What is the endpoint for Policylayer MCP Registry?
The endpoint is `https://api.policylayer.com/mcp` (Streamable HTTP).
@PolicyLayer
基本信息
The MCP server that vets MCP servers. Connect your agent to the PolicyLayer registry and check any MCP server's identity, risk grade, auth posture and tool classifications before installing it. Free single-server lookups over 32,500+ published servers and 515,000+ classified tool
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"policylayer": {
"url": "https://api.policylayer.com/mcp"
}
}
}Check an MCP server against the PolicyLayer registry BEFORE installing or allowing it. Accepts a registry slug, an npm package name (scoped or not), a remote server URL (https://…), or a server name. Returns the full published record: identity verification with its evidence, risk grade, auth posture, freshness, and the tool surface listed riskiest-first. A server the registry does not know is queued for scanning by this very call — check back shortly.
Check a whole MCP stack against the PolicyLayer registry in one call — up to 25 servers, each given as candidate identifiers (npm package name, registry slug, or remote URL) tried in order until one resolves. Returns the published record for every hit — plus a deterministic verdict (attention signals and a suggested action) — and the lookup status for every miss; counts, grades and flagged tools come from the published records only. Costs one rate-limit unit per server.
Search the PolicyLayer registry of published MCP servers by name, slug or package substring. Returns candidate matches with risk grade, identity confidence (verified / unverified / mismatch — mismatch means it claims to be an official server with no verifiable link to the brand) and tool count — follow up with check_mcp_server on the match you meant.
One tool's full risk classification on a published MCP server: category, severity, risk analysis and evidence, OWASP classes, parameter schema and the recommended policy default. Use when deciding whether to allow a specific tool call, e.g. "should execute_sql on this server be permitted?"
The registry change feed: tool-surface drift, auth-posture flips, impostor flags, version bumps — every event the freshness watchers emit, id-cursored so a consumer resumes exactly where it stopped. Requires a Registry Licence key (Authorization: Bearer plr_...); self-serve at https://policylayer.com/registry/pricing.
Policylayer MCP Registry is a hosted MCP server that vets any MCP server by returning its published safety record: verified identity, A–F risk grade, auth posture, and a risk classification for every tool. It covers 32,500+ published servers and 515,000+ classified tools via continuous scanning.
Connect your agent to the streamable HTTP endpoint (https://api.policylayer.com/mcp) using Claude Code (claude mcp add --transport http policylayer https://api.policylayer.com/mcp) or configure it in Claude Desktop, Cursor, Windsurf, or VS Code as a custom MCP connector. Then instruct your agent to check any server against PolicyLayer before installing. Free single-server lookups require no key.
get_change_events feed (with licence) reports drifts, posture flips, and impostor flagsThe endpoint is `https://api.policylayer.com/mcp` (Streamable HTTP).
No. All single-server lookups (via `check_mcp_server`, `search_registry`, `check_tool`) are free and require no key. A Registry Licence key is needed only for the `get_change_events` tool.
The registry includes 32,500+ published servers and 515,000+ classified tools, kept current by continuous scanning.
For Claude Code, append `--header "Authorization: Bearer plr_..."` to the add command. For Cursor/Windsurf/VS Code, add `"headers": { "Authorization": "Bearer plr_..." }` inside the server entry. Claude desktop/web connectors cannot send headers, so only free lookups are available.
Four tools: `check_mcp_server` (full record for one server), `search_registry` (search servers by name), `check_tool` (classification for one tool), and `get_change_events` (change feed, needs licence). The first three are free.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
Open-source Node.js FHIR MCP server with SMART Backend Services, metadata-aware search/CRUD tools, compact responses, FHIRPath filtering, safe pagination, audit events, and terminology lookup.

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
MCP server for x402-list.com: discover x402 payment services and on-chain-verified facilitator settlement volumes. Published on npm as x402-list-mcp.
Dreamwork MCP server: job search, tailored application materials, and application tracking for AI assistants.
评论