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

JPYC Agent MCP

yourbright-jp/jpyc-agent-mcp
HTTPregistry active
Summary

Connects Claude to JPYC stablecoin wallets on Polygon through an OAuth-protected remote endpoint. You get wallet creation, balance checks, JPYC transfers, and contract read/write operations all gated behind browser-based user consent. The quote-first execution pattern for transfers and contract writes lets you preview gas and effects before committing. Ships with Codex plugin metadata so ChatGPT can discover it directly from the repository root. If you're building payment flows or Web3 workflows that need user-owned wallet state without managing keys yourself, this gives you a secure RPC layer with session persistence across tools.

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 →

JPYC Agent MCP

JPYC Agent MCP can be used both as a public MCP endpoint and as a Codex plugin bundle. This repository now uses the repository root as the plugin root so Codex can discover it directly.

What It Supports

  • Polygon agent wallet creation and lookup
  • Wallet balance inspection
  • JPYC transfer quote and execution flows
  • Contract read calls
  • Contract write quote and execution flows
  • Transfer and contract call status tracking

Plugin Layout

Codex should discover the plugin from the repository root via the files below:

  • .codex-plugin/plugin.json
  • .mcp.json
  • skills/jpyc-agent-mcp/SKILL.md
  • skills/jpyc-agent-mcp/agents/openai.yaml
  • config/default.json

Public Endpoint

  • MCP endpoint: https://jpyc-info.com/api/jpyc-agent-mcp
  • OAuth issuer: https://jpyc-info.com/api/jpyc-agent-oauth
  • Resource metadata: https://jpyc-info.com/.well-known/oauth-protected-resource
  • Authorization server metadata: https://jpyc-info.com/.well-known/oauth-authorization-server
  • OpenID configuration: https://jpyc-info.com/.well-known/openid-configuration
  • Human sign-in page: https://jpyc-info.com/mcp/connect
  • MCP Registry auth file: https://jpyc-info.com/.well-known/mcp-registry-auth

The endpoint is OAuth-protected. Users must log in and grant consent before private wallet operations can run. If you open the MCP endpoint directly in a browser, it redirects to https://jpyc-info.com/mcp/connect. If an MCP client receives 401 unauthorized, it should follow WWW-Authenticate and the resource metadata above to discover the OAuth flow. If ChatGPT/Codex does not surface a full authorization URL automatically, open https://jpyc-info.com/mcp/connect in the browser as the canonical human fallback. Low-level manual auth with /api/jpyc-agent-oauth/start remains available for debugging, but it is not the primary documented path. Clients using the low-level flow must keep the returned auth_session_secret private and present it when polling /api/jpyc-agent-oauth/auth-session.

For the complete OAuth contract and exact URLs, see docs/auth.md and config/oauth.json.

Claude Code

Claude Code does not natively support streamable-http MCP servers. Use mcp-remote to bridge streamable-http + OAuth to stdio.

Quick Start

Add the following to your project .mcp.json or ~/.claude/settings.json:

{
  "mcpServers": {
    "jpyc-agent-mcp": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://jpyc-info.com/api/jpyc-agent-mcp"
      ]
    }
  }
}

On first connection, mcp-remote opens a browser for OAuth consent. After authentication, all tools are available immediately.

Client Token Persistence

This repository defines the OAuth-protected MCP endpoint and the plugin metadata needed for Codex discovery. It does not implement client-side credential storage on behalf of Codex, ChatGPT, or any other MCP client.

Expected client behavior:

  1. Start the OAuth flow against the JPYC Agent OAuth issuer
  2. Receive the issued bearer token or equivalent session credential
  3. Persist that credential in the client's local secure storage
  4. Reuse it on subsequent MCP calls to https://jpyc-info.com/api/jpyc-agent-mcp
  5. Verify the recovered session with auth_status

If a client can complete browser login but cannot persist and reuse the issued credential locally, the MCP integration is incomplete from the user's point of view. In that case, the fix belongs in the MCP client implementation rather than this repository's server-side OAuth protocol.

For local operator workflows, this repository includes helpers that persist the issued refresh token with DPAPI and reuse it across future sessions:

  • docs/local-token-cache.md
  • scripts/jpyc_oauth_cache.py (Python, Windows)
  • scripts/jpyc_oauth_cache.ps1 (PowerShell, Windows)

MCP Registry

This repository includes server.json for publishing the remote server to the public MCP Registry using the domain-based namespace com.jpyc-info/jpyc-agent-mcp.

For HTTP-based domain verification, host the exact text value v=MCPv1; k=...; p=... at https://jpyc-info.com/.well-known/mcp-registry-auth. In the jpyc-info deployment, that endpoint is served from the MCP_REGISTRY_AUTH environment variable.

Main Tools

  • auth_status
  • list_agent_wallets
  • get_agent_wallet
  • create_agent_wallet
  • get_agent_wallet_balance
  • quote_transfer
  • transfer_jpyc
  • list_transactions
  • get_transfer_status
  • read_contract
  • quote_contract_write
  • execute_contract_write
  • list_contract_call_history
  • get_contract_call_status

Detailed request and response examples are in docs/tools.md.

Recommended Flow

  1. Check auth_status
  2. Inspect wallets with list_agent_wallets
  3. Create a wallet only if needed with create_agent_wallet
  4. Check balances before transfers
  5. Use quote-first execution for transfers and contract writes

Transfer flow:

  1. quote_transfer
  2. transfer_jpyc

Contract write flow:

  1. quote_contract_write
  2. execute_contract_write

Notes

  • This repo does not include secrets.
  • This repo does not include private keys or signer material.
  • The bundled skill is intended to keep Codex inside the JPYC Agent MCP tool surface.
  • For more details, see docs/auth.md, config/oauth.json, and docs/openai-and-mcp.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 →
Categories
AI & LLM Tools
Registryactive
TransportHTTP
UpdatedMar 31, 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