou "quem está ganhando a corrida?" são respondidas direto no Claude.

Todas as ferramentas são somente leitura: o conector não altera nenhum dado.

Pré-requisitos: conta AlterVision ativa com acesso a pelo menos uma loja. A conexão é feita por OAuth com as suas credenciais do painel, e o Claude enxerga exatamente as lojas que o seu usuário já enxerga lá. Corridas, motivos de não conversão e transcrições dependem do AlterVez estar ativo na loja.

9 tools reported — Publisher-reported; not verified by Pod.

Anarlog

Anarlog is a private, local-first AI notetaker for meetings. This connector gives Claude read-only access to the meetings you have chosen to share with Anarlog Cloud: notes, AI summaries, participants, action items, transcripts, and the history of recurring meetings.

Ask Claude to find a meeting by title or date, summarize what was decided, pull the action items you own, compare this week's standup with last week's, quote what someone said from the transcript, or draft a follow-up email grounded in the actual conversation.

How it works: Anarlog records and transcribes on your computer. Nothing reaches the cloud until you enable Cloud API & Connectors in Settings → Developers, which uploads a server-readable snapshot of your meetings. Disabling it deletes the snapshots and revokes connector access. The connector never writes or deletes anything; editing notes stays in the Anarlog app.

Requires an Anarlog Pro account with Cloud API & Connectors enabled. Sign in with your Anarlog account when Claude asks; no API key is needed.

5 tools reported — Publisher-reported; not verified by Pod.

ANAV

ANAV est un logiciel de planification et de suivi de chantier pour les professionnels du BTP. Il réunit le planning des équipes, la charge de travail et le suivi des temps.

Le connecteur permet de consulter vos affaires, tâches, plannings et temps enregistrés depuis Claude, ainsi que de créer ou modifier des données selon vos autorisations.

Vous choisissez les organisations accessibles lors de la connexion. Les opérations restent limitées à vos droits ANAV. Vous pouvez modifier les organisations autorisées ou révoquer la connexion depuis Applications connectées dans ANAV.

90 tools reported — Publisher-reported; not verified by Pod.

Anomity

Anomity is an endpoint security and governance platform for agentic AI. A lightweight daemon on each managed device continuously inventories the AI tooling in use - MCP servers, coding agents, skills and instruction files, credentials, and account types - giving security teams visibility into a layer that sits between EDR and network controls.

This connector lets you query that telemetry directly in Claude, without opening the console.

What you can ask:

Fleet overview - device counts by status (online, stale, offline) and open or critical finding counts across the fleet. MCP inventory - every MCP server detected across managed devices, grouped by trust level: official, community, or unknown-origin. AI accounts - which devices authenticate with corporate accounts versus personal ("shadow") accounts, plus data-sharing settings and BYOK configuration. Secret exposure - plaintext credentials found in AI configuration files, ranked by severity and pattern type. Capability surface - inferred permissions across MCP servers, flagging overprivileged devices and risky capability combinations. Skill and instruction-file risk - CLAUDE.md-class files and skills flagged by on-device content scanning for prompt injection, exfiltration patterns, and unsafe directives. Findings - policy violations filterable by status (open, acknowledged, resolved). Compliance status - readiness across SOC 2, ISO 42001, NIST AI RMF, and the EU AI Act, mapped to the controls each finding affects. Audit trail - 90 days of change history: every MCP server added or removed, every permission modified, on every device.

Typical uses: investigating an alert without context-switching, preparing evidence for an audit, answering "which of our machines can reach production data through an agent?", or generating a weekly AI activity report.

Anomity's approach is to govern rather than block - give teams the visibility to set informed policy instead of shutting down the tools developers are already using.

10 tools reported — Publisher-reported; not verified by Pod.

Appier Enterprise MCP Server

Connect Claude securely to Appier Enterprise products through the Model Context Protocol. The connector helps marketing, data, and growth teams use Appier context directly within Claude. Teams can explore customer insights, understand campaign and journey performance, work with audiences and marketing content, and support cross-channel planning. It integrates with Appier products including AIQUA and AIRIS, with additional Enterprise capabilities added incrementally. Available tools and actions depend on the products, permissions, and connector version enabled for your organization. Authentication uses Appier OAuth, and access follows each user’s existing Appier project permissions. An eligible Appier Enterprise account is required.

