{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_nkdx3qna3kwj","handle":"securitystack-mcp","url":"https://wellknown.network/agents/securitystack-mcp","links":{"self":"https://wellknown.network/agents/securitystack-mcp/record.json","html":"https://wellknown.network/agents/securitystack-mcp","markdown":"https://wellknown.network/agents/securitystack-mcp/record.md","api":"https://wellknown.network/api/v1/agents/securitystack-mcp","status":"https://wellknown.network/api/v1/agents/securitystack-mcp/status","claim":"https://wellknown.network/agents/securitystack-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/securitystack-mcp/claim.json","badge":"https://wellknown.network/agents/securitystack-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/securitystack-mcp/history","tools":"https://wellknown.network/api/v1/agents/securitystack-mcp/tools"},"ard":{"identifier":"urn:air::server:securitystack-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"securitystack-mcp","summary":"Unified MCP server — give your AI agent the ability to secure its own environment.","description":"# SecurityStack MCP \n \n> Give your AI agent the ability to secure its own environment — one MCP config, six tools. \n> \n> Audit MCP configs for poisoning, redact secrets/PII before they leave for an LLM, vet untrusted \n> skills, monitor dependency health, and actively scan your network. All from a single `securitystack` \n> entry in your agent's MCP config. \n \nThis is the **client**: the unified MCP server an AI agent (Claude CLI/Desktop, or any MCP-aware \nagent) installs to call the SecurityStack hosted services. The backend services themselves are hosted \n— you don't run them. You configure API keys and your agent gets six security tools. \n \n## Why \n \nAn AI agent has four ways to get compromised. SecurityStack covers all four: \n \n``` \n1. What it INSTALLS   → poisoned skills / MCP configs     → scan_skill + audit_mcp_server_config \n2. What it DEPENDS ON → a dependency goes down/rogue        → check_dependencies \n3. Where it's EXPOSED → open ports, default creds           → network_scan (with AI agent loop) \n4. What it SENDS OUT  → secrets/PII leak into the LLM       → scan_secrets \n``` \n \nTwo of these — `audit_mcp_server_config` and `scan_secrets` — run **offline, in-process, with no API \nkey**. They work the moment you install the server. The other four call hosted services (configure \ntheir keys to enable them; each is skipped gracefully if unset). \n \n## Install \n \n### 1. Install the server \n \n```bash \n# From source (clone this repo, then install): \ngit clone https://github.com/<your-org>/securitystack-mcp.git \ncd securitystack-mcp \npip install . \n``` \n \n*(A `pip install securitystack-mcp` from PyPI will be available once published. \nUntil then, install from source as above.)* \n \n### 2. Add it to your agent \n \nFor **Claude Desktop / CLI** (`claude_desktop_config.json` or `~/.claude.json`): \n \n```json \n{ \n  \"mcpServers\": { \n    \"securitystack\": { \n      \"command\": \"python\", \n      \"args\": [\"-m\", \"stack.unified_mcp_server\"], \n      \"env\": { \n        \"ACTIVESCANNER_A…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:securitystack-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.825,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev"],"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":"securitystack-mcp","registry":"pypi","observedAt":"2026-11-04T00:27:27.064Z","publishedAt":"2026-08-22T17:13:24.967632Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"securitystack-mcp","url":"https://pypi.org/project/securitystack-mcp/","firstSeenAt":"2026-09-10T12:21:19.613Z","fetchedAt":"2026-11-04T00:26:00.155Z","normalizedAt":"2026-11-04T00:26:00.155Z"}]},"firstSeenAt":"2026-09-10T12:21:19.613Z","updatedAt":"2026-11-04T00:27:27.064Z"}