# MCP Servers with a get_agent tool Every MCP server Pod knows of that exposes a get_agent tool. 11 servers, ordered by adoption — npm downloads where a package exists, then reported issue volume. None have been dialled by Pod yet, so every tool list here is publisher-reported and unverified. ## [Conduit](/mcp/conduit) Conduit is the AI customer-experience platform for hospitality. Hotels, vacation-rental managers, and hospitality groups use Conduit to handle guest messaging, voice calls, and support across every channel and language with AI agents. This connector brings your Conduit workspace into Claude. Look up contacts, conversations, reservations, calls, and helpdesk tickets; inspect and configure your AI agents and their knowledge base; and manage workspace settings, all in natural language. Ask things like "show open tickets for this workspace," "what's this guest's reservation," or "what's in this agent's knowledge base," and act on the answer without leaving Claude. Read-only tools retrieve guest, conversation, reservation, ticket, and configuration data. Write tools (gated behind in-app approval) create and update agents, knowledge nodes, skills, tickets, and messages. Access follows your existing Conduit workspace permissions and applies only to your own Conduit account. 63 tools reported — Publisher-reported; not verified by Pod. ## [Kayse for Claude](/mcp/kayse-for-claude) Kayse is the Client Relationship AI for Plaintiff Firms. ⚖️ You cannot fix what you cannot see. Kayse dashboards show you the part that matters most: which cases make you money, and which marketing brought them in. 📊 Then Kayse lets you act on what you learn, right in the same platform. This connector brings Kayse into Claude, so you can just ask for what you need. What you can do: 📈 Build live dashboards on the fly and see which case types, sources, and ad spend actually pay off ⚡ Answer new leads fast with speed-to-lead outreach, so no lead goes cold while you are busy 🔄 Win back ghost clients with reactivation campaigns that reach the people who stopped answering 🗂️ Look up and update cases, clients, and case lists in seconds 💬 Send text and email updates that keep clients informed and happy 📞 Check call logs, recordings, and campaign results to see what is working Kayse is the only client platform for plaintiff firms that pairs a full client portal with AI that makes calls for you. 🤖 Its AI Receptionist handles the whole intake, no handoff needed. Its outbound AI wins back the cases that go quiet, which is close to 40% of cases every year at many firms. Ask Claude to build a dashboard, set up speed-to-lead workflows, send a client update, start a reactivation campaign, or check how your numbers look. Kayse does the rest. 🚀 93 tools reported — Publisher-reported; not verified by Pod. ## [Synthflow](/mcp/synthflow) Synthflow lets you build and operate AI voice agents that make and take phone calls. This connector brings your Synthflow workspace into your assistant, so you can create and configure voice agents; manage their actions (SMS, call transfers, bookings, custom API calls, and data extraction); organize knowledge bases, phone numbers, and contacts; review calls and analytics; and run agent simulations all from your favourite AI tool. It reads your workspace data and can make changes on your behalf; destructive actions like deletions are clearly marked and confirmed. 62 tools reported — Publisher-reported; not verified by Pod. ## [Sequentum MCP](/mcp/sequentum-mcp) Sequentum is the trusted execution layer for AI workflows and mission-critical web data. Our platform delivers deterministic web scraping, web search, and crawling at enterprise scale, with browser orchestration and web automation built on 18 years of mission-critical infrastructure. Agent Builder turns a natural language prompt into a production-ready web data agent in minutes. The Visual Editor takes it to atomic-level precision. From AI training data, agentic checkout flows, and real-time web search to compliance-grade research pipelines, Sequentum turns the web into reliable, actionable data that hedge funds, Fortune 500s, and government agencies trust. 39 tools reported — Publisher-reported; not verified by Pod. ## [Karumi](/mcp/karumi) Karumi is an AI-powered product demo platform for SaaS companies. This connector lets you run your Karumi workspace directly from Claude using natural language. Explore demos and sessions: browse and filter prospect demo sessions, deep-dive any session with its full transcript, and run keyword or semantic search across all conversations to see what prospects are asking about. Manage your demo experiences: create and update audiences (shareable, campaign-specific entry points), edit reusable demo journeys and start pages, update an agent's system prompt, and add knowledge files — all without leaving Claude. Surface leads and insights: pull lead records and engagement analytics, review Q&A content, and generate summaries from real demo activity to feed your sales and marketing workflows. Built-in safety: every tool is annotated as read-only or destructive, so Claude asks before any action that creates, updates, or deletes. Access is scoped to the organizations your account belongs to and authorized via OAuth 2.0. Ideal for sales, marketing, and product teams who want to monitor demo performance, qualify leads, and iterate on their AI demos conversationally. 38 tools reported — Publisher-reported; not verified by Pod. ## [Ballet](/mcp/ballet) Ballet is an agent and workflow automation platform for building AI-powered processes that can reason, take action, and run automatically. Create specialized AI agents, chain them together into multi-step playbooks, and connect them to the tools and systems your team already uses through MCP servers. Playbooks can coordinate multiple agents and actions to complete end-to-end workflows instead of handling just a single prompt or task. Ballet workflows can be launched manually or automatically from triggers including schedules, webhooks, Slack commands, form submissions, and other events. This makes it possible to turn repeatable operational processes into persistent AI-powered automations. Use Ballet to: - Build AI agents with specific roles, instructions, tools, and capabilities - Combine agents and actions into reusable multi-step playbooks - Connect external applications, data, and services through MCP - Automate workflows using schedules, webhooks, Slack commands, forms, and other triggers - Orchestrate processes that require multiple AI agents or tools working together - Run repeatable workflows consistently without manually prompting an AI for every step Example workflows include researching and enriching leads, generating recurring reports, processing inbound requests, coordinating customer or operational workflows, transforming information between systems, and automating internal processes that previously required several tools and manual steps. With the Ballet connector, Claude can interact with your Ballet environment to help users work with their agents, playbooks, and automated workflows. 