38 tools reported — Publisher-reported; not verified by Pod.

Axle Connect

Axle Connect brings your work into Claude. Ask questions, stay informed, and keep your day moving.

Available to members of Axle’s private business community. Sign in with your Axle account. Your existing permissions apply.

30 tools reported — Publisher-reported; not verified by Pod.

Base.com

Base MCP connects Claude to your Base account for read-only access to your store data. Once connected via OAuth 2.1 (with your login and consent through Base's screen), Claude can check account details, look up orders, review product listings, and check inventory levels — all without leaving the conversation. The connector only reads data; it cannot create, modify, or delete anything in your Base account.

1 tools reported — Publisher-reported; not verified by Pod.

beehiiv

Claude can plug directly into your beehiiv workspace, delivering deeper insights and more tactical support for your business. It has access to your entire beehiiv ecosystem, from podcasts and automations to segments, products, monetization data, and more. Use it to streamline your operations and spend more time on the work that matters.

198 tools reported — Publisher-reported; not verified by Pod.

Beeline

Your personal travel agent, built into Claude. Search, book, and manage flights and hotels from major airlines and hotels worldwide. Beeline allows you not just to book but also to change a booking, add a request, or cancel - all directly in Claude.

25 tools reported — Publisher-reported; not verified by Pod.

Bikky

Bikky is a customer data platform for restaurants. It unifies point-of-sale, online ordering, and loyalty data into per-guest profiles and analytics, so a restaurant group can see who its guests are, what they order, and how that changes over time.

This connector gives a Bikky customer read-only access to their own data from Claude. Ask in plain language — "what were my top ten menu items by revenue last month", "how many first-time guests came back in Q2", "which location had the biggest drop in average check" — and Claude answers against that business's own orders, guests, menu, location, and segment data.

5 tools reported — Publisher-reported; not verified by Pod.

CarGurus

Find the right new or used car by describing what you're looking for in plain language.

Search vehicle listings using specific criteria like price, make, model, or mileage - or broader needs such as "cars that are safe in the snow," "great family cars," or "reliable commuter vehicles."

Explore matching listings with high-quality photos, full vehicle specifications, safety information, and dealer details. Whether you're comparing options or narrowing down to a shortlist, the app helps you translate real-world needs into confident car-buying decisions.

2 tools reported — Publisher-reported; not verified by Pod.

Carpedia

O Carpedia é um catálogo do mercado automotivo brasileiro para consultar fichas técnicas, itens de série e opcionais, planos de manutenção, resumos editoriais, emplacamentos e preços de referência FIPE com histórico.

Com o Carpedia, você pode navegar por marcas, modelos e versões; buscar veículos por texto livre; consultar especificações e dados de consumo do PBEV-Inmetro; verificar equipamentos; consultar revisões previstas no manual do proprietário; obter imagens, resumos de modelos e informações de marcas; acompanhar rankings de emplacamentos; e estimar custos de uso, incluindo IPVA por estado. Também pode consultar a cota, o consumo e o status de uma cobrança de créditos já existente na própria conta de API.

As respostas distinguem informação ausente de informação negativa: um equipamento não rastreado não significa que o veículo não o possui. Estimativas e projeções são identificadas, e cálculos parciais de custo não são apresentados como custo completo de posse. Os rankings informam seu denominador e período de referência.

As ferramentas consultam informações; não alteram o catálogo, não criam cobranças e não executam pagamentos. O uso está sujeito à cota e às condições da conta de API. A autorização não dá acesso a favoritos, ao painel administrativo ou a conversas e arquivos do usuário.

Disponível em português para o mercado brasileiro.

16 tools reported — Publisher-reported; not verified by Pod.

