# Mcp MCP server

Agent View of the PolicyLayer registry record for Mcp: identity, probed posture, risk grade, and all 5 tools classified. HTML page: https://policylayer.com/tools/ai-clarx-mcp

## Facts

- Server id: `@clarxai/mcp`
- Install: `npx -y @clarxai/mcp`
- Homepage: https://github.com/Gernika-Labs/clarx-cloud
- Registry record: grade C, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 5 (5 with introspected schema)
- Tool categories present: Read, Write
- Tags: ai clarx mcp
- Record last modified: 2026-07-09T08:38:21.634Z

## Tools (5)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `analyze_clarx_manifest` | Read | Low | https://policylayer.com/tools/ai-clarx-mcp/analyze-clarx-manifest.md |
| `analyze_manifest` | Read | Low | https://policylayer.com/tools/ai-clarx-mcp/analyze-manifest.md |
| `generate_manifest_draft` | Write | Medium | https://policylayer.com/tools/ai-clarx-mcp/generate-manifest-draft.md |
| `get_ci_workflow` | Write | Medium | https://policylayer.com/tools/ai-clarx-mcp/get-ci-workflow.md |
| `suggest_manifest_fix` | Write | Medium | https://policylayer.com/tools/ai-clarx-mcp/suggest-manifest-fix.md |

## Tool descriptions

- `analyze_clarx_manifest` — Validate a clarx-manifest.json machine manifest against the Clarx engine schema. Returns recognized keys, errors, and suggestions for keys worth declaring (generated dirs, hubs, verification commands).
- `analyze_manifest` — Score CLAUDE.md / AGENTS.md manifest content with the same rules as the Clarx manifest studio. Returns an overall quality estimate (0-100), per-pillar scores, findings with line numbers, and a section checklist. This is a manifest qualit…
- `generate_manifest_draft` — Generate a first-draft agent manifest (CLAUDE.md / AGENTS.md / GEMINI.md) grounded in the repository README and description. Uses your ANTHROPIC_API_KEY. Claims the model cannot ground are marked as TODO comments.
- `get_ci_workflow` — Generate a GitHub Actions workflow YAML that gates pull requests on the Clarx AI-readiness score (npx @clarxai/cli). Write the result to .github/workflows/clarx.yml.
- `suggest_manifest_fix` — Write one well-formed markdown section of an agent manifest (CLAUDE.md / AGENTS.md) to close a finding from analyze_manifest. Uses your ANTHROPIC_API_KEY. Returns the section markdown to insert.

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=ai-clarx-mcp · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/ai-clarx-mcp