mcpField
H
Hive Openclaw Bridge

Hive Openclaw Bridge

Remote
thehiveryiq.comFinance0Updated 25w ago

About Hive Openclaw Bridge

Hive Openclaw Bridge is an MCP server connecting OpenClaw's layered payment governance model to Hive Gamification's paid services. It atomically reserves budget across namespace, user, agent, and task scopes, then settles or releases the reservation after the upstream request.

Key features

  1. 01Check four-level hierarchical budgets
  2. 02Atomically reserve, settle, and release funds
  3. 03Preflight budget headroom by scope
  4. 04Set per-key budget caps
  5. 05List and inspect eight paid doors

Use cases

  1. 01Check budget before a paid call
  2. 02Prevent spending beyond any scope's cap
  3. 03Settle a reservation after a successful request
  4. 04Release a reservation when a request fails

MCP support

It exposes tools for budget status, checks, cap changes, and paid-door operations to MCP clients. Paid calls reserve funds across four budget levels before requesting Hive Gamification, then settle or release based on the result.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://hive-mcp-gateway.onrender.com/openclaw-bridge/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

hive-mcp-openclaw-bridge

srotzin/hive-mcp-openclaw-bridge MCP server

Reference integration with @kinthaiofficial's OpenClaw 3-layer payment governance framework. MCP server that wraps Hive Gamification's 8 BOGO doors behind a 4-level hierarchical budget — atomic reserve, upstream POST, settle/release. Real rails. No mock settlement.

Brand: Hive Civilization gold #C08D23 (Pantone 1245 C). License: MIT.


Why this exists

OpenClaw's three-layer model splits payment governance into three concerns:

LayerConcernWhere it lives
Layer 1Internal hierarchical budget — atomic reserve / settlethis server
Layer 2Inter-agent millicent ledger settled at epoch boundariesOpenClaw
Layer 3External x402 settlement on real railsHive Gamification

This bridge demonstrates the Layer 1 ↔ Layer 3 seam. Every paid call to a Hive door (computational-debt, protocol-consensus-tax, pheromone-priority, zk-compliance-shield, capability-leasing, guild-synergy, audit-trail-premium, bounty-routing) is gated by an atomic reservation against every level in the caller's scope path:

Namespace → User → Agent → Task

The most-restrictive level governs. If any level is short of headroom, the upstream HTTP request is never made and no x402 settlement is signed.

The same BudgetHook interface is exposed from @hivemorph/qvac-client v0.2 — drop your own implementation in to wire this hierarchy into a different runtime.

Background reading

Tools

ToolWhat it does
budget_statusInspect caps, spend, reservations, headroom across all 4 levels
budget_set_capOverride a per-key cap at one level
budget_checkRead-only pre-flight against a proposed amount + scope
doors_listList all 8 BOGO doors with endpoint, price, asset, term
door_economicsFetch live /economics for one door
bogo_claimClaim first-use-free via /v1/bogo/claim
door_subscribeCanonical gated path — atomic reserve → upstream POST → settle/release

Doors

DoorEndpointPriceTerm
computational-debt/v1/debt/subscribe0.50 USDC30d
protocol-consensus-tax/v1/pct/subscribe0.25 USDC1 read
pheromone-priority/v1/pheromone/subscribe5.00 USDC30d
zk-compliance-shield/v1/compliance/subscribe1.00 USDC30d
capability-leasing/v1/lease/start0.15 USDC1h
guild-synergy/v1/guild_synergy/subscribe10.00 USDC30d
audit-trail-premium/v1/audit_premium/subscribe3.00 USDC30d
bounty-routing/v1/bounty_routing/route0.50 USDC1 routing

Backend: https://hive-gamification.onrender.com. All endpoints are live and verified.

Lifecycle of a paid call

client → tools/call door_subscribe { door_id, did, scope }
       → atomicReserve(scope, price, asset)
           ├─ each level checked: namespace, user, agent, task
           ├─ headroom = cap − spent − reserved
           └─ short on any level? reject before signing
       → POST hive-gamification.onrender.com<endpoint>
       → 2xx? settle(reservationId)
         non-2xx or throw? release(reservationId)
       → return { ok, reservationId, binding_level, upstream }

Quickstart

git clone https://github.com/srotzin/hive-mcp-openclaw-bridge
cd hive-mcp-openclaw-bridge
npm install
npm start

Then from any MCP client:

POST http://localhost:3000/mcp
{ "jsonrpc": "2.0", "id": 1, "method": "tools/list" }

Configuration

EnvDefaultMeaning
PORT3000listen port
HIVE_BASEhttps://hive-gamification.onrender.comupstream base URL
HIVE_TIMEOUT_MS15000upstream fetch timeout
NAMESPACE_CAP50default namespace-level cap (USDC)
USER_CAP10default user-level cap
AGENT_CAP2default agent-level cap
TASK_CAP0.50default task-level cap

Per-key caps override defaults via budget_set_cap.

Related

License

MIT — see LICENSE.

Hive Civilization Directory

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

Brand: #C08D23

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.