# saferagenticai-mcp MCP server

Read-only tools over the Safer Agentic AI framework: 238 patterns + 14 heuristics.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-nellinc-saferagenticai-mcp
- Repository: https://github.com/NellInc/saferagenticai-mcp

## Install
- Command: `uvx saferagenticai-mcp`
- Endpoint: https://mcp.saferagenticai.org/mcp
- Auth: Not captured

## Setup notes
- Package: Pypi saferagenticai-mcp v0.3.3
- Remote endpoint: https://mcp.saferagenticai.org/mcp

## Tools
- list_suites - List all 16 suites in the SaferAgenticAI framework (9 drivers + 7 inhibitors) with subgoal counts and titles. Call this first to orient. Endpoint: https://mcp.saferagenticai.org/mcp
- 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_id may resolve to multiple subgoals — underlined variants share display_ids. Endpoint: https://mcp.saferagenticai.org/mcp
- 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). Endpoint: https://mcp.saferagenticai.org/mcp
- search_patterns - Field-weighted keyword search across the framework. Substring match on lowercased terms; field weights: title 10x, summary 4x, SFR text 3x, description 2x, pattern body 1x. `matched_in` reports the highest-weighted field that matched. No semantic / embedding search — known limitation, see /mcp.html. Use verbosity='compact' to drop snippets and confidence flags (~70% smaller payload) when triaging. Endpoint: https://mcp.saferagenticai.org/mcp
- get_cross_references - Return outgoing adjacencies for a pattern. `explicit_cross_references` are author-asserted (each pattern's `cross_references` YAML field). `inferred_adjacent` (when include_inferred=true) currently returns *same-suite siblings only* — it does not do semantic similarity. Treat inferred entries as 'neighbours worth scanning,' not as endorsed dependencies. Endpoint: https://mcp.saferagenticai.org/mcp
- resolve_id - Resolve a loose reference (partial id, display_id, slug fragment, or title keyword) to canonical pattern_id(s). Call this when you have a rough reference and need the exact id before calling get_requirement. Always returns candidates — never 'not found'. Endpoint: https://mcp.saferagenticai.org/mcp
- 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. Use this as a starting point for any cross-cutting design question; then follow up with get_requirement on specific pattern_ids. Defaults to verbosity='compact' (cheap triage); pass 'full' to inline snippets and confidence flags. Endpoint: https://mcp.saferagenticai.org/mcp
- list_unreviewed - Return patterns that have not been human-reviewed yet (no reviewed_by). Sorted low-confidence first, then needs_human_review flagged, then alpha. Use during Phase 3 review to pick the next pattern to examine. Endpoint: https://mcp.saferagenticai.org/mcp
- review_stats - Coverage stats: total patterns, reviewed %, per-suite and per-confidence breakdown. Surfaces load-time validation issue count. Endpoint: https://mcp.saferagenticai.org/mcp
- 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 all consumers of a given pattern. Endpoint: https://mcp.saferagenticai.org/mcp
- list_operational_heuristics - List operational heuristics distilled from production agentic AI deployment (Claude Code, Rewind). These are cross-cutting safety principles discovered through building and operating AI agents, mapped to framework suites. Optional filters: suite_id (heuristics relevant to a specific suite), query (keyword search across titles and principles). Separate from the normative pattern layer — different category of knowledge. Endpoint: https://mcp.saferagenticai.org/mcp
- 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 production deployment, design patterns, anti-patterns, and discovery narrative. Endpoint: https://mcp.saferagenticai.org/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.NellInc
- Version: 0.3.4
- Runtime: Pypi
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 4, 2026
- Source: https://registry.modelcontextprotocol.io