Celero.io

Celero turns documents, presentations, and PDFs into microsites: shareable web pages with a link and per-page analytics on who opened it and how far they read. Connect Celero to Claude to publish links without leaving the chat. Give it a PDF, PowerPoint, Word, Excel, Design file, video, or image - and back a link that you can share instead of an attachment. List the microsites in your account and add a new version to an existing microsite, so a link you've already shared stays live and shows the updated content. Common uses: sharing a finished deck as a trackable link, updating a shared link with new content, and checking what's been published without opening the dashboard. Sign in with your own Celero account. Any tool that creates or changes content asks for confirmation first.

5 tools reported — Publisher-reported; not verified by Pod.

Cezanne HR Learning

Cezanne HR Learning is a people development platform that brings learning, skills and performance together in one place. This connector gives Claude authenticated access to your organisation's Cezanne HR Learning workspace through the Cezanne HR Learning V1 API.

Read across your workspace:

Make changes where your permissions allow:

Typical questions and requests:

Access and permissions: you sign in with your own Cezanne HR Learning credentials over OAuth. The connector acts as you and inherits your permissions, so it reaches only the data and actions your account already allows. Every tool is annotated as read-only or as modifying data, so Claude's permission prompts distinguish a lookup from a change or a deletion.

Before connecting you will need a Cezanne HR Learning account with connector access enabled by Cezanne HR, and your workspace address, for example acme in acme.learnamp.com.

Cezanne HR Learning is the first party for this API. The connector reaches your own Cezanne HR Learning tenant and no third-party service sits in the path.

58 tools reported — Publisher-reported; not verified by Pod.

Clipform by clipform

Clipform turns a conversation into an interactive, video-first form. Describe the quiz, survey, feedback form, or sign-up you want, and Claude builds it in your Clipform workspace - questions, options, scoring, answer feedback, an end screen, and a shareable link - in one go. Respondents can reply by video, audio, or text, which lifts completion and gives you richer answers than a plain web form.

Ask for changes in plain language: add or reword a question, reorder the flow, change settings, publish or unpublish. Then ask what came in - response counts, per-option breakdowns, and recent open-text replies - without leaving Claude.

What you can do:

Great for quizzes, feedback surveys, contact and sign-up forms, and video testimonial requests - anywhere a conversation converts better than a static form.

Your workspace, plan limits, and existing forms are always respected, and deleting a form or question asks you to confirm first. Requires a Clipform account, free to start.

15 tools reported — Publisher-reported; not verified by Pod.

CoCanvas

Initial release of the CoCanvas plugin for Claude.

Connect Claude to your CoCanvas workspace and ask about your own projects: status updates, rooms and their product and paint selections, moodboards, tasks, products, vendors, clients, RFQs and purchase orders. Claude can also do work for you inside CoCanvas: create an editable moodboard from a room's current selections, add tasks, notes and products, save files into the AI Assistant folder, and draft purchase orders or invoices that you review and send yourself.

You choose what Claude can reach when you connect ("Look things up" and, optionally, "Draft and add things"), and you can narrow or disconnect it at any time from Settings → AI assistants. Financial data (invoices, payments, budgets, balances) is not available to assistants in this release. Claude can never send invoices or purchase orders, record or refund payments, message clients or vendors, delete anything, or change your team, billing or integrations.

34 tools reported — Publisher-reported; not verified by Pod.

Common Sense Privacy

Common Sense Privacy brings trusted, independent privacy evaluations directly into your Claude conversations. No tab-switching, no searching, no friction.

Common Sense Media has reviewed hundreds of apps, platforms, and edtech tools to assess how they handle personal data. Each evaluation examines whether a product sells or shares user information, displays targeted advertising, allows third-party data collection, or builds data profiles for commercial purposes. Products that meet the highest standards earn the Common Sense Privacy Seal, a recognised mark of responsible data practice.

2 tools reported — Publisher-reported; not verified by Pod.

