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

DevSpeak

juanjaragavi/devspeak
7 toolsauthSTDIO, HTTPregistry active
Summary

This server sits between your AI tools and DevSpeak's translation engine to convert informal technical descriptions into formal specifications. It exposes operations that take natural language requirements or architecture notes and turn them into structured technical documents with consistent terminology and format. Reach for it when you're working in Claude or another AI IDE and need to transform rough technical thoughts into polished specs without context switching. The streamable HTTP transport means it works across different environments, not just local setups. Essentially bridges the gap between how developers talk about systems and how those systems need to be documented.

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.

7 tools
translate_textTranslates and optimizes informal text into formal, audience-specific technical specifications.6 params

Translates and optimizes informal text into formal, audience-specific technical specifications.

Parameters* required
tonenumber
Tone (0=Concise, 100=Detailed)
inputstring
Input text (min 10 chars)
formatstring
Output formatone of Technical Spec · Jira Tickets · API Design · RFC · Data Model · Prompt
contextstring
Tech contextone of Backend · Frontend · Mobile · Data/ML · DevOps
audiencestring
Target audienceone of Junior Dev · Senior Dev · Tech Lead · SRE · Data Engineer
customInstructionsstring
Optional custom instructions
translate_markdownTranslates README and docs content while preserving Markdown structure, links, and code fences.6 params

Translates README and docs content while preserving Markdown structure, links, and code fences.

Parameters* required
tonenumber
Tone (0=Concise, 100=Detailed)
inputstring
Input text (min 10 chars)
formatstring
Output formatone of Technical Spec · Jira Tickets · API Design · RFC · Data Model · Prompt
contextstring
Tech contextone of Backend · Frontend · Mobile · Data/ML · DevOps
audiencestring
Target audienceone of Junior Dev · Senior Dev · Tech Lead · SRE · Data Engineer
customInstructionsstring
Optional custom instructions
refine_translationIteratively refines generated output based on user feedback.8 params

Iteratively refines generated output based on user feedback.

Parameters* required
tonenumber
Tone (0-100)
formatstring
Output formatone of Technical Spec · Jira Tickets · API Design · RFC · Data Model · Prompt
contextstring
Tech contextone of Backend · Frontend · Mobile · Data/ML · DevOps
audiencestring
Target audienceone of Junior Dev · Senior Dev · Tech Lead · SRE · Data Engineer
feedbackstring
User feedback / changes requested
originalInputstring
Original user input
previousOutputstring
Previous generated output
preserveMarkdownboolean
Preserve Markdown structure
detect_languageDetects the primary natural language of the input text.1 params

Detects the primary natural language of the input text.

Parameters* required
inputstring
Text to analyze
list_languagesReturns a list of supported natural languages.

Returns a list of supported natural languages.

No parameter schema in public metadata yet.

auth_confirmVerifies the current API credentials against the DevSpeak backend.

Verifies the current API credentials against the DevSpeak backend.

No parameter schema in public metadata yet.

patch_translation_noteSurgically updates a note in the DevSpeak Notes Workspace by applying replace operations.2 params

Surgically updates a note in the DevSpeak Notes Workspace by applying replace operations.

Parameters* required
opsarray
List of patch operations to apply
noteIdstring
The ID of the note to update
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

DEVSPEAK_API_KEY*secret

DevSpeak API key. Generate one from Settings → API Keys in the DevSpeak dashboard.

DEVSPEAK_API_URL

Optional DevSpeak API base URL override. Leave unset to use https://www.devspeak.dev.

Categories
AI & LLM Tools
Registryactive
Package@devspeak/mcp
TransportSTDIO, HTTP
AuthRequired
UpdatedApr 27, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
SkillFM LLM Cost Optimizer

io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Llm Orchestration Agent

io.github.mikerawsonnz/llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Authenticated Llm Agent

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Copilot Memory MCP

labforgedev/copilot-memory-mcp

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
1
Agent Prompt Injection Firewall Mcp

csoai-org/agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Authenticated Multi Llm Agent

io.github.mikerawsonnz/authenticated-multi-llm-agent

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f