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=10.md or /mcp/for/developer-tools?page=10.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 226–250 of 405 · page 10 of 17.

InstaWP

Use Claude to launch WordPress sites, build and manage an entire fleet of sites.

Ask Claude to:

You can start by creating sandbox sites and then seamlessly upgrade them to production grade quality.

InstaWP operates at two levels.

At the account level, Claude can manage sites, backups, plans, teams, versions, and diagnostics.

At the site level, Claude can work directly inside any connected WordPress site — without requiring a separate MCP connector for every site, so you can:

Security and control

Account-level MCP access is disabled by default and connects securely using OAuth, on site level, you can selectively enable access and go deep to enable execute/files/db access.

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

Kamai AI

Kamai turns construction blueprints into structured data. Its geometric foundational models read your sheet sets and return areas, volumes, lengths, counts, and materials, each number keyed back to the sheet, layer, and geometry it came from, so every quantity is traceable.

Connect Kamai to create projects, ingest drawings from a URL or straight from a PDF you share in the conversation, and read structured takeoff data without leaving Claude. Projects, blueprints, takeoffs, and uploads render as interactive views in chat, so you can page through sheets and inspect quantities visually instead of reading raw output.

Use it for quantity takeoff, material estimating, bid preparation, scope checks, and drawing review. Available now for interior finishes (Div 09), plumbing (Div 22), and electrical (Div 26), with more divisions coming.

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

Kastra

Kastra is an AI authorization platform that evaluates your AI agents’ actions against your policies and maintains a tamper-evident audit trail. This connector gives Claude read-only access to your Kastra account, allowing you to ask questions about your governance posture in plain language instead of navigating the console.

After you authorize the connector through a Kastra OAuth consent screen and select an environment, Claude can read—but never modify—the following:

•⁠ ⁠Decisions and their outcomes (allow, deny, and hold) •⁠ ⁠Policies, environments, and per-rule statistics •⁠ ⁠Incidents and HOLD approval checkpoints •⁠ ⁠Audit-chain verification results and governance audit logs •⁠ ⁠Activity statistics and trends •⁠ ⁠Onboarding governance preferences and masked API key metadata

Access is limited to your tenant and the specific environment you select during authorization. The connector cannot write data, modify settings, access other tenants, or expose raw prompt content or plaintext API keys. You can revoke access at any time through your connector settings.

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

MerchantSpring

MerchantSpring is the marketplace analytics platform built for agencies and enterprise brands, unifying sales, profit, advertising, inventory, traffic, Buy Box, and customer performance across seller and vendor accounts on 120+ marketplaces including Amazon, Walmart, eBay, Shopify, and more.

This connector puts all of it inside Claude. Ask questions in plain language and Claude pulls live, portfolio-wide metrics with period-on-period comparisons built in. Drill from the total portfolio down to a single store or SKU, covering sales trends, store and product-level profit and loss, advertising performance by channel, and 16 on-demand report types spanning inventory health, Buy Box performance, traffic and conversion, customer lifetime value, refunds, and repeat purchase.

Ask things like "Compare sales across all client marketplaces this month vs last", "Which SKUs ran negative margins last quarter?", "How did advertising performance shift across channels week on week?", or "Show ordered vs shipped revenue for our Amazon Vendor accounts by month". Claude fetches the live numbers and does the analysis on the spot.

For agencies, that means the whole client book in one conversation - filter any query by marketplace, country, or store tags, compare performance across every account you manage, and turn the answers straight into client-ready reporting. Seller and vendor accounts are both fully supported.

Trusted by 35,000+ brands and agencies.

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

Notehub

Notehub IQ is an intelligence layer for Notehub. For teams already collecting data from deployed products, it removes the last hard step: getting actionable answers out. Rather than building dashboards, exporting data, or pulling in an engineer to write a query, you ask your products a question in plain language and get an answer drawn from the Notehub data you already collect. It works whether you have a hundred devices or a million.

Under the hood, today Notehub IQ is comprised of two Blues-provided components, used with an AI agent you already have:

  1. A first-party storage service that acts as the data layer that securely stores and syncs the Notefile data you choose, ready for fast analytical queries.
  2. This MCP server called that acts as the interface to Notehub IQ. It turns your plain-language questions into queries, runs them, and reasons over the results.

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

Senzing

Senzing is entity resolution — deciding which records refer to the same real-world person or organization — delivered as an embeddable SDK. This connector is Claude's authoritative, tool-first source for building and evaluating entity resolution: it grounds every answer in Senzing's own documentation and indexed code rather than model training data, which is frequently wrong about Senzing.

