CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Vercel

pulsemcp/mcp-servers
12 toolsauthSTDIOregistry active
Summary

Connects to Vercel's platform APIs to manage deployments and monitor logs directly from your MCP client. You get build and runtime application log access without switching to the dashboard, plus deployment management operations. Built by PulseMCP with their focus on minimizing tool chain steps and conversational turns, which means fewer round trips to check deployment status or debug production issues. Reach for this when you're iterating on Vercel projects and want to monitor deploys or investigate errors without context switching. Uses stdio transport and requires Vercel API credentials.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Tools

Public tool metadata for what this MCP can expose to an agent.

12 tools
search_vercel_documentationSearch the Vercel documentation. Use this tool to answer any questions about Vercel’s platform, features, and best practices, including: - Core Concepts: Projects, Deployments, Git Integration, Preview Deployments, Environments - Frontend & Frameworks: Next.js, SvelteKit, Nuxt...2 params

Search the Vercel documentation. Use this tool to answer any questions about Vercel’s platform, features, and best practices, including: - Core Concepts: Projects, Deployments, Git Integration, Preview Deployments, Environments - Frontend & Frameworks: Next.js, SvelteKit, Nuxt...

Parameters* required
topicstring
Topic to focus the documentation search on (e.g., 'routing', 'data-fetching').
tokensnumber
Maximum number of tokens to include in the result. Default is 2500.default: 2500
deploy_to_vercelDeploy the current project to Vercel

Deploy the current project to Vercel

No parameter schema in public metadata yet.

list_projectsList all Vercel projects for a user (with a max of 50). Use this to help discover the Project ID of the project that the user is working on.1 params

List all Vercel projects for a user (with a max of 50). Use this to help discover the Project ID of the project that the user is working on.

Parameters* required
teamIdstring
The team ID to get the deployment events for. Alternatively the team slug can be used. Team IDs start with "team_". If you do not know the team ID or slug, it can be found through these mechanism: - Read the file .vercel/project.json if it exists and extract the orgId - Use the `list_teams` tool
get_projectGet a specific project in Vercel2 params

Get a specific project in Vercel

Parameters* required
teamIdstring
The team ID to get the deployment events for. Alternatively the team slug can be used. Team IDs start with "team_". If you do not know the team ID or slug, it can be found through these mechanism: - Read the file .vercel/project.json if it exists and extract the orgId - Use the `list_teams` tool
projectIdstring
The project ID to get the deployment events for. Alternatively the project slug can be used. Project IDs start with "prj_". If you do not know the project ID or slug, it can be found through these mechanism: - Read the file .vercel/project.json if it exists and extract the projectId - Use the `list_projects` tool
list_deploymentsList all deployments for a project4 params

List all deployments for a project

Parameters* required
sincenumber
Get deployments created after this timestamp.
untilnumber
Get deployments created before this timestamp.
teamIdstring
The team ID to list deployments for.
projectIdstring
The project ID to list deployments for.
get_deploymentGet a specific deployment by ID or URL.2 params

Get a specific deployment by ID or URL.

Parameters* required
teamIdstring
The team ID to get the deployment events for. Alternatively the team slug can be used. Team IDs start with "team_". If you do not know the team ID or slug, it can be found through these mechanism: - Read the file .vercel/project.json if it exists and extract the orgId - Use the `list_teams` tool
idOrUrlstring
The unique identifier or hostname of the deployment.
get_deployment_build_logsGet the build logs of a deployment by deployment ID or URL. Can be used to investigate why a deployment failed. It can work as an infinite stream of logs or as a JSON endpoint depending on the input parameters.3 params

Get the build logs of a deployment by deployment ID or URL. Can be used to investigate why a deployment failed. It can work as an infinite stream of logs or as a JSON endpoint depending on the input parameters.

Parameters* required
limitnumber
Maximum number of log lines to return. Defaults is 100.default: 100
teamIdstring
The team ID to get the deployment events for. Alternatively the team slug can be used. Team IDs start with "team_". If you do not know the team ID or slug, it can be found through these mechanism: - Read the file .vercel/project.json if it exists and extract the orgId - Use the `list_teams` tool
idOrUrlstring
The unique identifier or hostname of the deployment.
get_runtime_logsGet runtime logs for a project or deployment. Runtime logs show application output (console.log, errors, etc.) from serverless functions and edge functions during execution. Supports filtering by environment, log level, status code, source, time range, and full-text search. Us...12 params

Get runtime logs for a project or deployment. Runtime logs show application output (console.log, errors, etc.) from serverless functions and edge functions during execution. Supports filtering by environment, log level, status code, source, time range, and full-text search. Us...

