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

Realmint

realmint-io/mcp
HTTPregistry active
Summary

Gives Claude read-only access to Realmint's catalog of tokenized real-world assets across chains. You get seven tools: search the catalog, pull spot prices and historical charts, retrieve risk and rights scores across six dimensions (backing, enforceability, control, exit, liquidity, social), check issuer metadata change history, and map routable venues ranked by liquidity. The scoring is opinionated: composite scores below 55 flag high-risk tokens, and anything migrated or discontinued gets capped at 49. Reach for this when you need an AI to evaluate treasury-grade stablecoins, compare tokenized gold products, or route large RWA acquisitions without hardcoding asset metadata. No keys required for the public catalog, and trade execution stays client-side in their HTTP API.

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 →

Realmint MCP

Agent-native access to the Realmint catalog of tokenized real-world assets (RWAs): scoring, market data, route support, and price history — exposed as native tools over the Model Context Protocol.

The MCP surface is read-only by design. Trade execution lives in the Realmint HTTP API and requires client-side wallet signing — keys never touch the MCP server.

Endpointhttps://mcp.realmint.io/mcp
TransportStreamable HTTP
AuthNone for the public catalog
Discovery card/.well-known/mcp/server-card.json
StatusLive since May 2026

What you can ask it

CapabilityExample prompt
Score risk & rights"Score Tether Gold and tell me if it's safe for our DAO treasury"
Search the catalog"Find tokenized treasuries on Ethereum with no freeze capability"
Track issuer changes"Has anything in my watchlist changed control parameters this month?"
Map routable venues"Where can I acquire 100k of OUSG, ranked by liquidity?"
Pull market & price data"Show me PAXG's spot price, 24h volume, and 6-month chart"

Add it to your client

Claude.ai (custom remote connector)

  1. Settings → Connectors → Add custom connector
  2. Server URL: https://mcp.realmint.io/mcp
  3. Auth: none required
  4. Save and start asking the example prompts above.

Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "realmint": {
      "transport": {
        "type": "streamable-http",
        "url": "https://mcp.realmint.io/mcp"
      }
    }
  }
}

Restart Claude Desktop.

Cursor / Cline / Continue / any MCP client

Configure a remote MCP server with:

  • URL: https://mcp.realmint.io/mcp
  • Transport: streamable-http
  • Auth: none

Programmatic

curl -X POST https://mcp.realmint.io/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

You should see 7 tools, each with annotations.title and annotations.readOnlyHint=true.


The 7 tools

ToolPurpose
realmint_list_assetsEnumerate the full catalog with schemas
realmint_list_marketSpot price, 24h change, volume, market cap, history
realmint_get_assetFull schema for one asset (by lowercased ticker)
realmint_get_asset_historyVersioned metadata change history
realmint_get_scoreSix-dimension Risk & Rights Score + composite
realmint_get_route_supportRoutable venues + per-venue scores
realmint_get_price_historyTime-series prices (5m/1h/1d auto-cascading)

All tools are read-only. Annotations follow the MCP spec:

readOnlyHint:    true
destructiveHint: false
idempotentHint:  true
openWorldHint:   true

The complete tool catalog with descriptions, inputs, and titles is published in the discovery card.

The Risk & Rights Score

realmint_get_score returns a 0–100 composite plus six per-dimension scores:

  • backing — proof of reserves, audit cadence, backing mechanism.
  • enforceability — governing law, issuer verification, legal documents.
  • control — issuer power risk: freeze, mint, burn, blacklist, upgrade.
  • exit — redemption, transferability, KYC/whitelist, settlement, holding periods.
  • liquidity — market data, venue count, evidence docs.
  • social — recency-weighted Twitter activity; unverified handles penalized.

Suggested decision thresholds:

  • composite ≥ 75 → typical case, proceed.
  • 55 ≤ composite < 75 → elevated friction (gates, missing audits); review the asset's flags before acting.
  • composite < 55 → high risk; abort or require explicit user override.

Tokens with a non-null metadata.lifecycle (migrated, discontinued, abandoned) are score-capped at 49 by policy.


Troubleshooting

HTTP 403 — "Invalid Origin header" The server enforces Origin-header validation as required by the Anthropic Connectors Directory. claude.ai, chatgpt.com, mcp.realmint.io, app.realmint.io, and realmint.io are pre-allowed. If you operate from a different origin and need it added, email us at the address below.

Tool returns an empty list The Realmint catalog is curated — at any given time it indexes ~30 assets. Run realmint_list_assets to see the current set before asking about a specific ticker.

Asset ID format Asset IDs are lowercased tickers — xaut, not XAUT; paxg, not PAXG.

metadata.lifecycle is non-null The token has been migrated, discontinued, or abandoned. Trading is disallowed and the score is capped at 49. The lifecycle field tells you why and points to the replacement (if any).

Price history returns coarser buckets than asked The server cascades to coarser buckets (5m → 1h → 1d) when the requested bucket is empty for that asset. Look at effective_granularity in the response for what was actually returned.


Security & privacy

  • Read-only. No write tools, no trade execution, no destructive operations.
  • No PII collected by the MCP server. The optional x-api-key header is used solely for upstream rate-limit identification.
  • HTTPS termination via Traefik.
  • Origin / Host validation enabled at the FastMCP layer (DNS rebinding protection).
  • Privacy policy: https://realmint.io/privacy
  • Terms of service: https://realmint.io/terms

Versioning & changelog

This connector is versioned alongside the Realmint platform. Substantive changes to tool surfaces or output shapes will be announced in this README and reflected in the discovery card (serverInfo.version).


Contact & support

  • General: contact@realmint.io
  • Realmint web app: https://realmint.io
  • API docs: https://api.realmint.io/docs
  • Discovery card: https://app.realmint.io/.well-known/mcp/server-card.json

Realmint is operated by 0xFútbol Inc, a BVI Business Company (registration 2169115), trading as Realmint. The MCP server source lives in a private repository; the hosted endpoint at https://mcp.realmint.io/mcp is the supported public interface.

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 ToolsSearch & Web Crawling
Registryactive
TransportHTTP
UpdatedMay 21, 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