Because it carries the full runbook, you don't drive it one step at a time. Hand Claude a few unmapped data files and describe what you want, and it can map your sources, deploy and load Senzing, resolve and analyze the data, and build an interactive explorer over the results — turning what is normally a multi-week integration into an afternoon, with no entity-resolution background required. It also covers the pieces on their own: SDK code in Python, Java, and C# (official) plus Rust and TypeScript/Node.js (community), installation and deployment, error troubleshooting, V3→V4 migration, and the business case.

You can ask Claude to: "Here are three customer files from different systems — build me a demo that finds the same people across them and lets me explore the matches." "Map this data to Senzing and show me what resolves." "Generate a pipeline to load and resolve these records, then measure the match quality." "How would entity resolution help with my problem, and what would it cost?"

It works entirely from pre-fetched documentation: no live Senzing instance, no authentication, no user data or PII sent to Senzing, and all data mapping runs locally on your machine.

***Get the best experience with Claude Code and/or mcp.senzing.com allowlisted in Chat/CoWork.

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

Sourcegraph

Connect Claude to Sourcegraph's powerful code intelligence APIs - enabling semantic code search, symbol lookup, file retrieval, and repository navigation across your entire codebase, including private and multi-repo setups.

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

Stark

Make Stark a native part of your AI workflow. Use it to create projects, scan assets, and quickly remediate accessibility issues across your entire workflow including design, code, and production.

Key features:

Pair with our SKILLs or plugin for a complete accessibility AI workflow.

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

CarsXE

CarsXE’s connector provides live vehicle data through the CarsXE API, so you can look up a car in plain language instead of hitting REST endpoints yourself.

You identify a vehicle by VIN, license plate, year/make/model, or a photo. From there Claude can pull specs, history, recalls, market value, images, lien/theft records, and OBD trouble-code meanings — and chain those lookups in one conversation (decode a plate → specs → recalls → value).

Key features

VIN decode & specs — full vehicle specifications from a 17-character VIN, including an international VIN decoder License plate lookup — plate + state/country → VIN and basic vehicle info Image recognition — extract a VIN or license plate from a photo URL Year/make/model lookup — specs, colors, features, and packages without a VIN Vehicle history — accidents, titles, odometer, salvage/junk, and ownership records Recalls — open safety recalls and remedies by VIN Market value — estimated retail/trade-in, adjustable by state, mileage, and condition Lien and theft — title liens and stolen-vehicle records OBD-II decode — diagnostic trouble codes (e.g. P0115) with diagnosis Vehicle images — photos by make, model, year, color, angle, and more

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

CertScore.ai

Use CertScore when you want Claude to scan or audit a website for cookies, trackers, consent behavior, GDPR/ePrivacy risk signals, privacy-policy gaps, TLS, CMP or related CCPA/CPRA signals. Claude can start a scan, retrieve the result, inspect pre-consent cookies and trackers, and explain findings in plain language. Results are automated public-web observations for review, not legal conclusions or compliance determinations.

Ask Claude to: scan a domain for GDPR/CCPA compliance signals, pull the latest completed scan for a site, explain a specific finding in plain language, or export findings into a report for legal or a client. The compact scan bundle returns status, findings, supporting evidence, and the exact pre-consent cookies/trackers detected in one retrieval step.

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

Charts by Szum

After connecting, start a new chat and say: "Use Charts by Szum to create an editorial bar chart from this data: North 42, South 35, East 28, West 31.".

Charts by Szum helps Claude turn plain-language requests and raw data into publication-ready charts. It can explore curated themes and examples, validate the chart definition, and display an interactive preview with an SVG or PNG image link. When you want to keep a result, save it for permanent image and interactive embed links, then reopen, update, rename, or delete it from Claude or Szum Studio. Useful for reports, presentations, product work, and dashboards.

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

DodgePrint

DodgePrint is the central hub for automated print-on-demand, trusted by 2,000+ sellers running shops on Etsy, Amazon, TikTok Shop, and Shopify.

This connector brings DodgePrint's Etsy intelligence and more features directly into Claude

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

Kavara Kirk

Kavara Kirk is the first algorithm in the Ulysses family — an algorithmic primitive for detecting structural change in raw, unlabeled data streams. Think of it as a Kalman filter for the non-Gaussian, non-stationary world. It maintains a running structural state, updates that state as each new observation arrives, and returns a scalar score measuring how much the current observation diverges from the accumulated structure. No labels. No training. No GPU.

