MCP security report
api.jarvisclaw.ai
C73/100
Security grade CA few things are worth a closer look before connecting.
Connected ✓9 tools scanned
https://api.jarvisclaw.ai/mcp
mediumdiscover_agents
Enables delegation of tasks/data to unknown third-party agents
This tool lets the calling agent discover and connect directly to arbitrary third-party agents on the network and 'delegate' work to them. Nothing in the tool restricts what data gets sent to these external agents or vets their trustworthiness. An agent could be induced to forward user conversation content, credentials, or task data to an untrusted external MCP endpoint without the user's explicit awareness or consent.
mediumaip_execute_with_budget
Autonomous financial transaction execution with on-chain settlement
This tool resolves a provider, executes a paid call, and settles payment automatically (via x402/on-chain) in a single step, with only a soft 'hard cap' (max_total_usd) as a guardrail. This gives the agent the ability to autonomously spend real money on the user's behalf across many intent types without a per-transaction confirmation step, which is a broad capability relative to a simple 'run a task' tool and could result in unwanted charges if invoked repeatedly or with a high budget default.
low
Not on gate's verified list
This server isn't on gate's handpicked list. That's not necessarily bad, but there's no third-party signal about it — review its tools carefully.
lowsearch_apis
Surfaces arbitrary user-published third-party APIs for invocation
The tool explicitly includes 'APIs other developers have published' alongside a curated catalogue. Results feed directly into get_api_detail and subsequent invocation, meaning the agent could be routed into calling unvetted, attacker-controlled endpoints that receive user data or return manipulated instructions, with no described vetting/sandboxing of these community-submitted APIs.
Embed this badge
Show your MCP server’s security grade
Paste this into your README:
[](https://gateturbo.com/report/c39472b9-05dc-4e5e-8647-bfb7ebd3d7bf)Scanned 9/5/2026 · This is a point-in-time snapshot of the server’s public tools. Re-scan.
Connect this server safely with gate.
Continuous re-scans, drift alerts, per-tool allow/ask/block, and a log of every call.
Monitor it — free