Parameters* required
levelarray
Filter by log level(s). Can specify multiple levels.
limitnumber
Maximum number of log entries to return. Defaults to 50, max 1000.
querystring
Full-text search query to filter logs.
sincestring
Start time - ISO format or relative time (e.g., "1h", "30m", "7d"). Defaults to 24 hours ago.
untilstring
End time - ISO format or relative time. Defaults to now.
sourcearray
Filter by source type(s). Can specify multiple sources.
teamIdstring
The team ID to get the deployment events for. Alternatively the team slug can be used. Team IDs start with "team_". If you do not know the team ID or slug, it can be found through these mechanism: - Read the file .vercel/project.json if it exists and extract the orgId - Use the `list_teams` tool
projectIdstring
The project ID to get runtime logs for.
requestIdstring
Filter by specific request ID.
statusCodestring
Filter by HTTP status code (e.g., "500", "4xx").
environmentstring
Filter by environment: "production" or "preview".one of production · preview
deploymentIdstring
Filter logs to a specific deployment ID or URL.
get_access_to_vercel_urlCreates a temporary shareable link that bypasses authentication for protected Vercel deployments. When you encounter a Vercel deployment URL (like https://myapp-abc123.vercel.app), you might receive a 403 (Forbidden) error when trying to access it. This tool generates a specia...1 params

Creates a temporary shareable link that bypasses authentication for protected Vercel deployments. When you encounter a Vercel deployment URL (like https://myapp-abc123.vercel.app), you might receive a 403 (Forbidden) error when trying to access it. This tool generates a specia...

Parameters* required
urlstring
The full URL of the Vercel deployment (e.g. "https://myapp.vercel.app").
web_fetch_vercel_urlFetches a Vercel deployment URL and returns the response. This is useful if another web fetch tool returns 401 (Unauthorized) or 403 (Forbidden) for a Vercel URL. Supports accessing deployments protected with Vercel Authentication which the user of this MCP server has access to.1 params

Fetches a Vercel deployment URL and returns the response. This is useful if another web fetch tool returns 401 (Unauthorized) or 403 (Forbidden) for a Vercel URL. Supports accessing deployments protected with Vercel Authentication which the user of this MCP server has access to.

Parameters* required
urlstring
The full URL of the Vercel deployment including the path (e.g. "https://myapp.vercel.app/my-page").
list_teamsList the user's teams. Use this to help discover the Team ID of the teams that the user is part of.

List the user's teams. Use this to help discover the Team ID of the teams that the user is part of.

No parameter schema in public metadata yet.

check_domain_availability_and_priceCheck if domain names are available for purchase and get pricing information1 params

Check if domain names are available for purchase and get pricing information

Parameters* required
namesarray
Array of domain names to check availability for (e.g., ["example.com", "test.org"])

PulseMCP's MCP Servers

We build reliable servers thoughtfully designed for MCP Client-powered workflows.

Design principles

You can have confidence that any Pulse-branded MCP server was built with these north stars in mind:

  1. Purpose-built. LLM-powered MCP clients offer uniquely new user interaction patterns that necessitate a different layer of abstraction than the REST API's from a pre-AI era. We thoughtfully scope drawing lines like building a new server, versus incorporating a new feature in another server. Or deciding where one slew of REST API endpoints might be better packaged as a single Tool call. And more.
  2. Easy set up. Many MCP servers die before ever getting a chance to be used. We offer guides and a frustration-free experience to get going with our MCP servers inside your favorite MCP clients.
  3. Time savings. By minimizing the number of tool chain steps or conversational turns you need to accomplish a task, our MCP servers will save you (and your agents) time waiting for a task to be completed.
  4. Inference cost savings. By minimizing the number of tokens you need to consume to a accomplish a task, our MCP servers will save you on your LLM inference bills.
  5. Reliability. You should have confidence that you can deploy our servers in a production application serving mass market consumers or business clients.
  6. Future-proof. We sit on the bleeding edge of the MCP specification, working to push the ecosystem forward. As such, you can be sure that if you commit to baking our server into your workflow, it will self-improve over time to take advantage of the latest and greatest MCP features.

