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
srotzin avatar

Hive Compute Grid

srotzin/hive-mcp-compute-grid
HTTPregistry active
Summary

A cross-cloud compute auction system that bids across io.net, Akash, and Render to find you the cheapest GPU or CPU capacity. The server exposes 11 tools: quote gathers prices without committing, solve runs the full auction and returns a Groth16 proof plus signed receipt, book reserves the winning provider, and verify_proof checks any Groth16 envelope for $0.001. Behind the scenes, a 15-agent fleet handles workload decomposition, capacity listening, and settlement reporting. Every auction result gets logged to a canonical ledger with USDC telemetry on Base. Reach for this when you need decentralized compute with verifiable cost minimization and real settlement rails, not mock testnet tokens.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
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 →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
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 →

Hive Civilization MCP Gateway · Solver auction across io.net / Akash / Render · signed receipts

hive-mcp-compute-grid

Solver auction across io.net / Akash / Render · signed receipts

Smithery Glama Live Release License

https://mcp-compute-grid.thehiveryiq.com/mcp


HiveComputeGrid

Cross-pool compute auction grid — 15-agent fleet, 6 driver types, Groth16-verified

MCP server for the Hive Compute Grid. A 15-agent fleet across 6 driver types (cross-pool auction, workload decomposition, verification fleet, capacity listener, QVAC mesh orchestrator, settlement reporting) bids on compute capacity from io.net, Render, Akash, Aleo provers, and any custom hMo driver. Verification fleet emits Groth16-style proofs at $0.001/proof. Capacity Listener is read-only by spec (no bids, no hedges, no derivatives — energy futures permanently rejected by R3 council).

Compute Grid D2 build (v1.1.0) — real auction solver + io.net/Akash/Render adapters live, Groth16-shaped selection proofs, cost telemetry to canonical receipt ledger.


What this is

hive-mcp-compute-grid is a Model Context Protocol (MCP) server that exposes the HiveComputeGrid platform on the Hive Civilization to any MCP-compatible client (Claude Desktop, Cursor, Manus, etc.). The server proxies to the live production backend at https://receipts.thehiveryiq.com.

  • Protocol: MCP 2024-11-05 over Streamable-HTTP / JSON-RPC 2.0
  • Transport: POST /mcp
  • Discovery: GET /.well-known/mcp.json
  • Health: GET /health
  • Settlement: Real rails. USDC / USDT on Base, Ethereum, Solana. No mock. No simulated.
  • Brand gold: Pantone 1245 C / #C08D23

Tools (v1.1.0 — 11 tools)

ToolDescription
computegrid_list_agentsList the 15-agent fleet across all 6 driver types.
computegrid_get_capacityRead-only capacity view from the Capacity Listener fleet.
computegrid_list_providersList enabled provider adapters (io.net, Akash, Render) and their upstream health.
computegrid_quoteGather quotes across enabled providers WITHOUT running the auction (price discovery).
computegrid_solveRun the cross-pool auction. Returns chosen provider, all quotes, Groth16-shaped selection proof, signed receipt, settlement path. Persists cost_usdc telemetry to the Hive ledger.
computegrid_bookReserve compute with the chosen provider (gated on provider keys; 503 with documented missing-key error if not configured).
computegrid_statusPoll a provider booking by id.
computegrid_releaseRelease a reservation.
computegrid_auditRead recent compute_grid_auction entries from the canonical receipt ledger.
computegrid_verify_proofSubmit any Groth16 proof envelope to the Verification Fleet ($0.001/proof).
computegrid_verify_selectionIndependently verify a selection proof from a prior /solve response.

Backend endpoints

MethodPathPurpose
GET/v1/compute-grid/agents15-agent fleet across 6 driver types
GET/v1/compute-grid/capacityRead-only capacity telemetry
GET/v1/compute-grid/providersEnabled adapters + upstream health
POST/v1/compute-grid/quoteGather quotes without running auction
POST/v1/compute-grid/solveRun cross-pool auction → proof + receipt + settlement
POST/v1/compute-grid/bookReserve compute (gated on provider keys)
GET/v1/compute-grid/statusPoll booking status
POST/v1/compute-grid/releaseRelease reservation
GET/v1/compute-grid/auditRead recent auction telemetry
POST/v1/compute-grid/verifyVerify any Groth16 proof
POST/v1/compute-grid/verify-selectionIndependent verifier for selection proofs

Run locally

git clone https://github.com/srotzin/hive-mcp-compute-grid.git
cd hive-mcp-compute-grid
npm install
npm start
# server up on http://localhost:3000/mcp
curl http://localhost:3000/health
curl http://localhost:3000/.well-known/mcp.json

Connect from an MCP client

Claude Desktop / Cursor / Manus — add to your mcp.json:

{
  "mcpServers": {
    "hive_mcp_compute_grid": {
      "command": "npx",
      "args": ["-y", "mcp-remote@latest", "https://your-deployed-host/mcp"]
    }
  }
}

Hive Civilization

Part of the Hive Civilization — sovereign DID, USDC settlement, HAHS legal contracts, agent-to-agent rails.

