CCM
/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

Claude Code Marketplaces

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
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
sethclawd-prog avatar

Schemaguard

sethclawd-prog/schemaguard
STDIOregistry active
Summary

Monitors OpenAPI spec drift and catches breaking changes before deployment. Exposes operations to diff two specs, run CI checks against a baseline, and lint for schema quality issues. Detects nine categories of breaking changes including removed endpoints, type changes, narrowed enums, and deleted response fields, plus tracks non-breaking additions for visibility. Returns structured JSON output that agents can parse, exits with status codes that block pipelines when breaking changes are found, and can validate specs for missing operation IDs or security schemes. Reach for this when you're maintaining API contracts and need automated guardrails to prevent silent breakage in downstream consumers between versions.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →

SchemGuard

API Schema Drift Monitor — detect breaking changes in OpenAPI specs before they break your consumers.

npm version License: MIT

Why

APIs break silently. A field gets renamed, an endpoint gets removed, an enum value disappears — and downstream consumers break in production. SchemGuard catches these before deploy.

Install

npm install -g schemaguard

Usage

Diff two specs

schemaguard diff old-api.yaml new-api.yaml

Output:

Found 11 change(s):

❌ BREAKING CHANGES (9):
──────────────────────────────────────────────────
  ⛔ [endpoint-removed]
     Endpoint removed: DELETE /pets/{petId}
     at: DELETE /pets/{petId}

  ⛔ [field-type-changed]
     Parameter type changed: petId (string → integer)
     at: GET /pets/{petId} > param petId
  ...

🚨 9 breaking change(s) detected — deployment blocked.

CI mode

schemaguard ci --spec ./openapi.yaml --baseline ./main-openapi.yaml
  • Exit 0 = no breaking changes, safe to deploy
  • Exit 1 = breaking changes detected, blocks the pipeline
  • Exit 2 = error (invalid spec, file not found)

Lint a spec

schemaguard lint ./openapi.yaml

Checks for missing operationId, missing descriptions, no security schemes, etc.

JSON output

schemaguard diff old.yaml new.yaml --format json

Returns structured JSON for programmatic consumption by agents and CI tools.

What it detects

Breaking changes (exit code 1)

RuleDescription
endpoint-removedAn endpoint was deleted
method-removedAn HTTP method was removed from a path
required-param-addedA new required parameter was added
param-removedAn existing parameter was removed
request-field-made-requiredA request field became required
field-type-changedA field's type was changed
response-field-removedA response field was removed
enum-value-removedAn enum value was narrowed
auth-requirement-changedSecurity schemes were modified
response-code-removedA response status code was removed

Non-breaking changes (info only)

RuleDescription
endpoint-addedA new endpoint was added
optional-param-addedA new optional parameter was added
response-field-addedA new response field was added
enum-value-addedAn enum value was widened
description-changedDescription or summary text changed
deprecatedAn endpoint was marked as deprecated

GitHub Actions

- name: Check API compatibility
  run: npx schemaguard ci --spec ./openapi.yaml --baseline ./baseline.yaml

Programmatic API

import { parseSpec, diffSpecs, formatDiff } from 'schemaguard';

const oldSpec = parseSpec('./v1.yaml');
const newSpec = parseSpec('./v2.yaml');
const result = diffSpecs(oldSpec, newSpec);

if (result.hasBreakingChanges) {
  console.log(`${result.breaking.length} breaking changes found`);
}

License

MIT

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
Monitoring & Observability
Registryactive
Package@sethclawd/schemaguard
TransportSTDIO
UpdatedFeb 21, 2026
View on GitHub

Related Monitoring & Observability MCP Servers

View all →
sipflow avatar
SIPFlow

sipflow/sipflow

Sipflow MCP is a SIP/VoIP/telecom grounding layer and PCAP analyzer: - Hybrid search across a curated VoIP corpus — ~40 vendor stacks, 60+ RFCs, STIR/SHAKEN, ATIS branded-calling specs - Vendor detection from a trace or a config blob (Kamailio, OpenSIPS, FreeSWITCH, Asterisk, SIP.js, JsSIP, ...) - Trace tools — minimize noisy headers, render SIP ladders as Mermaid, lint/diff/parse messages - Config review for Kamailio / OpenSIPS / FreeSWITCH / Asterisk with risk flags - SDP parse + offer/answer compare - STIR/SHAKEN Identity header validation and attestation explainer - E.164 number validation, response-code troubleshooter, DNS NAPTR/SRV + TLS cert diagnostics - One-shot hydration of `sipflow.dev/share/<token>` URLs All tools are read-only. Every result carries a verbatim `source_url` so the agent cites real RFC sections and vendor docs instead of hallucinating directive names or response-code semantics. A skill (`/sip-debugger`) and a file-scoped rule ship with the plugin so the agent reaches for these tools automatically when you're editing SIP material.
site.lanlan avatar
Lanlan

site.lanlan/website-builder

Build a hosted website by chatting. Snapshots, forms, analytics. Hand off the dashboard. Walk away.
slmusayev avatar
tls-radar

slmusayev/tls-radar

Run SSL/TLS scans, issue free Let's Encrypt certificates (private key stays local), and monitor certificate expiry from inside Claude Code or Cowork - through a single MCP server, no account needed for scans and issuance.
space.agentmemory avatar
Agentmemory MCP

space.agentmemory/agentmemory-mcp

Paid remote MCP for persistent AI agent memory, analytics, checkout, and search-readiness.
space.promptguardscan avatar
PromptGuard Scan MCP

space.promptguardscan/promptguardscan-mcp

Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.
space.syntheticuserlab avatar
SyntheticUser Lab MCP

space.syntheticuserlab/syntheticuserlab-mcp

Paid remote MCP for synthetic user testing, UX validation, analytics, checkout, and readiness.