Freysa Security is listed as active in the registry but did not answer our last check. It exposes 11 tools.
Security intelligence for AI agents. 27 x402 endpoints: honeypot, forensics, CAPTCHA, preflight.
Uptime history
29 days of history · worst day 0%
29 days agonow
0.0%
Uptime 24h
0 of 91 checks
11
Tools
read from the server
19 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 46
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 26 August 2026. No other catalogue keeps this.
26 Aug
12 tools appeared
captcha.solve, security.address, security.approval and 9 more
26 Aug
11 tools changed the parameters they ask for12 times that day
address_risk, agent_preflight, approval_risk and 8 more
26 Aug
10 tool descriptions were rewritten11 times that day
address_risk, agent_preflight, approval_risk and 7 more
26 Aug
10 tools disappeared
address_risk, agent_preflight, approval_risk and 7 more
26 Aug
a tool changed version
and 2 more, back to 26 August 2026
Freysa Security does not always answer
Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.
run in your terminal
claude mcp add freysa-intelligence --transport http https://economic-agent-369.freysa.dev/mcp~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"freysa-intelligence": {
"url": "https://economic-agent-369.freysa.dev/mcp"
}
}
}~/.codex/config.toml
[mcp_servers.freysa-intelligence]
url = "https://economic-agent-369.freysa.dev/mcp".cursor/mcp.json
{
"mcpServers": {
"freysa-intelligence": {
"url": "https://economic-agent-369.freysa.dev/mcp"
}
}
}.vscode/mcp.json
{
"mcpServers": {
"freysa-intelligence": {
"url": "https://economic-agent-369.freysa.dev/mcp"
}
}
}Available tools 11
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
security
security.address
Check if a wallet address is safe. Returns scam indicators risk score 0 to 100 and recommendation. Checks sanction lists phishing links and suspicious patterns. Used by trading agents before sending funds.
security.approval
Check if a token approval is safe. Detects dangerous spenders unlimited allowance risks and malicious patterns. Every output cites block evidence. Use before signing any approve transaction.
security.buy_decision
BUY_AVOID_CAUTION decision for any token. Combines honeypot check contract risk liquidity analysis and holder concentration. Returns structured decision with confidence score and evidence.
security.contract
Smart contract risk assessment. Checks if verified upgradeable has dangerous functions proxy patterns owner privileges and known exploit vectors. Deterministic on-chain analysis no LLM hallucination.
security.honeypot
Check if a token is a honeypot using real eth_call sell simulation. Detects if you can actually sell the token. Returns sell restrictions buy_sell tax blacklist status and evidence with block number. Deterministic no AI hallucination.
security.pre_trade
Full pre-trade risk check. Checks token contract wallet liquidity slippage and price impact in one call. Includes amount-based impact calculation. For agents that need to know if a trade is safe.
security.preflight
One-call comprehensive safety check for AI agents. Checks target contract token and wallet together. Returns PROCEED_CAUTION_ABORT decision with evidence. Designed for autonomous agents executing complex workflows. Most thorough analysis at $0.50.
security.score
Quick token security score 0-100. Returns SAFE_CAUTION_DANGER decision plus risk flags. Fastest decision at $0.01. For agents that need one number before trading.
security.trial
Free trial - 3 security/reasoning calls per day. No payment needed. Try security_score, honeypot_check, or address_risk.
security.wallet
Deep wallet forensic audit. Traces on-chain history flags suspicious patterns identifies scam links MEV activity and money flow patterns. Returns structured risk score with evidence chain. For security agents doing due diligence.
captcha
captcha.solve
Solve CAPTCHA challenges. Supports image CAPTCHAs, reCAPTCHA v2, and Turnstile. Submit base64 image or image URL. Returns solved text in seconds. 99% accuracy. Power your web automation agents with CAPTCHA bypass. $0.01 per solve.
Tools removed
Tools this server used to expose. Anything built against them stopped working on the day they went.
address_risk
removed 26 Aug 2026
agent_preflight
removed 26 Aug 2026
approval_risk
removed 26 Aug 2026
contract_risk
removed 26 Aug 2026
free_trial
removed 26 Aug 2026
honeypot_check
removed 26 Aug 2026
pre_trade_risk
removed 26 Aug 2026
security_score
removed 26 Aug 2026
should_i_buy
removed 26 Aug 2026
wallet_forensics
removed 26 Aug 2026
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://economic-agent-369.freysa.dev/mcp | streamable-http | answering | 19 ms | 4 min ago |
Alternatives to Freysa Security
same job, measured the same way
N
Think MCP
by agentutil
Intent security pre-flight checks for autonomous AI agents.
Signal Oracle
by neruoticfarrow
Pay-per-call change-intelligence feeds for AI agents over x402 (deps, security, regs, tariffs)
Feedmyagent
by makash
Technology intelligence feed for AI agents: tech stack, compliance, security.
Proofpoint
by wyre-technology
MCP server for Proofpoint TAP — threat intelligence, forensics, quarantine, and email security.
Proofpoint
by wyre-ai
MCP server for Proofpoint TAP — threat intelligence, forensics, quarantine, and email security.
Domain Intel
by erikirby
Website intelligence for AI agents: tech stack, hosting, security posture, SEO, and DNS.
BentCrypto Machine Payments
by ghstaking
Paid token risk and security intelligence for AI agents over MCP with x402 payments.
ArchGraph
by archgraph
Code intelligence platform for AI agents. 20 tools for architecture, security & impact analysis.
Freysa Security — questions
Answers built from our own checks of this server.
What can Freysa Security do?
It exposes 11 tools, read directly from the server on our last check. Among them: captcha.solve, security.address, security.approval, security.buy_decision, security.contract, security.honeypot and 5 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is Freysa Security working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 19 ms. The bar chart above shows every period we have measured.
Did Freysa Security ever remove tools?
Yes. address_risk, agent_preflight, approval_risk, contract_risk and 6 more are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
The registry lists Freysa Security as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect Freysa Security?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Freysa Security need an API key?
No. Freysa Security completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 11 of them are readable on this page. This is what we observed, not what the docs claim.