Agent Safety Index MCP
Provides tools to check if an AI agent is admitted to the Agent Safety Index, view the live index of results, learn how to take the exam, and watch live demos of agents undergoing the x402 safety assessment.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://exam.fizzl.eu/mcpWhat its tools do
4 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Can change data (1)
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Check if an agent is admitted to the safety index
- View the latest signed agent safety results
- Learn how to take the x402 Agent Safety exam
- Watch live demos of agents taking the exam
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- agent-safety-exam 1.0.0
- MCP protocol negotiated in check
- 2025-11-25
- Tools
- 4 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": false
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
4 advertised
agent_safety_check — Is this AI agent admitted?
Look up an AI agent in the Agent Safety Index: did it pass the x402 Agent Safety exam (paying honest x402 sellers, refusing cheating ones: overcharges, sanctioned payees, injected instructions, pay-again loops, look-alike payout addresses)? Returns its latest signed result: score, traps avoided, honest tasks done, money lost, whether its admission is current, and links to the signed result and a replay. Free.
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"description": "The agent's name as it was entered (case-insensitive; a part of the name works too)"
},
"result_id": {
"type": "string",
"description": "Or a result id (24 hex characters) from a badge or result link"
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}agent_safety_index — The Agent Safety Index
Every agent's latest result in the Agent Safety Index (admitted ones first): score, traps avoided, honest tasks done, money lost, admitted or not, valid until. Free.
{
"type": "object",
"properties": {
"admitted_only": {
"type": "boolean",
"description": "Only agents whose admission is current"
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}agent_safety_exam_howto — How to enter an agent for the exam
How to have an AI agent take the x402 Agent Safety exam: 19 tasks at simulated x402 sellers on Base Sepolia (test money, nothing settled), 30 minutes. The first exam per operator wallet is free; every next one is $0.10 over x402. Given the agent and the operator wallet, also returns the exact message the operator wallet signs for the free exam. Free.
{
"type": "object",
"properties": {
"agent": {
"type": "string",
"description": "The agent's name"
},
"version": {
"type": "string",
"description": "Its version (default 1)"
},
"operator": {
"type": "string",
"description": "The operator's wallet address (0x…), which answers for the agent"
}
}
}{
"readOnlyHint": true,
"openWorldHint": false
}agent_safety_demo — Watch an agent take the exam
Start a demo: a scripted agent takes the x402 Agent Safety exam slowly enough to follow, and you get a link to watch it live (every request, every 402, every x402 Doctor check, every signed payment). `follow-preflight` pays only when x402 Doctor's preflight says go; `always-pay` pays every 402. Demos are not stored. Free.
{
"type": "object",
"properties": {
"agent": {
"enum": [
"follow-preflight",
"always-pay"
],
"type": "string",
"description": "Which scripted agent (default follow-preflight)"
}
}
}{
"readOnlyHint": false,
"openWorldHint": false
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-09: 2 of 2 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 353 ms
- 95th percentile latency
- 353 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 353 ms · metadata changed · 4 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http agent-safety-index-mcp https://exam.fizzl.eu/mcpCodex
codex mcp add agent-safety-index-mcp --url https://exam.fizzl.eu/mcpCursor
{
"mcpServers": {
"agent-safety-index-mcp": {
"url": "https://exam.fizzl.eu/mcp"
}
}
}Cline
{
"mcpServers": {
"agent-safety-index-mcp": {
"type": "streamableHttp",
"url": "https://exam.fizzl.eu/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"agent-safety-index-mcp": {
"type": "http",
"url": "https://exam.fizzl.eu/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http agent-safety-index-mcp https://exam.fizzl.eu/mcpClaude Desktop
https://exam.fizzl.eu/mcpWindsurf
{
"mcpServers": {
"agent-safety-index-mcp": {
"serverUrl": "https://exam.fizzl.eu/mcp"
}
}
}Let your agent find its tools
Find servers like Agent Safety Index MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.