Servers Available

Productionized Servers

These are PulseMCP-branded servers that we intend to maintain indefinitely as our own offerings.

The MCP Registry column controls whether the server is published to the official MCP Registry (com.pulsemcp/<server-name>) by the publish-mcp-registry.yml workflow.

NameDescriptionLocal StatusRemote StatusMCP RegistryTarget AudienceNotes
pulse-fetchPull internet resources into context0.3.3Not StartedYesAgent-building frameworks (e.g. fast-agent, Mastra, PydanticAI) and MCP clients without built-in fetchSupports Firecrawl and BrightData integrations; HTML noise stripping; Resource caching; LLM extraction
pulse-subregistryBrowse the PulseMCP Sub-Registry0.0.8Not StartedYesDevelopers discovering MCP servers from the PulseMCP Sub-RegistrySearch and pagination; Version selection; Integrates with PulseMCP Sub-Registry API
image-diffProgrammatic image comparison0.1.3Not StartedYesDevelopers comparing design mocks against UI implementationsPixel-level diff with clustering; Heatmap visualization; Anti-aliasing detection; Auto-alignment for different-sized images
svg-tracerBitmap-to-SVG vector tracing0.1.3Not StartedYesDevelopers converting bitmap images to SVG vector graphicsSupports PNG, JPG, WebP, BMP, GIF, TIFF; Alpha channel preprocessing; Target size scaling; Customizable tracing parameters

Experimental Servers

These are high-quality servers that we may discontinue if the official provider creates and maintains a better MCP server.

