Pod

Yes, this is on purpose. Pod is built for agents, so the default page is plain HTML.
Human? View the normal website.
Agent? You probably prefer /mcp/for/developer-tools?page=6.md or /mcp/for/developer-tools?page=6.json, or Pod over MCP.

Best Developer Tools MCP Servers

MCP servers for developer tools, what each one reports it can do, and whether Pod has verified it.

405 servers, ordered by adoption — npm downloads where a package exists, then reported issue volume. Pod has connected to 3 of them; the rest are publisher-reported and unverified.

Showing 126–150 of 405 · page 6 of 17.

Agility CMS

Agility CMS is a headless content management system built for teams that want marketers in control and developers unblocked. This MCP server gives AI assistants authenticated access to your Agility instances so you can model content, author pages, publish updates, and manage media through natural language instead of clicking through admin screens.

27 tools cover the full authoring and publishing workflow. Discover instances, locales, containers, and sitemaps. Inspect or change content models, component models, and page templates. Retrieve, create, update, publish, or delete content items across multiple locales. Compose pages from zones and modules. Upload, browse, and remove media. Move items and pages through approval.

Works across multiple Agility instances under one account, so agencies and enterprises with several brands can switch contexts in a single conversation. Authentication is OAuth 2.0 against your existing Agility account, and the MCP server inherits the permissions you already have. Read-only users stay read-only. The server can't escalate access beyond what your account already grants. Destructive actions are gated. Publish and unpublish ask for explicit confirmation.

Deletes require typing DELETE. On clients that support MCP elicitation, those prompts render in your own UI so the AI assistant can't satisfy them on its own.

Use it to scaffold content models from a spec, compose landing pages from a brief, audit cross-locale content, generate TypeScript types from your schema, migrate spreadsheets into product catalogs, or build a Next.js site with its content models in a single conversation.

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

Domainee

Domainee is the custom domains API for SaaS. Your users connect their own domain to your product with one API call - Domainee issues the SSL, renews it forever, and watches the DNS so you don't have to.

Connect your workspace and Claude manages the whole domain lifecycle from a conversation:

Plus 16 domain and DNS diagnostic tools that work on ANY public domain:

Built for SaaS teams that offer white-label or custom domains, and for anyone who debugs DNS. Ask "why isn't my customer's domain verifying?" and let Claude check the CNAME, the propagation, and the SSL chain in one go.

Requires a free Domainee account. Domain management uses your workspace; diagnostic tools work on any domain.

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

Laimonade.com

Your coding agents can already write the code. The bottleneck is everything around it: deciding what to build next, writing it down well enough to hand over, and knowing when it is actually finished.

Laimonade is an AI Product Owner that grooms the backlog and runs the sprint. This connector gives your coding agent direct access to it, so work moves off the board and into the agent without anyone pasting a ticket into a prompt.

Ask what is ready this sprint and you get the real Ready column back. Load a story and you get the whole thing — description, acceptance criteria, estimate, and the epic it sits under. Before touching a file, your agent can pull the regression notes for the paths it is about to edit, and your project's own conventions: the CLAUDE.md, AGENTS.md and Cursor rules your team already wrote. Bugs it trips over along the way are filed against the item that surfaced them, so you can see later what caused what. When the work is done, it hands the item back for review.

What it deliberately cannot do matters as much. Nothing here marks work done: an agent submits for review, and deciding something is finished stays with a person. Unattended implementation is opt-in per item and set by a human, an agent cannot add work to that queue, including its own. A connection is bound to one project and sees only that project's backlog, sprints, roadmap and rules. It never reads your chat history, Claude's memory, or files you have uploaded.

Built for teams whose agents ship faster than their planning can keep up.

You will need a Laimonade account with at least one project and an active sprint. Adding a second project means connecting again and signing in to it — every reply names the project it came from, so you always know which backlog answered.

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

Axiom

Axiom's MCP server makes the full Axiom experience available to agents. Query your data, build dashboards, and set up monitors — all through natural language prompts with your preferred agentic client.