Categories: compute, depin, agent-to-agent, infrastructure, verification, web3.

License

MIT (c) Steve Rotzin / Hive Civilization

Agent-native (v1.1.2)

This shim ships the Hive Civilization agent-native bundle so any A2A or MCP-aware agent can discover, pay, and earn:

  • A2A AgentCard — `GET /.well-known/agent.json` (also at `/agent.json`).
  • Open Agent Card (OAC) JSON-LD — embedded inline at `/` and `/agent.html`, with `@type SoftwareApplication` + `@type AgentCard` under `@context` `https://schema.org\` + `https://a2a-protocol.org/v1\`.
  • Earn rails — every shim exposes `hive_earn_register`, `hive_earn_me`, `hive_earn_leaderboard` against `https://receipts.thehiveryiq.com/v1/earn/*\`. Resilient to upstream cold-start: returns a structured "earn rails not yet live" body if upstream isn't yet deployed.
  • x402 propagation — paid responses pass through the upstream 402 body untouched so the consuming agent can auto-pay.
  • Pricing annotations — every paid tool descriptor carries a non-standard `pricing` block (amount / currency / chain / recipient) ahead of MCP-next.
  • Brand: Hive Civilization gold `#C08D23`. Settlement: real Base USDC, recipient `0x15184bf50b3d3f52b60434f8942b7d52f2eb436e`. No mock, no testnet.

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


About Hive Civilization

This MCP server is part of the Hive Civilization ecosystem — post-quantum-ready receipt infrastructure for agent-to-agent (A2A) commerce.

Each transaction can be receipted with post-quantum receipts using ML-DSA-65 (NIST FIPS 204) dual signatures and ML-KEM-768 (NIST FIPS 203) key encapsulation. Receipts are anchored by Swarm-MAPET 16-axis Byzantine consensus and settled in USDC on Base 8453.

Pricing: per-call profiles from Nano $0.0001 to Swarm $0.0096. See pricing.

Learn more:

  • How agent-to-agent commerce works (A2A / AP2 / MCP primer)
  • Hive platform architecture
  • Developer SDKs (Node, Python, Go)
  • Compliance & EU AI Act alignment
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
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 →
Categories
Design & Creative
Registryactive
TransportHTTP
UpdatedMay 4, 2026
View on GitHub

More from srotzin

  • Hive Credit
  • Hive DePIN
  • Hive Evaluator
  • Hive Gateway
  • Hive Insurance Broker
  • Hive Mos
  • Hive Swap
  • Hive Trade
  • Hive Vault
  • HiveAttest
  • Execute Intent
  • Hive Address Screen
  • Hive Agent Kyc
  • Hive Agent Quota
  • Hive Agent Storage
  • Hive Aml Screen
  • Hive Auction
  • Hive Backup
  • Hive Barter
  • Hive Capital
  • Hive Cdn
  • Hive Compute
  • Hive Consult
  • Hive Credit Broker

Related Design & Creative MCP Servers

View all →
studio.approval avatar
Approval Studio

studio.approval/mcp

Approval Studio is an online proofing software for creative teams and everyone working with designs
tech.skybridge.times-up avatar
Time's up Skybridge example App

tech.skybridge.times-up/time-s-up

Skybridge Example App showcasing a Time's up game with the LLM
thegridwork avatar
Siteaudit

thegridwork/siteaudit

Audit websites for accessibility, performance, SEO, design, and mobile. 47 WCAG checks.
tonyc23 avatar
Systemonomic — Work Domain Analysis & AI Task Suitability

tonyc23/systemonomic-mcp

Model work domains, score tasks for AI suitability, and design organisations.
useorgx avatar
OrgX

useorgx/orgx-mcp

OrgX is coordination infrastructure for AI-native teams. It gives your LLM a persistent organizational layer: initiatives with milestones and tasks, human-in-the-loop decision workflows, specialist agent delegation, and cross-session memory that survives tool switching. What you can do with OrgX via MCP: Scaffold initiatives — decompose a goal into workstreams, milestones, and tasks in one call Manage decisions — create, review, approve, or reject decisions with audit trails Delegate to specialist agents — spawn tasks for domain agents (engineering, marketing, product, sales, operations, design) and monitor their progress Query organizational memory — search past decisions, artifacts, and learnings across initiatives Track progress — get initiative health, agent status, blockers, and morning briefs Plan and prioritize — score queues, get next-action recommendations, and run autonomous sessions with budget guardrails OrgX is built for solo founders and small teams who work across multiple AI tools and lose context between sessions. Instead of manually shuttling context between Claude, Cursor, and ChatGPT, OrgX holds the organizational graph so every tool sees the same state.
video.quiz avatar
Api

video.quiz/api

Quiz.Video MCP: list, create, AI-generate, and render quiz and flashcard videos.