NameDescriptionLocal StatusRemote StatusMCP RegistryTarget AudienceNotes
agent-orchestratorAgent parallelization system for agentic coding and ops0.8.8Not StartedNoPulseMCP team for agent orchestrationRequires AGENT_ORCHESTRATOR_BASE_URL and API_KEY; Internal use only
appsignalAppSignal application performance monitoring and error tracking0.5.4Not StartedYesDevelopers using AppSignal for application monitoringRequires AppSignal API key; NOT officially affiliated with AppSignal
claude-code-agentClaude Code Agent MCP Server for managing Claude Code CLI sessions0.0.8Not StartedNoDevelopers building AI-powered automation workflowsRequires Claude Code CLI installed locally
dynamodbAWS DynamoDB table and item operations with fine-grained access0.2.7Not StartedYesDevelopers using AWS DynamoDBRequires AWS credentials; Fine-grained tool access control
remote-filesystemRemote filesystem operations on cloud storage (GCS)0.1.5Not StartedYesDevelopers needing cloud storage integrationRequires GCS credentials; Full CRUD operations; Published as remote-filesystem-mcp-server
s3AWS S3 bucket and object management0.0.5Not StartedYesDevelopers needing S3 storage integrationRequires AWS credentials; Fine-grained tool access control; Published as s3-aws-mcp-server
fetchpetFetch Pet insurance claims management0.1.8Not StartedYesPet owners with Fetch Pet insuranceRequires Fetch Pet username and password; NOT officially affiliated with Fetch Pet
fly-ioFly.io cloud platform app and machine management0.1.7Not StartedYesDevelopers deploying applications to Fly.ioRequires FLY_IO_API_TOKEN; NOT officially affiliated with Fly.io
gcsGoogle Cloud Storage bucket and object management0.1.14Not StartedYesDevelopers needing GCS storage integrationRequires GCS credentials; Fine-grained tool access control; Published as gcs-google-mcp-server
google-flightsGoogle Flights search, date grids, and airport lookup0.2.5Not StartedYesUsers searching for flights via Google FlightsNo API key required; Uses protobuf-encoded HTTP requests; Published as google-flights-mcp-server; NOT officially affiliated with Google
gmailGmail integration for email access0.4.11Not StartedYesGmail users (personal or Google Workspace)Supports OAuth2 (personal) and service account (Workspace); NOT officially affiliated with Google
google-calendarGoogle Calendar Workspace integration for calendar management0.0.13Not StartedYesGoogle Workspace organizations needing Calendar integrationRequires service account with domain-wide delegation; NOT officially affiliated with Google
good-eggsGood Eggs grocery shopping automation0.1.10Not StartedYesUsers of Good Eggs grocery delivery serviceRequires Good Eggs username and password; NOT officially affiliated with Good Eggs
onepassword1Password credential and secrets management via CLI0.5.4Not StartedYesDevelopers using 1Password for secrets managementRequires 1Password CLI and service account token; NOT officially affiliated with 1Password
hatchboxHatchbox Rails hosting platform management0.1.3Not StartedYesRails developers using Hatchbox for hostingRequires Hatchbox API key and deploy key
langfuseReadonly Langfuse LLM trace and observation analysis0.1.3Not StartedYesDevelopers using Langfuse for LLM observabilityRequires Langfuse API keys; Published as langfuse-observability-mcp-server; NOT officially affiliated with Langfuse
monarch-moneyMonarch Money personal finance management (read + mutate)0.0.9Not StartedYesMonarch Money users tracking accounts, transactions, net worth, and budgetsRequires Monarch credentials; tool-group filtering for write protection; NOT officially affiliated with Monarch Money
playwright-stealthBrowser automation with Playwright and optional stealth mode0.2.3Not StartedYesDevelopers needing browser automation with anti-bot bypassOptional stealth mode via STEALTH_MODE env var
pointsyeahAward flight search across 20+ airline loyalty programs0.2.9Not StartedYesTravelers optimizing credit card points for flightsOptional PointsYeah refresh token (can be set at runtime); NOT officially affiliated with PointsYeah
proctorProctor exam runner for testing MCP servers0.1.9Not StartedYesPulseMCP team for MCP server testingRequires PROCTOR_API_KEY; Internal use only
pulsemcp-cms-adminInternal API for managing PulseMCP newsletter content0.10.4Not StartedNoPulseMCP team for content managementRequires PULSEMCP_ADMIN_API_KEY; Internal use only
serpapi-hotelsGoogle Hotels search, details, and reviews via SerpAPI0.0.4Not StartedYesUsers searching for hotels via Google HotelsRequires SerpAPI key; NOT officially affiliated with SerpAPI or Google
slackSlack workspace messaging and collaboration integration0.0.7Not StartedYesTeams using Slack for team communicationRequires Slack Bot Token; NOT officially affiliated with Slack
sshSSH remote server management with agent authentication0.1.5Not StartedYesDevelopers needing SSH access to remote serversSupports SSH agent for passphrase-protected keys
twistTwist team messaging and collaboration platform integration0.2.3Not StartedYesTeams using Twist for asynchronous communicationRequires Twist API bearer token and workspace ID
vercelVercel deployment management and runtime log retrieval0.1.3Not StartedYesDevelopers using Vercel for deployment and hostingRequires Vercel API token; Published as vercel-platform-mcp-server; NOT officially affiliated with Vercel
google-docsMCP server for Google Docs integration with OAuth2 and service account support0.1.4Not StartedYesTBDTBD

Contributing

See CONTRIBUTING.md.

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Configuration

VERCEL_TOKEN*secret

Vercel API token for authentication.

VERCEL_TEAM_ID

Team ID for team-scoped operations.

VERCEL_TEAM_SLUG

Team URL slug for team-scoped operations.

VERCEL_ENABLED_TOOLGROUPS

Comma-separated list of tool groups to enable (readonly, readwrite).

Categories
Cloud & Infrastructure
Registryactive
Packagevercel-platform-mcp-server
TransportSTDIO
AuthRequired
UpdatedMay 18, 2026
View on GitHub

Related Cloud & Infrastructure MCP Servers

View all →
K8s

silenceper/mcp-k8s

Provides Kubernetes resource management and Helm operations via MCP for easy automation and LLM integration.
145
Containerization Assist

azure/containerization-assist

TypeScript MCP server for AI-powered containerization workflows with Docker and Kubernetes support
41
AWS Builder

io.github.evozim/aws-builder

AWS CloudFormation and Terraform infrastructure blueprint builder.
Kubernetes

strowk/mcp-k8s-go

MCP server connecting to Kubernetes
381
Kubernetes

reza-gholizade/k8s-mcp-server

Provides a standardized MCP interface to interact with Kubernetes clusters, enabling resource management, metrics, logs, and events.
156
MCP Server Kubernetes

flux159/mcp-server-kubernetes

Provides unified Kubernetes management via MCP, enabling kubectl-like operations, Helm interactions, and observability.
1.4k