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

CarlyEmail

CarlyEmail gives an agent a real email address it can work from — not a simulation and not a relay through your personal mailbox.

Create an inbox in a single call and it starts receiving straight away. Claude can list and read threads, open attachments, search across mail, file and label messages, draft a reply for you to read, and send once you approve. Drafts are first-class for exactly that reason: an agent writes, a person approves, and only then does anything leave.

Every tool declares what it does before it runs. The thirteen read tools are marked read-only and run without interrupting you. Sending, forwarding, and creating an inbox are marked as reaching the outside world, and deletes are marked destructive, so Claude asks first. Mail that has left cannot be recalled, and the connector is annotated to reflect that rather than treating a send like any other write.

Access is scoped. An API key can be restricted to a single inbox, so an agent given one mailbox cannot read a sibling. Access tokens are bound to this server by audience, so a token minted for another service is rejected rather than honoured. Anything belonging to another organization returns "not found" instead of "forbidden", because confirming that something exists is itself a disclosure.

Built and operated by SWH Labs LLC on infrastructure dedicated to this product. Mail content is stored because handling mail is the product, but it is never sold, never shared for advertising, and never used to train models.

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

Rezonant

Rezonant is where product teams shape what they're building — defining specs and PRDs, pulling in context, aligning the team, and spinning up tasks for coding agents. This connector closes the gap between that upstream work and the code.

Once connected, your agent can pull the projects, specs, PRDs, tasks, and product context from your Rezonant workspace whenever you ask — so decisions made upstream carry into the build without you re-explaining them. It can also create, update, and delete Rezonant artefacts (projects, documents, tasks) and start coding-agent jobs, right from your editor.

Common uses:

Access is secured with OAuth and scoped to the workspace and teams you authorize. Works with the free tier.

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

Expo

Build, ship, and monitor React Native apps with Expo and EAS, directly from Claude. Get answers from the latest Expo docs, kick off cloud builds and CI/CD workflows, submit to the App Store and Google Play, and track how your app is doing in production.

Key features

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

Nitrosend

Nitrosend is AI-Native Email: a full email service provider built for the MCP era, where Claude is the interface. Connect once with OAuth and Claude can run your entire email program: no tab-switching, no drag-and-drop editor, no CSV wrangling.

What Claude can do with Nitrosend:

• Compose on-brand emails with a section-based designer. A composition contract feeds Claude your brand kit, voice, and design context so drafts come out on-brand, then validates them before anything persists. • Send campaigns to lists and segments, with review, test sends, and an explicit approval step before anything goes live. • Build automation flows (welcome series, cart abandonment, win-backs) from triggers, waits, splits, and webhooks. • Send transactional email: receipts, OTPs, password resets, single recipient, immediate, idempotent. • Import and manage contacts: CSV imports up to 250k rows, segments, tags, lists, and TCPA/GDPR-aware opt-in handling. • Verify sending domains, configure senders, and read deliverability-aware analytics with trends and benchmarks.

Safety is built in: read-only tools are annotated as such, destructive actions prompt, sends require explicit approval, and large imports hold for review. Docs: docs.nitrosend.com

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

Render

Render's official MCP server lets AI apps and agents manage your Render infrastructure through natural language. Create and deploy web services, static sites, and cron jobs; provision Render Postgres and Key Value instances; trigger and inspect deploys; update environment variables and compute plans; stream logs; analyze performance metrics; and run read-only SQL against your Postgres — all scoped to a workspace you choose. Hosted by Render at https://mcp.render.com/mcp, it connects over OAuth (or a Render API key) and is designed to keep secrets like connection strings out of your AI app's context.

