janus-kinematic-drive
OfficialEnables USDC payment processing over the Solana blockchain for self-serve checkout and provision of Kinematic Drives.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@janus-kinematic-drive provision a kinematic drive for my project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Janus Kinematic Drive MCP - retired
Do not send USDC or any other payment for this package or its tools. The hosted Janus service and its self-service and pay-per-call payment paths are unavailable. No payment sent through instructions from an older release can provision a service or purchase a tool call.
ubos-janus-mcp is retained as a historical record of UBOS's earlier
deterministic-retrieval work. Version 0.1.4 is an inactive, fail-closed
retirement release. It exposes one local service_status MCP tool and makes no
network requests.
Successor
The proven retrieval and evidence mechanisms continue inside Sovereign Desk, a provider-neutral resident harness for coding agents. Read-only contract parity has been exercised through isolated Codex, Claude, and Gemini hosts.
That proof does not establish shared writes, multi-agent coordination, durable cross-provider memory, clean-machine installation, or customer value. OpenClaw has not been tested and is not claimed as supported.
The current managed Sovereign Desk pilot, its proof boundary, and its contact path are published at https://welcome-to-ubos.com/. This retired repository is not an order or payment surface. Contact: info@welcome-to-ubos.com.
Related MCP server: Memory Nexus MCP
Historical installation
Existing users may install the retirement release to replace older payment instructions with a local status notice:
pip install --upgrade ubos-janus-mcp==0.1.4The source remains available for provenance under the MIT license. Historical benchmarks describe deterministic retrieval fixtures, not the retired hosted service or a guarantee of generated-answer quality.
Available Tools
8 toolsjanus_askA
Ask Janus, the UBOS Kinematic Drive concierge, anything about getting or using a private Kinematic Drive (what it is, pricing, privacy, how to connect your agent). Grounded on real product knowledge and live data.
Inputs: question (required), mode.
kinematic_checkoutA
Buy a private Kinematic Drive with USDC, fully self-serve. Creates an order and returns payment instructions (Solana wallet + memo + amount). Send the USDC with the memo EXACTLY as given, then poll kinematic_checkout_status until it returns your provision token. No card, no account — pure on-chain.
Inputs: email (required).
kinematic_checkout_statusA
Check a Kinematic Drive checkout order: pending (with pay instructions) or paid (with your provision token).
Inputs: order_id (required).
kinematic_pricingA
Get the current Kinematic Drive pricing (live source of truth).
Inputs: no named parameters.
kinematic_provisionA
Request a private Kinematic Drive (managed onboarding). Records the request; the UBOS team mints an isolated drive for you. No charge or spin-up happens from this call.
Inputs: instance (required), repo, contact.
kinematic_statusA
Check whether a Kinematic Drive instance is up and running.
Inputs: instance.
ubos_store_callA
Call a UBOS x402 metered tool, pay-per-call. Choose any api_key string as your agent identity; with no balance you receive HTTP-402 pay instructions (send USDC on Solana to the wallet with memo = your api_key; credits in ~15s; retry). governor payload: {"action": "..."}; hotvessel payload: {"prompt": "..."}.
Inputs: api_key (required), product (required), payload.
ubos_store_productsA
List the UBOS x402 metered tools any agent can pay-per-call with USDC — e.g. governor (constitutional reality-check of an action, $0.005/call) and hotvessel (metered LLM completion, $0.01/call).
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Most tools are clearly distinct: provisioning, checkout, checkout status, instance status, pricing, store listing, store calling, and concierge all map to different actions. The main potential confusion is between kinematic_checkout and kinematic_provision (both lead to getting a drive) and between kinematic_checkout_status and kinematic_status, but the descriptions clarify the differences well.
The server uses consistent snake_case and useful prefixes like kinematic_ and ubos_store_, but the naming style is mixed: some tools are verb-led (kinematic_provision, kinematic_checkout), while others are noun-led (kinematic_pricing, kinematic_status). The pattern is readable and scannable, but it is not a uniform verb_noun convention.
Eight tools is a well-scoped set for this server's purpose. Each tool covers a distinct aspect of Kinematic Drive access, checkout, status, pricing, and UBOS store usage, with no obvious bloat or excessive granularity.
The core lifecycle is covered: request, checkout, checkout status, instance status, pricing, and concierge support. Minor gaps exist, such as no explicit cancellation or deprovisioning tool and no direct status endpoint for a provision request, but these are workable gaps given the concierge and live data grounding.
Related MCP Connectors
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Hosted persistent memory with semantic search, importance and TTL for AI agents.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Durable memory, headless browser and research for agents. Pay per call: x402 USDC on Base or credits
Related MCP Servers
AlicenseAqualityDmaintenanceProvides persistent, self-optimizing memory for AI agents, enabling them to remember preferences and context across sessions and share knowledge across multiple agents.410 npmISC- AlicenseAqualityDmaintenanceEnables AI agents with persistent semantic memory, including semantic recall, knowledge graphs, and instant domain expertise via pre-built Intelligence Packs.1054 npmMIT
- AlicenseBqualityBmaintenanceEnables AI agents to maintain persistent, searchable two-layer memory with 37 tools, hybrid search, knowledge graphs, and enterprise features like authentication and backups.723 PyPI1MIT
- AlicenseNot gradedqualityDmaintenanceProvides durable memory for AI agents with structured storage, semantic search, OAuth authentication, and lifecycle controls.10Apache 2.0