The engine runs on the CPU you already have. Order-book snapshots score in under a millisecond on modern Intel and AMD server-class hardware. State is small enough (kilobytes) to embed in confidential-compute enclaves, so customer data never crosses the trust boundary in cleartext.

Available via MCP: score single or batched observations against a registered model, retrieve engine attestation (cryptographic proof of the exact binary running), browse capabilities and case studies, inspect usage and inference-unit balance.

The finance domain has been characterized end-to-end — a bit-exact reproduction of a published FY24 US-equities result runs in seconds against our production sealed engine. Other domains (industrial telemetry, network traffic, biosignal streams) are structurally compatible but require characterization first.

Output is a scalar structural-change score per observation, with the engine attestation attached. No black-box embeddings, no opaque logits — a single number you can reason about, backtest, and audit.

Prepaid inference units, metered per call. First checkout is $500 → 50,000 IU. Pricing is public via the kirk_pricing tool. The sealed engine ships as Intel TDX, AWS Nitro, and AMD SEV-compatible; every response carries a cryptographic attestation of the running binary.

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

Lance App Manager

Lance connects Claude to your real App Store Connect account. Not an API wrapper: an autonomous operator holding your team's credentials on a real Mac, driving the actual ASC website where Apple's API falls short.

Ask anything, get answers in seconds from live account data: apps, versions, builds, TestFlight, IAPs, subscription prices, customer reviews, submission status.

Delegate what you'd do by hand in ASC: create listings, fill metadata/privacy details, set up IAPs/subscriptions (including clearing the Missing Metadata state API-created products get stuck in), diagnose rejections, drive to submit-ready. Work runs in the background, typically 1-10 minutes; keep chatting while it runs.

The operator carries shipping tradecraft no API exposes: which rejections need a Resolution Center reply vs a fixed resubmission, what each Guideline citation actually requires, when an expedited review request is justified.

Ship builds without a Mac: stage a private git remote, push, and Lance reads the authoritative next build number live from ASC, then builds/signs/uploads to TestFlight on a managed Mac. Works from Windows/Linux/CI; re-pushes transfer only deltas; a typed receipt reports the outcome. For reads the named tools don't cover, mint short-lived audit-logged ASC API tokens and call any endpoint from your own runtime, no .p8 keys to manage. Files move through expiring artifact slots (.ipas in, APNs keys/provisioning profiles out); an account health check flags expiring certificates/unsigned agreements before they block a release.

Built for people shipping with AI: first-time submitters, rejection loops (2.1, 5.1.2(i)), the gap build tools leave open between TestFlight and review.

Safe by design: your Apple password never enters the conversation, the operator never overwrites existing ASC values, Submit for review happens only when you explicitly ask, every account read is audit-logged.

Connect your team at lance.app, then ask Claude to ship.

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

Mixer4AI

Mixer4AI is where verified business AI agents find each other. Agents publish machine-readable capability manifests and get attested to a real business behind them, then browse or publish structured intents — needs, RFPs, problem statements — into a searchable exchange instead of relying on scraped data or cold outreach. Every participant opts in, so consent is built into the exchange by design, and every match traces back to the agents and businesses that made it.

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

PDQ Connect

PDQ Connect lets you search your managed devices, device groups, and package library directly from Claude. Ask which machines missed a check-in, find devices that match specific hardware or OS criteria, look up available package versions, and kick off deployments to individual devices or groups, all in plain language. Built for IT admins who want to move fast without switching tabs.

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

Port IO

Connect Port's context lake and software catalog directly to Claude. Query services, dependencies, and ownership using natural language. Analyze scorecards and service health. Execute governed self-service actions and workflows with built-in guardrails.

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

Project Desk

Agents can move work across ten projects at once. Your attention is one decision at a time. Project Desk closes that gap: many agents, many projects, one desk reflecting exactly what needs you next.

As agents work, they automatically update the shape of the project, file tickets, record handoffs, return decisions to you, and close what ships. The board becomes a byproduct of the work — not another tracker you have to maintain.

Two queues separate judgment from execution. The Attention Queue holds what only you can do: decisions, reviews, walks, and approvals. The Agent Queue holds scoped work with a clear proof of done. Because agent-ready work from every project gathers in one place, a single agent can keep making progress across your portfolio unattended — even overnight — without stopping at every handoff.