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

AgentMail

AgentMail gives AI agents their own email inboxes. Through this connector, an agent (or you, in Claude) can spin up a dedicated inbox on the fly, then send, receive, reply to, and forward email, with full thread context, drafts, and attachments, entirely through tool calls. Unlike traditional email APIs built for one-way notifications, AgentMail is built for two-way conversations: an agent can read an incoming thread, understand it, and respond in context, just like a person would. This makes email a first-class communication and identity channel for agents, letting them sign up for services, coordinate with people, and talk to other agents. Key capabilities exposed over MCP: • Inboxes: create, list, get, update, and delete agent inboxes • Messages: send, reply, forward, list, and update • Threads: list, read, label, and delete full conversation threads • Search: full-text search across threads and messages • Drafts: create, list, read, update, send (with scheduling), and delete • Attachments: retrieve attachments by ID, with text extraction for PDF/DOCX Connect in seconds via OAuth using your AgentMail console identity. No API key required in Claude. Sign up free at console.agentmail.to.

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

Birta

Birta turns a conversation with Claude into a live, working website — a landing page, a service page, a small commercial site — and keeps it manageable afterwards. You describe the result you want, Claude builds and publishes the pages, and the site goes online at a real address. No servers, builds, or deploy pipelines to set up.

What you can do through the connector:

• Create and list projects, and rename an existing one. • Work on a draft version of a site: create files, read and edit them in place, replace an exact fragment or a range of lines, move or delete files, and list everything before it goes live. • Publish a draft to a real, shareable address — or roll a project back to an earlier published version if something goes wrong. • Read the remarks left on a version, so feedback from a client or a teammate comes back into the same conversation. • Declare lead forms on a site and read the leads that come in, without writing any backend code. • Check a project's visitor stats.

Every published site gets its own address immediately. Custom domains, billing and account settings live in the Birta dashboard, which mirrors what the connector can do — dangerous, irreversible actions stay with you, not the agent.

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

Cloudflare Developer Platform

Enables users to build applications on Cloudflare Workers using built-in storage, AI, and compute primitives. Deploy code to production, create and query databases, manage KV stores, and more.

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

Inbin

Inbin turns email into a structured, trust-labeled data source for Claude. Every message arriving at your Inbin inbox is extracted against your schema, checked verbatim against the source by a hallucination guard, and served as typed JSON. Each field carries a trust label (typed vs untrusted text a stranger wrote), each event carries the sender's SPF/DKIM/DMARC verdicts, and provenance is channel-derived, so nothing in an email's content can claim authority. Claude can list, search, and aggregate events server-side, wait for confirmation emails to complete signup flows, record decisions, and share individual events across applications by id instead of resending content.

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

JupiterOne

JupiterOne is a agentic risk management platform that maps your cloud resources, identities, devices, vulnerabilities, and the relationships between them into a queryable graph. This connector lets you work with that graph in natural language: run J1QL queries against your asset inventory, explore entity types, triage active alerts, create and evaluate detection rules, review integration ingestion status, and build dashboards. Every action runs with your existing JupiterOne user permissions.

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

Keynodex Memory

Keynodex Memory is a private, tenant-scoped memory store for Claude and other MCP clients. It stores decisions, preferences, project facts, playbooks, and verified claims so assistants can search, save, and reuse durable context across sessions and tools—not only inside one product’s built-in memory feature.

Sign in with Google and approve access once. Claude can then recall stored work, save durable notes, use artifact-linked recall, and run playbooks for recurring procedures. Each account’s store is isolated from other users.

Connect via remote MCP at memory.keynodex.com. Plan status and upgrades are on the website only; tools never purchase, cancel, or change billing.

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

Whalesync

Whalesync keeps data in sync between the tools your team already uses — Airtable, Webflow, HubSpot, Salesforce, Notion, Postgres, and more — with two-way sync that feels native in every app.

With this connector, Claude can set up and run syncs for you: create a sync between two apps, map tables and fields, validate the mapping, and turn the sync on. Once data is flowing, Claude can monitor it — check sync status, find out why a record isn’t syncing, review held deletes, and retry failed work after you fix the cause.

Connecting your apps and approving anything irreversible always stays in your hands: OAuth connections, starting a sync, and approving deletes happen in the Whalesync app, and Claude hands you a link at each of those steps.

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

Blynk

Manage your IoT device fleet directly from Claude. Create device templates with datastreams and events, provision new devices, read live sensor data, and control outputs. The Blynk connector integrates with the Blynk IoT platform, enabling direct configuration and monitoring of connected devices and infrastructure.

