io.github.NellInc/saferagenticai-mcp

up checked 2026-11-11T10:37:32.642Z

Unclaimed · Unverified

Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.

Publisher-provided description

Read-only tools over the Safer Agentic AI framework: 239 patterns + 15 heuristics.

Summary by lookupd

Read-only lookup of AI agent safety patterns, heuristics, and requirements for finding guidance matching a task, with cross-reference…

Install

Claude Code, remote (streamable-http)

claude mcp add --transport http saferagenticai https://mcp.saferagenticai.org/mcp

Claude Code, pypi package (stdio)

claude mcp add saferagenticai -- uvx saferagenticai-mcp

Codex, remote (streamable-http)

codex mcp add saferagenticai --url https://mcp.saferagenticai.org/mcp

Codex, pypi package (stdio)

codex mcp add saferagenticai -- uvx saferagenticai-mcp

Cursor, remote (streamable-http) → .cursor/mcp.json

{
  "mcpServers": {
    "saferagenticai": {
      "url": "https://mcp.saferagenticai.org/mcp"
    }
  }
}

Cursor, pypi package (stdio) → .cursor/mcp.json

{
  "mcpServers": {
    "saferagenticai": {
      "command": "uvx",
      "args": [
        "saferagenticai-mcp"
      ]
    }
  }
}

Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.

Tools (10 tools)

Publisher-provided text

list_suites List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient.
get_requirement Retrieve one subgoal (framework normative content + Pattern layer guidance) by pattern_id (e.g., 'D3::idx2::sandboxing') or display_id (e.g., 'D3.2'). display_i
list_requirements List subgoals matching filters (suite_id, suite_type, content_type, min_confidence, missing_pattern_only). Results capped by limit (default 50, max 100). Every
search_patterns Field-weighted keyword search across the framework. Terms match at word starts on lowercased text and are IDF-weighted, so rare terms outrank ubiquitous ones; f
get_cross_references Return outgoing adjacencies for a pattern. `explicit_cross_references` are author-asserted (each pattern's `cross_references` YAML field). `inferred_adjacent` (
resolve_id Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Case, separator and G/I prefix are normalised (d
find_patterns_for_task Given a natural-language task description (e.g., 'I'm building a tool-using agent that runs shell commands'), return the most relevant patterns grouped by suite
get_reverse_references Return patterns that reference the given pattern_id in their cross_references. Complement to get_cross_references (outgoing); this shows incoming. Use to find a
list_operational_heuristics List operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind). These are cross-cutting safety principles discovered through
get_operational_heuristic Retrieve a single operational heuristic by id (e.g., 'OH::geoffrey-pattern'). Returns the full entry: principle, framework mapping, evidence sources from produc

Details

Version: 0.4.2
Transports: streamable-http, stdio
Uptime (7 days): 100%
Median latency: 766 ms
First indexed: 2026-11-01T09:12:46.109Z
Last seen in registry: 2026-11-06T03:17:08.983Z
Repository: https://github.com/NellInc/saferagenticai-mcp

Badge for your README

Shows this live status and links here; updates hourly.

[![lookupd status](https://lookupd.com/badge/io.github.NellInc/saferagenticai-mcp.svg)](https://lookupd.com/servers/io.github.NellInc/saferagenticai-mcp)

62092 servers
Last crawl: 2026-11-11T17:38:11.606Z
API base: https://api.lookupd.com
MCP URL: https://api.lookupd.com/mcp