{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_96avaqn47x25","handle":"mcp-security-toolkit","url":"https://wellknown.network/agents/mcp-security-toolkit","links":{"self":"https://wellknown.network/agents/mcp-security-toolkit/record.json","html":"https://wellknown.network/agents/mcp-security-toolkit","markdown":"https://wellknown.network/agents/mcp-security-toolkit/record.md","api":"https://wellknown.network/api/v1/agents/mcp-security-toolkit","status":"https://wellknown.network/api/v1/agents/mcp-security-toolkit/status","claim":"https://wellknown.network/agents/mcp-security-toolkit/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-security-toolkit/claim.json","badge":"https://wellknown.network/agents/mcp-security-toolkit/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-security-toolkit/history","tools":"https://wellknown.network/api/v1/agents/mcp-security-toolkit/tools"},"ard":{"identifier":"urn:air::server:mcp-security-toolkit","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-security-toolkit","summary":"Atomic MCP tools for AppSec and AI Security engineers","description":"# mcp-security-toolkit\n\n[![CI](https://github.com/x0base/mcp-security-toolkit/actions/workflows/ci.yml/badge.svg)](https://github.com/x0base/mcp-security-toolkit/actions/workflows/ci.yml)\n[![PyPI](https://img.shields.io/pypi/v/mcp-security-toolkit.svg)](https://pypi.org/project/mcp-security-toolkit/)\n[![Python](https://img.shields.io/pypi/pyversions/mcp-security-toolkit.svg)](https://pypi.org/project/mcp-security-toolkit/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\n> Built by [Redmai](https://redmai.io). For continuous autonomous API / agent\n> security scanning, use Redmai.\n\n**Source / schema / prompt audit primitives for agent builders.**\n\nPlug into Claude Code / Cursor / Claude Desktop. Audit MCP servers, agent\ntool schemas, system prompts, JWTs, and HTTP-response diffs — locally,\nin the coding agent you already use. Atomic, auditable, no orchestration.\n\n## Why this exists\n\nMost security-flavored MCP servers wrap an existing CLI (Burp, Shodan,\nCyberChef) or audit MCP configurations and tool descriptions. The primitives\na developer reaches for when *their own* code ships an LLM feature —\nsource-level audit of an MCP server, schema-level audit of an agent tool,\nstatic review of a system prompt — are thinly covered.\n\n`mcp-security-toolkit` ships those primitives, plus the everyday pentest\natoms an agent reaches for during AppSec work, so you can run one server\ninstead of five.\n\n---\n\n## Headline tools\n\n### `mcp_server_audit`\nHeuristic AST audit of an MCP server's Python source. Enumerates\n`@tool`-decorated and imperatively-registered tools, then runs 13 detectors:\n\n| Detector | Category | Sev |\n|---|---|---|\n| Shell execution | `shell-exec` | high |\n| Filesystem write/delete | `fs-write` / `fs-destructive` | med–high |\n| Network egress | `network-egress` | medium |\n| Code injection | `code-injection` | high |\n| Over-broad params | `over-broad-param` | medium |\n| Ambiguous/missing docstring | `ambiguous-description` | low–med |\n| Se…","publisher":{"name":"x0base","url":null},"homepage":"https://github.com/x0base/mcp-security-toolkit","repository":"https://github.com/x0base/mcp-security-toolkit","version":"0.3.1","license":"MIT","protocols":["mcp"],"tags":["ai-security","appsec","llm","mcp","red-team","security"],"pricing":null,"endpoints":[{"url":"pypi:mcp-security-toolkit","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.filesystem","name":"Filesystem","confidence":0.882,"provenance":"derived"},{"slug":"security.scanning","name":"Security Scanning","confidence":0.859,"provenance":"derived"}],"categories":["dev","security"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"mcp-security-toolkit","registry":"pypi","observedAt":"2026-11-03T15:23:10.227Z","publishedAt":"2026-05-17T14:26:31.233376Z","latestVersion":"0.3.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-security-toolkit","url":"https://pypi.org/project/mcp-security-toolkit/","firstSeenAt":"2026-09-10T03:19:41.159Z","fetchedAt":"2026-11-03T15:21:36.158Z","normalizedAt":"2026-11-03T15:21:36.158Z"}]},"firstSeenAt":"2026-09-10T03:19:41.159Z","updatedAt":"2026-11-03T15:23:10.227Z"}