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

Commercient Data Lake \ Data Hub

The Commercient Data Lake MCP connector gives Claude direct, secure access to your tenant's business data, enabling a wide range of data operations without leaving your workflow.

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

Crustdata

Search, enrich and watch people and companies from a single conversation in Claude with Crustdata. Build TAM, prospect and candidate lists using 150+ search filters such as job title, industry, funding and more. You can also enrich people and company profiles with 350+ datapoints such as verified emails, full work experience, education, funding, headcount, web traffic, job postings and more.

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

Descope for Claude

Add Descope authentication to your customer apps and MCP servers directly through Claude. Access the Descope Management SDK to manage users, tenants, roles, and other identity primitives. Create and modify user journeys including signup, login, MFA, SSO, and federation. Add auth, consent, access control, and credential management to your MCP servers and AI agents through natural language prompts.

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

Fabric

Fabric is a personal AI workspace where everything you save, write, capture, or record lives in one intelligent space. Notes, files, PDFs, bookmarks, voice recordings, meeting transcripts, web clippings, photos, and more – all searchable by meaning, not just keywords.

The Fabric MCP connector gives Claude direct access to your entire Fabric library. Ask Claude to search your notes, find a PDF you saved last month, pull up highlights from a book, or reference a meeting transcript – without leaving the conversation.

What you can do:

Search across everything in your Fabric library by meaning. Ask "what were my notes on pricing strategy" and get results from across notes, documents, bookmarks, and recordings.

Reference your own materials in conversations with Claude. Instead of pasting content manually, Claude can pull directly from your saved research, course materials, client files, or personal notes.

Build on your own knowledge. Claude's intelligence combined with your personal library means answers grounded in your actual work – not generic internet results.

Fabric connects to all your favourite apps and tools – Google Drive, email, Linear, Google Calendar, Slack, and more – which feed into the same searchable library that Claude can access.

Whether you're a student studying from lecture recordings and textbook PDFs, a researcher working across hundreds of papers, a freelancer managing client projects, or a founder keeping track of competitive research – Fabric gives Claude the context it needs to help you with your actual work.

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

Meko

Meko is a data-persistence cloud platform for hybrid teams (AI agents and humans). It gives you a place to keep shared context (agent memory, conversations, and knowledge base docs) without the need for you to stitch it together yourself. We have already done this behind the scenes, so everything just works out of the box with natural language. No knowledge of SQL required.

Meko stores "context," which enables sharing across agents and harnesses.

Meko stores and enables you to:

Save AI conversations and extract facts from them into searchable memory, so work from an earlier session doesn't have to be reprocessed from all the individual pieces of data.

Easily upload documents into a hosted knowledge base, so that you don't have to write complex data pre-processing pipelines.

Allow resuming your context over time or switching between LLMs and IDEs, so you can pick up where you left off. This is helpful if you run out of tokens, an LLM goes down for a while, or you want to use a different AI provider.

Share agent memory and knowledge base documents with other teammates (agents or humans) selectively, so everyone can work together and learn from each other.

Store agent traces in a visual portal, so you can see what the agent thought or did during conversations or agentic work.

Gain access through a remote MCP endpoint, so that any MCP-capable agent (Claude, Cursor, Codex, and other AI chat apps with MCP) can use it.

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

Retool

Connect Claude directly to your Retool workspace. Manage users, configure resources, and run admin operations directly from Claude Chat or Code.

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

Shipstar

Shipstar is automated product marketing for engineers and agents. Connect a Shipstar project to this connector and Claude can drive the full content pipeline from your shipped code:

Each OAuth connection is scoped to exactly one Shipstar project, chosen on the consent screen. Read tools are annotated read-only; publishing and email sends only happen through explicit tool calls. Requires a Shipstar account (free plan available) with a connected GitHub repository.

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

YouTrack

Connect Claude to YouTrack to find and summarize issues, create and update work, manage assignees, links, tags, and comments, log time, and search or update knowledge base articles. Requires automatic OAuth client registration in YouTrack.

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

Page 6 of 17. ← 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.