Project Desk never opens your repositories or scans your machine. Your coding agents work only with the access you give them, then reflects the project context you approve into your authenticated, isolated desk.

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

Qualisend

Qualisend verifies email addresses and cleans lists so your messages reach real inboxes — no exports, no dashboards. Ask your assistant to check a single address, a batch, or a whole list and get a clear deliverable / risky / undeliverable / unknown verdict for each, with typo suggestions and disposable/role detection.

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

Syntitan

The Syntitan MCP server helps teams check whether enterprise data is ready for AI use. Connect a dataset from Claude to get a six-axis readiness score, review what blocks AI use in plain language, and refine what needs attention. Syntitan saves the refined data as a versioned release, so results can be compared, reproduced, and traced back to the exact data state used.

Key features: • Score AI readiness - Check a dataset across six readiness dimensions and see what blocks AI use.

• Prepare data for AI execution - Refine missing, inconsistent, or hard-to-use data conditions before running AI workflows.

• Reproduce released data states - Save the prepared state as a release and return to it when results need to be checked.

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

Varify MCP

Varify MCP connects Claude to your Varify.io A/B testing account, letting you manage experiments directly through conversation. Create new experiments and variations, or edit, duplicate, pause, and archive existing ones. Adjust traffic allocation between variants and define page and audience targeting by URL, device, browser, or UTM parameters. Turn tracking on or off per experiment. If GA4 is connected, view results directly, including daily reports and revenue analyses based on GA4 data. Agencies get an overview of all managed client accounts in one place. The MCP uses the same public API available for custom integrations.

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

Ysaere

Ysaere connects Claude to prepaid AI research swarms for Angels and Due Diligence teams.

What you can do • Run Company Intelligence, Angel / Angel Deep, Market Intelligence, Due Diligence, and Security Assessments • Check credit balance, poll report status, and fetch provenance (integrity hashes—not a claim of factual truth)

How it works Remote Streamable HTTP MCP at https://mcp.ysaere.com/mcp. Sign in with OAuth (Client ID: claude.ai; leave Client Secret blank) or use an MCP-enabled API key. Tools that spend credits are marked destructive and open-world: they debit your Ysaere balance and may use live web research.

Requirements A Ysaere account with credits. Sign up at https://app.ysaere.com. After login, open Developer → MCP Server https://ysaere.com/mcp/ for setup. Public API reference: https://api.ysaere.com/v1/openapi.json

Legal Outputs are designed and engineered AI-generated research for informational purposes only—not investment, legal, or professional advice. Terms: https://app.ysaere.com/terms · Privacy: https://app.ysaere.com/privacy

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

Act Security

Act Security is the action-first cloud security platform built to secure the cloud at its foundation. Rather than just surfacing findings, Act eliminates the conditions that make risk exploitable in the first place. By analyzing both network and identity layers in a single access graph, Act enforces precise boundaries for humans, workloads, and AI agents across multi-cloud infrastructure. Grounded in real business context and enforced through cloud-native controls, Act helps organizations eliminate attack paths, safely scale AI, and maintain continuous, audit-ready compliance.

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

Agensi

Agensi is the curated marketplace for AI agent skills. Search security-scanned SKILL.md skills by keyword, category, or task. Preview skill details, ratings, and credit prices. Install paid skills with credits directly from your conversation. Every skill on Agensi passes an 8-point automated security scan, AI intent review, and manual human review before going live. Skills work across Claude Code, Cursor, Codex CLI, Gemini CLI, and 20+ other agents. Free to search. Credits required for paid installs. One balance for web and MCP.

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

Agent Native Slides

Agent-Native Slides is an open-source AI presentation builder from Builder.io, built on the Agent-Native framework - which means every app action (generating a deck from a prompt, editing slides, applying brand styles, reordering, sharing) is exposed as an MCP tool over streamable HTTP. Connect Claude to the endpoint and it can build and revise real, editable decks a human can then refine in the visual editor or in code - there's no dead end where the AI's 85%-right output has to be rebuilt elsewhere. Decks can follow a supplied design system, or Slides derives one automatically from a reference deck and sticks to it. A library of data connectors pipes real data straight into your slides - no import/export dance. Also includes logo/image search, presentation mode, and an ask-agent meta-tool that hands complex requests to the app's own agent loop. MIT-licensed, self-hostable, and free - decks live in your repo, not a vendor's cloud. Auth is standard MCP OAuth 2.1 with dynamic client registration.

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

Page 10 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.