17 security tools an agent can call, scored
As of 2026-10-27, 17 listings meet this rule: every listing in the Security Tool category, ordered by Sato Score; highest Sato Scores: PulseFeed, Agent Skills Hub and Self Protocol.
- Listings17
- Updated2026-10-27
The rule behind this listShowHide
Rule. Every listing in the Security Tool category, ordered by Sato Score; rebuilt daily.
The Sato Score is a 0–100 measure of how open, active and verifiable a project is; not a safety, quality or returns grade. No winner is declared; the order is the score.
| # | Listing | Sato Score | Liveness | Chains |
|---|---|---|---|---|
| 1 | PulseFeed✓ probed PulseFeed checks an x402 endpoint before an agent pays it (liveness, a 0-100 score, receiver and price flags) and tracks changes to MCP servers and npm packages. Ships a guard SDK, an MCP server, and Vercel AI SDK and LangChain tools. Security Tool · ★ 0 | High | Active · 6d ago | Base |
| 2 | Agent Skills Hub✓ reproduced A registry of AI agent skills that applies automated source-code scanning and assigns security grades before installation. Security Tool · ★ 119 | High | Active · 25d ago | — |
| 3 | Self Protocol✓ reproduced Open-source zero-knowledge identity protocol (passport-based proof of personhood) used to gate agent access to onchain services. Security Tool · ★ 1,260 | High | Active · 4d ago | Multichain |
| 4 | GoPlus AgentGuard✓ reproduced MIT-licensed runtime guard for AI coding agents: hook-level action blocking, a 24-rule skill scanner, and a per-skill trust registry. Security Tool · ★ 470 | High | Active · 8d ago | — |
| 5 | Socket✓ probed Dependency and package analysis from Socket, with a CLI and an MCP server that returns package scores to an AI assistant. Security Tool · ★ 334 | High | Active · today | — |
| 6 | MistTrack MCP✓ reproduced MCP server from SlowMist exposing MistTrack address risk scoring and fund-flow tracing to AI agents. Security Tool · ★ 39 | High | Quiet · 6mo ago | Ethereum, Bitcoin, Polygon, Solana, Multichain |
| 7 | Usenami Signer MCP✓ reproduced MCP server that signs CEX/DEX orders inside an attested AWS Nitro Enclave so keys never touch the agent process. Security Tool · ★ 2 | Medium | Active · 26d ago | — |
| 8 | Privacy infrastructure that gives MCP-compatible agents private wallets, encrypted messaging, and confidential smart contracts using Garbled Circuits. Security Tool · ★ 14 | Medium | Active · 2d ago | COTI, Ethereum |
| 9 | PRXVT✓ reproduced Open-source privacy SDK that adds unlinkable, zero-knowledge payments on top of the x402 agent payment standard. Security Tool | Medium | no signal | Ethereum, Base, Polygon |
| 10 | Pre-built MCP blockchain capability modules giving agents fraud detection, AML scoring, wallet profiling, and token analysis. Security Tool · ★ 10 | Medium | Recent · 3mo ago | Polygon, Ethereum, BNB Chain, Base, TON, Tron, Solana |
| 11 | Intercepts agent transactions and checks them against 5 security oracles before execution. Security Tool · ★ 9 | Medium | Active · 2d ago | Multichain |
| 12 | Agent-identity authentication protocol modeled on Sign-In-With-Ethereum, letting services verify an agent before granting access. Security Tool · ★ 43 | Medium | Quiet · 6mo ago | Ethereum |
| 13 | Keyless REST APIs for token risk, approval risk, malicious addresses, signature decoding and transaction simulation across 46 chains. Security Tool | Medium | no signal | Multichain |
| 14 | Keyed risk APIs for address, contract and transaction screening, including sanction checks, across 13 documented networks. Security Tool | Low | no signal | Multichain |
| 15 | Keyless API that simulates a buy and sell of an EVM token and reports the observed taxes, gas and honeypot result. Security Tool | Low | no signal | Ethereum, BNB Chain, Base |
| 16 | Public Solana token-report API: mint and freeze authority, metadata mutability, LP lockers and insider graphs, with a published OpenAPI document. Security Tool | Low | no signal | Solana |
| 17 | Pay-per-use security verification endpoints for AI agents, billed via x402 micropayments. Security Tool | Low | no signal | Base, Ethereum, Solana |
✓ marks an earned state — reviewed against evidence, install reproduced, on-chain identity read from the chain, or endpoint probed — named as what was checked. None of them is a safety claim.
Related
Other scored lists
- 17 trading agent frameworks, scored
- 82 onchain trading tools on Base, scored
- 66 x402 payment tools on Base, scored
- 41 Solana MCP servers, scored
- 56 Base MCP servers, scored
- 40 Ethereum MCP servers, scored
- 90 x402-ready tools, scored
- 17 ERC-8004 tools, scored
- 31 agent frameworks, scored
- 35 wallets for agents, scored
- 69 MCP servers with a verified install, scored
- 50 onchain trading tools on Solana, scored
- 50 npm-installable crypto agent tools, scored
- 46 Python-installable crypto agent tools, scored
- 18 wallets for agents on Solana, scored
- 37 x402 payment tools on Solana, scored
- 40 payment tools for agents, scored
- 25 highest Sato Scores in the directory
- 52 hosted MCP endpoints answering today, scored
- 7 Solana MCP servers you can use without a local server
- 15 Base MCP servers you can use without a local server
- 5 Ethereum MCP servers you can use without a local server
- What 87 crypto MCP servers do with your keys: dated Sato Check readings
- 9 onchain agent frameworks with recent commits or releases
Reference
QuestionsWhat people ask about this pageShowHide
Questions this list answers
- Which security tools can an AI agent call?
- As of 2026-10-27, 17 listings meet this rule: every listing in the Security Tool category, ordered by Sato Score; highest Sato Scores: PulseFeed, Agent Skills Hub and Self Protocol.
- Which of these are open source?
- 8 of 17: PulseFeed, Self Protocol, GoPlus AgentGuard, MistTrack MCP, Usenami Signer MCP, PRXVT, CryptoGuard, SIWA (Sign In With Agent).
- Which are actively maintained?
- 8 had a commit or release in the last 30 days: PulseFeed, Agent Skills Hub, Self Protocol, GoPlus AgentGuard, Socket, Usenami Signer MCP, COTI, CryptoGuard. Posts on X do not count. Activity is a recency signal, not a quality judgment.
- Which have an earned verification on Sato Hub?
- 8: PulseFeed, Agent Skills Hub, Self Protocol, GoPlus AgentGuard, Socket, MistTrack MCP, Usenami Signer MCP, PRXVT. An earned check is named as what was checked (install reproduced, endpoint probed, on-chain identity read, reviewed against evidence); none is a safety claim.
- Which run as MCP servers?
- 4: Agent Skills Hub, Socket, COTI, ChainAware.
- How is this list ranked?
- 17 security tools an agent can call is derived from Sato Hub's live records by a stated rule and ordered by Sato Score, a 0–100 measure of how open, active and verifiable each project is. It is not a quality ranking and declares no winner.
SourcesWhere the data comes fromShowHide
Sources — the projects' own repositories and docs
Cite this pagePlain text, APA or BibTeXShowHide
Cite this page
Sato Hub. "17 security tools an agent can call, scored." Sato Hub, updated 2026-10-27, accessed 2026-10-27. https://satohub.ai/lists/security-tools-for-agentsData last refreshed 2026-10-27; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.