31 tools reported — Publisher-reported; not verified by Pod. ## [Coval](/mcp/coval) Connect Claude to your Coval workspace to inspect agents, test sets, test cases, personas, metrics, and evaluation runs. Build or update evaluation fixtures, launch safe chat and SMS evaluation runs, and ask Sofia for grounded, read-only analysis and recommendations. The Claude connector does not start voice, outbound voice, or WebSocket voice runs. 19 tools reported — Publisher-reported; not verified by Pod. ## [Mnemom](/mcp/mnemom) Mnemom is trust infrastructure built for agents, not just the humans who run them. In one chat you can look up an agent's Continuous Trust Rating — the score, the grade, and the accountability evidence behind it — and confirm it's cryptographically signed, not merely asserted. Drop your own alignment card and get an instant trust read back; claim a verifiable identity with no human in the loop; and walk away with an embeddable Trust Rating badge for your README or agent card. Every read is honest about what it knows: a quiet record reads as quiet, never as a red flag. The system tells the truth — and view-source proves it. 15 tools reported — Publisher-reported; not verified by Pod. ## [ElevenLabs](/mcp/elevenlabs) Connect Claude to your ElevenLabs workspace to create and manage voice agents. Find existing agents, review their configuration, update prompts and voices, duplicate or delete agents. Sign in with ElevenLabs to get started. 11 tools reported — Publisher-reported; not verified by Pod. ## [app.cotera.co](/mcp/app-cotera-co) Cotera is where teams build AI agents on top of their own data and tools. This connector puts that workspace inside Claude: browse the agents you already have, build new ones, run them, and bring the output back into the conversation. Build agents. Describe what an agent should do in plain markdown and Claude creates it in your workspace, with headings, lists, and code blocks intact. Prompts can reference your connected tools, your documents, and your other agents, so a new agent delegates work the same way one built in the Cotera editor does. Find what to reference. Search the tools your workspace has connected — including whether each one is currently connected and ready to run — and search your documents, so an agent is wired to the real thing rather than to a guess. Run them, one input or many. Run an agent against a single input, or start up to 50 runs in parallel over a list: a batch of leads, tickets, transcripts, or rows. Runs execute in the background, and you collect the outputs as they finish. Read what you have. List every agent in the workspace, newest first, including ones your teammates built in the Cotera app, and read any agent's full prompt. Everything happens in the workspace you authenticate with. Agents created here are ordinary Cotera agents — your team can open, edit, schedule, and share them in the app afterwards. Nothing is destructive: creating an agent never modifies an existing one, and running an agent never changes it. Two things I deliberately kept in, since they're the details that make the listing trustworthy: the 50-run batch ceiling (the real MAX_BATCH_SIZE) and the read-only/non-destructive framing, which matches the tool annotations you ship. 8 tools reported — Publisher-reported; not verified by Pod. ## [FidelicAI: Hire AI Agents](/mcp/fidelicai-hire-ai-agents) FidelicAI is an AI workforce platform for small businesses. Use Claude to match business work to a published AI agent; compare doing the work with a custom system, a hired role, or a human lead; inspect the role's public rates and limits; and open the accurate hire path. A Day Pass is one active day with the selected role and can carry one substantial assignment or several in-scope requests. It is not a per-task meter. FidelicAI uses Claude Managed Agents as the hosted runtime for production role systems that need persistent tool use and long-running work. FidelicAI participates in the Claude Partner Network. Anthropic does not endorse this public connector, a returned role, or a customer hiring decision. Claude helps the buyer choose and prepare the hire. The hired fidelic agent does the role work. Each fidelic agent is a production role formed over months around attributable sources, written work methods, production tools, evaluation gates, a tested deployment, and continued maintenance. This does not claim special model weights; Claude and a fidelic agent may use the same foundation model without being equivalent work systems. Claude can also search and read FidelicAI Field Guide articles, Research, Hard Questions, decision guides, use cases, and comparisons, or return official setup, private support, and Slack community routes. A hired fidelic agent works through Slack, WhatsApp, or Microsoft Teams according to the chosen setup. Checkout, payment, and customer-workspace connection finish securely at start.fidelic.ai; the connector does not charge a card, install Slack, or deploy an agent. No connector account is required. Requests are processed only to return the selected public information or first-party link and are not stored by the application. Do not include confidential business information in a roster or publication search. 8 tools reported — Publisher-reported; not verified by Pod. ## For agents This page has a [Markdown](/mcp/tool/get-agent.md) and a [JSON](/mcp/tool/get-agent.json) twin. Pod is also queryable over MCP at `https://api.askpod.ai/mcp/read`.