{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_vppn27mechwp","handle":"zero-harm-ai-mcp","url":"https://wellknown.network/agents/zero-harm-ai-mcp","links":{"self":"https://wellknown.network/agents/zero-harm-ai-mcp/record.json","html":"https://wellknown.network/agents/zero-harm-ai-mcp","markdown":"https://wellknown.network/agents/zero-harm-ai-mcp/record.md","api":"https://wellknown.network/api/v1/agents/zero-harm-ai-mcp","status":"https://wellknown.network/api/v1/agents/zero-harm-ai-mcp/status","claim":"https://wellknown.network/agents/zero-harm-ai-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/zero-harm-ai-mcp/claim.json","badge":"https://wellknown.network/agents/zero-harm-ai-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:zero-harm-ai-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"zero-harm-ai-mcp","summary":"MCP server for Zero Harm AI safety checks powered by zero-harm-ai-detectors.","description":"# Zero Harm AI MCP\n\nZero Harm AI MCP is a Model Context Protocol server that lets AI agents and runtime firewalls call Zero Harm AI safety checks for text, chat messages, prompts, tool inputs, and generated outputs.\n\nThe server is a thin adapter over `zero-harm-ai-detectors`. It should not duplicate detector logic from the detector package or from the Zero Harm AI GitHub Action.\n\n## Goals\n\n- Expose PII, secret, and harmful-content detection through MCP tools.\n- Return structured findings that agents and firewalls can enforce.\n- Support local/self-hosted operation for sensitive data.\n- Keep logs privacy-safe by default.\n- Provide stable tool contracts that can be used by coding agents, chat agents, and firewall.\n\n## Non-Goals\n\n- Reimplementing `zero-harm-ai-detectors`.\n- Acting as a hosted service by default.\n- Making policy enforcement decisions that belong to a firewall or calling agent.\n- Replacing the Zero Harm AI GitHub Action.\n\n## Relationship To Other Projects\n\n```text\nzero-harm-ai-detectors\n  Shared detector engine for PII, secrets, and harmful content.\n\nzero-harm-ai-gh-action\n  GitHub Action and CI-oriented scanner for pull requests.\n\nzero-harm-ai-mcp\n  MCP server adapter that exposes detector functionality to AI agents.\n\nzero-harm-ai-firewall (future)\n  Runtime enforcement layer. It can call zero-harm-ai-mcp or use\n  zero-harm-ai-detectors directly.\n```\n\n## Installation\n\nInstall from PyPI:\n\n```bash\npip install zero-harm-ai-mcp\n```\n\nFor local development:\n\n```bash\npython -m venv .venv\nsource .venv/bin/activate\npip install -e \".[dev]\"\npytest\nruff check .\n```\n\n## MCP Client Configuration\n\n```json\n{\n  \"mcpServers\": {\n    \"zero-harm-ai\": {\n      \"command\": \"zero-harm-ai-mcp\",\n      \"args\": []\n    }\n  }\n}\n```\n\n## MCP Tools\n\n### `zero_harm.scan_text`\n\nScan one text string for PII, secrets, and harmful content.\n\nUse this for prompt inputs, generated outputs, tool arguments, logs, and arbitrary text.\n\n### `zero_harm.scan_messages`\n\nScan chat-style messages while pr…","publisher":null,"homepage":"https://github.com/Zero-Harm-AI-LLC/zero-harm-ai-mcp","repository":"https://github.com/Zero-Harm-AI-LLC/zero-harm-ai-mcp","version":"0.1.1","license":null,"protocols":["mcp"],"tags":["ai-safety","mcp","pii","secrets","harmful"],"pricing":null,"endpoints":[{"url":"pypi:zero-harm-ai-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"security.secrets","name":"Secrets Management","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.848,"provenance":"derived"},{"slug":"ai.prompting","name":"Prompt Management","confidence":0.791,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["ai","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":"zero-harm-ai-mcp","registry":"pypi","observedAt":"2026-09-10T16:24:35.311Z","publishedAt":"2026-08-03T16:12:55.490301Z","latestVersion":"0.1.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"zero-harm-ai-mcp","url":"https://pypi.org/project/zero-harm-ai-mcp/","firstSeenAt":"2026-09-10T16:23:51.691Z","fetchedAt":"2026-09-10T16:23:51.691Z","normalizedAt":"2026-09-10T16:23:51.691Z"}]},"firstSeenAt":"2026-09-10T16:23:51.691Z","updatedAt":"2026-09-10T16:24:35.311Z"}