Contentful MCP

About the Contentful Remote MCP App

The Remote MCP App makes your Contentful spaces accessible to AI agents, enabling them to perform content management operations. Once installed, the app gives space admins a simple dashboard to control exactly which Contentful tools are available to AI clients, like enabling read-only access for marketing teams auditing content, or unlocking write tools for developers building agentic workflows. Each space gets its own configuration.

Features

Per-Space MCP Permissions

Configure which tools are exposed to AI clients on an environment-by-environment basis, scoping access to only what each team or workflow needs.

Granular Tool Control

Toggle individual tools on or off — restrict to read-only content queries, or enable write operations for agentic content pipelines.

Admin Dashboard

A simple, purpose-built UI for space administrators to review and update tool permissions without touching code.

Requirements

This app must be installed in a Contentful environment before the Remote MCP server can be used within that environment.

70 tools reported — Publisher-reported; not verified by Pod.

crm.care

crm.care is the campaign execution layer for B2B marketing teams. Connect it alongside your CRM and analytics connectors and an assistant gains what none of those provide: it can turn a brief into a live campaign and track what comes back.

Four tools run that loop against a connected workspace:

• launch_campaign turns a brief into a draft campaign, returning its id and URL. It creates the draft only — generation, review and publishing stay in the workspace, and the action is logged and undoable.

• list_campaigns and get_campaign_status read it back: what is running, its content, its CRM sync state.

• get_goal_pnl returns goal roll-ups — target pipeline vs influenced, budget vs spend, ROI, pacing. Check it before proposing more work.

These four need a workspace API token, minted by an admin. Without one they return a short instruction on how to connect, not an error.

Campaigns publish through the workspace's connected marketing automation platform — today Account Engagement (Pardot) or HubSpot.

Three more work immediately, with no account and no key:

• preflight_email_html audits marketing email HTML before it is sent: Outlook-safe layout, inline styles, width, alt text, unsubscribe link, merge-tag balance (%%...%% and {{...}}), Gmail's ~102KB clip.

• score_campaign_brief scores a brief 0-100 on audience specificity, objective measurability, message clarity, channels, timing and tone.

• audit_nurture_sequence checks touch count, cadence gaps, subject hygiene and give-then-ask arc.

All three are rule-based: no LLM runs server-side, so they are free and deterministic.

The rest answer questions about crm.care itself: fit, pricing, comparisons.

The same token unlocks 26 further tools across calendar, emails, social posts, assets, brand voice, budget and CRM sync. Every tool that changes anything is off until an admin grants it individually, and every change is reversible.

Full API reference: https://crm.care/docs/api

14 tools reported — Publisher-reported; not verified by Pod.

Datadog

Analyze, investigate, and act on your Datadog telemetry directly from Claude using natural language. Ask questions about your production applications. Identify, visualize, and remediate issues in your critical services. Run agentic loops to ensure you continue to maintain good observability and service management posture.

182 tools reported — Publisher-reported; not verified by Pod.

Davia Creation

Davia Creation lets creators build and revise private Davia game drafts with Claude. Choose one of your games, inspect its premise, rules, world stats, characters, places, and map placements, then make precise updates while preserving the structure of the world. Claude can add, edit, or remove entities and landmarks, update game rules and stats, and search across the draft before making changes. Access is limited to games owned by the authenticated Davia creator.

7 tools reported — Publisher-reported; not verified by Pod.

Delivra

Connect a Delivra account to explore email and SMS campaign performance, subscriber activity, engagement metrics, top domains, and poll results directly in Claude.

13 tools reported — Publisher-reported; not verified by Pod.

docs.devic.ai

Este MCP permite poder trabajar desde claude con las herramientas que desarrollemos y publiquemos dentro de Devic

3 tools reported — Publisher-reported; not verified by Pod.

Drata

Drata's MCP server allows automating all aspects of GRC covering the full lifecycle of controls, policies, risks, evidence, frameworks, vendors, personnel, and devices directly inside the Drata platform.

36 tools reported — Publisher-reported; not verified by Pod.

Page 88 of 101. ← previous · next →

For agents

This page has a Markdown and a JSON twin. Pod is also queryable over MCP at https://api.askpod.ai/mcp/read.