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

Hive Sla Monitor

srotzin/hive-mcp-sla-monitor
HTTPregistry active
Summary

This is an observability layer for agent fleets that want to track uptime and latency without settling claims. Register a health endpoint with target SLA thresholds, and the service probes it every 60 seconds to record uptime and p95 latency. When the rolling window misses targets, it writes a breach record you can query via MCP tools like sla_status and sla_breach_history. All paid reads use USDC on Base with inline payment proofs in the X-Payment header. The service caps at 100 active monitors and explicitly disclaims underwriting or settlement. Useful if you're running coordinated agents and need third-party SLA data without building your own probe infrastructure.

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 →

hive-mcp-sla-monitor

srotzin/hive-mcp-sla-monitor MCP server

SLA observation broker for the A2A network. Agents register a public health endpoint with target uptime and p95 latency; the shim probes it on a 60s schedule (read-only HTTP, 8s timeout) and records the result. When a rolling window misses the targets, a breach record is written. Reading breach records is paid. Inbound only. ENABLE=true by default.

Brand color: #C08D23 (Pantone 1245 C, Hive Civilization gold).

Observation only

Hive does not underwrite or settle SLA claims. This is observational data only. The shim does not hold custody, does not pay claims, and does not indemnify counterparties. The disclaimer rides every paid response and every breach record.

Surface

LayerEndpointDescription
MCPPOST /mcpJSON-RPC 2.0, Streamable-HTTP, protocol 2024-11-05.
DiscoveryGET /.well-known/mcp.jsonTool list and transport metadata.
RESTPOST /v1/sla/registerRegister an endpoint. 402 if no proof.
RESTGET /v1/sla/status/{id}Read observed uptime and p95. 402 if no proof.
RESTGET /v1/sla/breaches?monitor_id=…Read recent breach records. 402 if no proof.
RESTGET /v1/sla/todayUTC-day ledger snapshot. Free.
HealthGET /healthLiveness, pricing, recipient address.
RootGET /HTML for browsers, JSON for agents (Accept-header sniff).

Tools

NameTierCostDescription
sla_register1$0.01/probeRegister a public endpoint for probing.
sla_status1$0.01Read observed uptime and p95 over the rolling window.
sla_breach_history2$0.10Read recent breach records. Disclaimer rides every record.
sla_unregister0freeDeactivate a monitor.

Probe semantics

The scheduler scans active monitors every 60 seconds and issues a GET with an 8-second timeout. 2xx and 3xx count as up; 5xx and timeouts count as down. Probe rows are stored at /tmp/sla.db along with the monitor record and any breach records.

The breach evaluator runs after each probe. It looks at the rolling window (default 60 minutes), computes observed uptime and observed p95 latency, and records a breach if either target is missed. Repeated breaches inside half the window are de-bounced so a single bad window does not fan out.

The service caps active monitors at 100 (SLA_MAX_MONITORS) to keep probe fan-out deterministic.

x402 envelope

Every paid endpoint returns a 402 envelope on first hit:

{
  "error": "payment_required",
  "x402_version": 1,
  "disclaimer": "Hive does not underwrite or settle SLA claims. This is observational data only.",
  "payment": {
    "nonce": "…",
    "amount_usd": 0.01,
    "accept_min_usd": 0.007,
    "accepts": [{
      "chain": "base",
      "asset": "USDC",
      "contract": "0x833589fcd6edb6e08f4c7c32d4f71b54bda02913",
      "decimals": 6,
      "recipient": "0x15184bf50b3d3f52b60434f8942b7d52f2eb436e",
      "scheme": "exact"
    }],
    "tier": 1,
    "product": "sla_register",
    "floor_pct": 0.7
  }
}

Submit the proof inline via X-Payment header on the retry, or POST it to mint an access token used in X-Hive-Access.

Pricing inherits the hivemorph barter floor pattern: the envelope advertises both amount_usd (asking) and accept_min_usd (floor). A client may submit a proof whose on-chain paid amount is anywhere in [floor, asking] and the shim accepts it.

Settlement

USDC on Base L2 (0x833589fcd6edb6e08f4c7c32d4f71b54bda02913) to the recipient address above. Verification reads Transfer logs on the receipt against the configured Base RPC. Real chain reads, no mocks. A single tx_hash may only be redeemed once.

Environment

VariableDefaultNotes
PORT3000HTTP port.
ENABLEtrueWhen false, only /health and / respond.
WALLET_ADDRESS0x1518…436eUSDC recipient.
SLA_REGISTER_PRICE_USDC0.01Per registration.
SLA_BREACH_PRICE_USDC0.10Per breach-history read.
SLA_STATUS_PRICE_USDC0.01Per status read.
SLA_PROBE_INTERVAL_MS60000Probe loop interval.
SLA_PROBE_TIMEOUT_MS8000Per-probe HTTP timeout.
SLA_MAX_MONITORS100Active monitor cap.
BASE_RPC_URLhttps://mainnet.base.orgBase L2 JSON-RPC.
SLA_DB_PATH/tmp/sla.dbSQLite path.

Run

npm install
npm start
# → http://localhost:3000/health

License

MIT. Author: Steve Rotzin steve@thehiveryiq.com.

Hive Civilization Directory

Part of the Hive Civilization — agent-native financial infrastructure.

  • Endpoint Directory: https://thehiveryiq.com
  • Live Leaderboard: https://hive-a2amev.onrender.com/leaderboard
  • Revenue Dashboard: https://hivemine-dashboard.onrender.com
  • Other MCP Servers: https://github.com/srotzin?tab=repositories&q=hive-mcp

Brand: #C08D23

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 ToolsMonitoring & Observability
Registryactive
TransportHTTP
UpdatedApr 28, 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