Pins MCP tool definitions at approval and blocks the session when they change
Runs locally- Open source
- Security
Pins MCP tool definitions at approval and blocks the session when they change
Runs locallyCollect API keys in a browser page and write them to .env without the model seeing them
Runs locally
Wraps any MCP server so repeated write calls run once and every call is logged
Runs locallySecrets manager MCP server that runs commands with API keys the model never sees
Runs locally
Free read-only agent-readiness, TLS, DNS and MCP checks over a remote server
Not checked yetLook up WHOIS, RDAP, DNS, IP, ASN and ENS, Handshake and other Web3 names with no key
Not checked yetStructural code-quality scoring for coding agents, from SLOP to PLATINUM, run locally
Runs locallyOpen-source order limits, phone approval and a kill switch for trading AI agents
Runs locallyGive a coding agent the dependency graph: scan, explain and diff packages
Runs locally
Read-only access to desk notes on US sanctions and cyber records, with official sources
Not checked yetSourced comparison of BitBox, Ledger and Trezor hardware wallets, plus a buying checklist
Not checked yetPublic MCP server to timestamp SHA-256 hashes, verify codes and read Argentine news
Not checked yetRemote MCP server giving defender agents ledger reads and findings on a coding-agent fleet
Not checked yetQuery internet censorship evidence, plus an encrypted agent relay with guarded writes
Runs locallyFree read-only lookup of Swedish building inspection duties and due dates
Not checked yetSearch, read and cite essays on application security, identity and agent identity
Not checked yetAuthorization proxy that needs a rule check and AI judges to approve each tool call
Runs locallyManaged IT firm's MCP server with downtime and cyber insurance calculators and a site scan
Not checked yetFree signed check of an x402 paid endpoint, run by an agent before it pays
Not checked yetTrust checks that return ok, careful or stop for a wallet or bot before an agent pays
Not checked yet
Lint Dockerfiles for root users, latest tags, secrets in ENV or ARG and more
Runs locally
Decode JWTs without trusting them, flag risky claims, verify signatures, mint test tokens
Runs locally
Look up known vulnerabilities in OSV.dev by package and version, and scan lockfiles
Runs locally
Grades a site's security headers and explains each one, over stdio
Runs locallyCheck a domain's SPF, DKIM, DMARC, DNS, SSL and subdomains from public data
Not checked yetRules for each agent tool call, then a check of what a database really changed
Runs locallyFree check of a domain's SPF, DKIM, DMARC, MX and blocklists to explain why mail hits spam
Not checked yetRead-only feed of community-voted security findings about tools that AI agents use
Runs locallyRank open-source packages on maintenance signals so assistants stop guessing
Not checked yet
Self-hosted gateway that lets AI agents use your accounts, with writes held for approval
Not checked yetSee every kind of AI for security: tools, agents, MCP servers and skills.Ranked: the best AI for security.